---
title: "Reviewed AI Agent Definitions: roles, prompts & source files · Undominated.ai"
canonical: https://undominated.ai/agents/
description: "Explore 401 selected AI agent definitions with original source reviews, selection reasons, limitations and practical setup guidance."
---

# Reviewed AI Agent Definitions: roles, prompts & source files · Undominated.ai

> Explore 401 selected AI agent definitions with original source reviews, selection reasons, limitations and practical setup guidance.

THE AI TOOLKIT / AGENTS

# Agents. A clear role. A reviewable brief.

Find reusable agent definitions for real project work. Inspect the role, expected output and review notes, then reuse an attributed definition where its licence allows it.

 [Explore the selection ↓](#catalogue)[What we checked ↗](#screening)

 REVIEWED SELECTION selected role definitions 401
 distinct publishers 33
 supporting source URLs 773

Reviewed 2026-10-14 Original notes. Linked evidence.

 **Selected for a reason. Reviewed within a stated scope.** Every entry includes our own findings and limitations. Source review is not a runtime test, a security certificate or proof of a universal “best.”
 Build your toolkit [AI Tools ↗](/tools/)[Skills](/skills/)[Agents](/agents/)[MCP Servers](/mcp-servers/)[Workflows](/workflows/)

01 / START WITH THE JOB

## What are you working on?

Explore a category, then refine your shortlist. All categories are available in the filters.

 104 selected **Evidence review** Explore this category → 26 selected **Testing and review** Explore this category → 19 selected **Security review** Explore this category → 13 selected **Operations and reliability** Explore this category → 11 selected **Infrastructure and delivery** Explore this category → 11 selected **Security and governance** Explore this category →

PLAN THE HANDOFF

## Put the resources to work.

[Explore 88 workflows →](https://undominated.ai/workflows/)

Task briefs, working sheets and acceptance checks. Suggested plans; each resource needs its own setup.

 [Review a change before merging ↗](https://undominated.ai/workflows/#review-a-change)[Investigate a browser regression ↗](https://undominated.ai/workflows/#debug-a-browser-regression)[Investigate a slow PostgreSQL query ↗](https://undominated.ai/workflows/#investigate-a-postgres-query)[Document an API or codebase ↗](https://undominated.ai/workflows/#document-an-api)[Investigate an application incident ↗](https://undominated.ai/workflows/#investigate-an-incident)[Plan an interface from code and design ↗](https://undominated.ai/workflows/#plan-an-interface)

BUILT BY UNDOMINATED

## Evidence tools you can inspect.

Original source, MIT licence and complete downloads. Each review names the checks performed and their limits.

 - [3D parallelism architect ↗](/agents/undominated-3d-parallelism-architect/) Architects balanced 3D parallelism configurations (TP, PP, DP, SP) for massive LLM serving clusters.
- [Adversarial Red Teamer ↗](/agents/undominated-adversarial-red-teamer/) Classifies supplied reports of prompt-injection and jailbreak failures. It does not generate bypasses or run attacks.
- [Agent cascade failure auditor ↗](/agents/undominated-agent-cascade-failure-auditor/) Audits multi-agent autonomous chains for failure cascades, hallucinated handoffs, and infinite retry loops.
- [Agent State Budget Architect ↗](/agents/undominated-agent-state-budget-architect/) Architects conversation state pruning, sliding context windows, and tool output summarization to control multi-turn token costs.
- [Agent trajectory pruning specialist ↗](/agents/undominated-trajectory-pruning-specialist/) Multi-turn log auditor specializing in identifying conversational bloat, redundant tool executions, memory leaks, and obsolete context across agent trajectories.
- [Agent workflow economist ↗](/agents/undominated-agent-workflow-economist/) Autonomous agent economist specializing in multi-step agent orchestration efficiency, tool schema minimization, function call consolidation, and token-preserving memory architectures.
- [AI resource curator ↗](/agents/undominated-resource-curator/) Review skills, agents and MCP servers against a concrete use case, with pinned identity, rights and runtime evidence.
- [Attention Architecture Economist ↗](/agents/undominated-attention-architecture-economist/) Models serving economics and hardware footprint trade-offs across Multi-Head Attention (MHA), Grouped-Query Attention (GQA), and Multi-Head Latent Attention (MLA).
- [Attention Sink Custodian ↗](/agents/undominated-attention-sink-custodian/) Manages initial token attention sink preservation and sliding window buffers in infinite-horizon streaming generation.
- [Batch pipeline architect ↗](/agents/undominated-batch-pipeline-architect/) Systems architect specializing in asynchronous batch inference pipelines, SLA deadline management, partial batch ingestion, and automated synchronous fallback cascades.
- [Benchmark rigor auditor ↗](/agents/undominated-benchmark-rigor-auditor/) Evaluation integrity specialist auditing public benchmark leaderboards for test set contamination, cherry-picked task splits, and uncalibrated significance claims.
- [Cache retention evaluator ↗](/agents/undominated-cache-retention-evaluator/) Audits needle-in-a-haystack retrieval accuracy under aggressive KV cache compression strategies.
- [Canary Rollout Commander ↗](/agents/undominated-canary-rollout-commander/) Orchestrates traffic splitting, statistical drift detection, and automated rollbacks for model migrations.
- [Chunked Prefill Tuner ↗](/agents/undominated-chunked-prefill-tuner/) Calibrates chunked prefill batch parameters to achieve target ITL p99 while maintaining prefill throughput.
- [Comparison editor ↗](/agents/undominated-comparison-editor/) Edit model-comparison copy so ties, same-seller tiers and dropped requirements are not published as dominance.
- [Constrained Decoding Optimizer ↗](/agents/undominated-constrained-decoding-optimizer/) Optimizes JSON schema compilation, regex FSM caching, and token masking to maximize structured output throughput.
- [Context parallelism planner ↗](/agents/undominated-context-parallelism-planner/) Plans context-parallel serving topologies for 1M+ token context windows using Ring and Ulysses algorithms.
- [Continuous Eval Guardian ↗](/agents/undominated-continuous-eval-guardian/) Maintains continuous regression evaluation harnesses across production endpoints to detect silent capability degradation.
- [Crawl auditor ↗](/agents/undominated-crawl-auditor/) Review a sitemap or llms.txt before publication, so an English-only path is not locale-prefixed and a markdown link names a file that was written.
- [Delivery-class reviewer ↗](/agents/undominated-delivery-class-reviewer/) Review a dominance sentence before it treats batch delivery, or a model's own other delivery, as a like-for-like beater.
- [Disaggregated Serving Architect ↗](/agents/undominated-disaggregated-serving-architect/) Designs separate prefill and decode GPU clusters connected via RDMA to eliminate TTFT and ITL scheduling interference.
- [Distributed Context Engineer ↗](/agents/undominated-distributed-context-engineer/) Architects sequence-parallel, RingAttention, and context-parallel clusters for million-token inference pipelines.
- [Draft Model Calibrator ↗](/agents/undominated-draft-model-calibrator/) Aligns draft model tokenizer, temperature, and logit distributions with the verifier model to maximize acceptance rates.
- [Draft verification auditor ↗](/agents/undominated-draft-verification-auditor/) Profiles draft verification kernels to prevent compute overhead from outpacing verification gains.
- [Dynamic Routing Economist ↗](/agents/undominated-dynamic-routing-economist/) Architects real-time cost-and-latency aware multi-provider routing proxies that arbitrage spot price shifts.
- [Edge AI deployment architect ↗](/agents/undominated-edge-ai-deployment-architect/) Sizes models for edge hardware (Apple Silicon, mobile NPUs, local workstations) to eliminate cloud API spend.
- [Enterprise Compliance Guardian ↗](/agents/undominated-enterprise-compliance-guardian/) Audits Zero Data Retention (ZDR), HIPAA, SOC2, and sovereign data boundary commitments across commercial AI providers.
- [Enterprise compliance officer ↗](/agents/undominated-enterprise-compliance-officer/) Enterprise compliance and regulatory risk auditor evaluating AI inference pipelines against GDPR data sovereignty, EU AI Act risk classifications, HIPAA BAA requirements, and SOC 2 Type II controls.
- [Eval harness auditor ↗](/agents/undominated-eval-harness-auditor/) Audit LLM evaluation harnesses, judge prompt rubrics, scoring determinism, and benchmark data hygiene to eliminate evaluation leaks and spurious rankings.
- [Evidence reviewer ↗](/agents/undominated-evidence-reviewer/) Independently challenge numerical claims using source identity, denominator reconstruction and repeatable calculations.
- [Expert Load Balancer Auditor ↗](/agents/undominated-expert-load-balancer-auditor/) Monitors router entropy, expert skew, and load balancing auxiliary loss regularization in production MoE models.
- [Failover router architect ↗](/agents/undominated-failover-router-architect/) Systems resilience architect designing active-active multi-provider inference topologies with zero-loss retries, automated circuit breaking, and cross-region failover.
- [GPU Footprint & Sharding Architect ↗](/agents/undominated-gpu-footprint-calculator/) Calculates required GPU VRAM, tensor parallelism sharding (TP=2, 4, 8), and minimum cluster configurations for hosting open-weight models.
- [GPU Utilization Optimizer ↗](/agents/undominated-gpu-utilization-optimizer/) Implements autoscaling, sleep modes, and batch backfilling to maximize hardware utilization and eliminate idle power waste.
- [Graph RAG Cost Optimizer ↗](/agents/undominated-graph-rag-cost-optimizer/) Tunes entity extraction prompts and graph traversal depths to balance retrieval precision and token spend.
- [Guardrail Overhead & Latency Analyst ↗](/agents/undominated-guardrail-overhead-analyst/) Analyzes the throughput, latency, and financial token overhead of enterprise AI safety and moderation layers.
- [Hardware Infrastructure Planner ↗](/agents/undominated-hardware-infrastructure-planner/) Sizes on-premise GPU clusters based on enterprise peak and off-peak token demand profiles and CapEx payback models.
- [Hierarchical Memory Architect ↗](/agents/undominated-hierarchical-memory-architect/) Designs multi-tiered memory architectures combining working memory, episodic summaries, and graph knowledge.
- [Hybrid SSM serving architect ↗](/agents/undominated-hybrid-ssm-serving-architect/) Architects hybrid Transformer-Mamba/SSM inference pipelines for extreme token throughput.
- [In-Context Example Pruner ↗](/agents/undominated-in-context-example-pruner/) Audits the marginal accuracy contribution of few-shot exemplars and prunes low-ROI examples to trim token costs.
- [Indirect Injection Defender ↗](/agents/undominated-indirect-injection-defender/) Designs untrusted data isolation boundaries and document sanitization filters to prevent indirect prompt injection.
- [Inference CI/CD Architect ↗](/agents/undominated-inference-cicd-architect/) Integrates model quality, latency, and cost regression gates into continuous integration and automated deployment pipelines.
- [Inference Firewall Engineer ↗](/agents/undominated-inference-firewall-engineer/) Architects low-latency security firewalls, prompt injection classifiers, and rate limiters at the API gateway layer.
- [Inference Scaling Strategist ↗](/agents/undominated-inference-scaling-strategist/) Analyzes test-time compute scaling laws, verifier passes, and search budgets to optimize accuracy per dollar spend.
- [Inference SLO Gate Architect ↗](/agents/undominated-slo-gate-architect/) Defines and enforces strict latency, availability, and error budget SLO gates for production AI gateways.
- [Inference SRE architect ↗](/agents/undominated-inference-sre-architect/) Designs production observability, SLO alert thresholds, and automated traffic shedding for inference platforms.
- [Judge Model Calibrator ↗](/agents/undominated-judge-model-calibrator/) Calibrates LLM judge prompts with few-shot calibration anchors to eliminate position bias and rating drift.
- [KV eviction policy architect ↗](/agents/undominated-kv-eviction-policy-architect/) Architects dynamic KV cache pruning and eviction policies under strict hardware VRAM limits.
- [Library intake editor ↗](/agents/undominated-library-intake-editor/) Decide whether a skill, agent profile, or MCP server belongs in the public install set, using pinned identity, a licence, and a real checker or an explicit reason it has none.
- [Licence derivation auditor ↗](/agents/undominated-licence-derivation-auditor/) Open-source legal and IP compliance specialist auditing fine-tuning data lineage, synthetic data derivation rights, model weight inheritance, and commercial redistribution boundaries.
- [LLM security red teamer ↗](/agents/undominated-llm-security-red-teamer/) Designs adversarial jailbreak probes and evaluates model alignment under automated attacks.
- [Long context bandwidth auditor ↗](/agents/undominated-long-context-bandwidth-auditor/) Audits inter-node network requirements to guarantee communication is fully masked by attention compute.
- [Low-bit fidelity auditor ↗](/agents/undominated-low-bit-fidelity-auditor/) Audits mathematical reasoning and coding benchmarks under aggressive sub-4-bit quantization.
- [Merged capability auditor ↗](/agents/undominated-merged-capability-auditor/) Audits merged model checkpoints for catastrophic forgetting and multi-task capability collisions.
- [Mixed Precision Architect ↗](/agents/undominated-mixed-precision-architect/) Designs layer-wise quantization profiles balancing perplexity retention against memory savings across FP4, FP8, and INT4.
- [Model Cascade Architect ↗](/agents/undominated-model-cascade-architect/) Architects multi-tier model cascading pipelines with confidence-gated fallback routing to optimize cost-per-task.
- [Model merging architect ↗](/agents/undominated-model-merging-architect/) Architects zero-training model merges using TIES, DARE, and SLERP to combine specialized domain models.
- [Model Merging Evaluator ↗](/agents/undominated-model-merging-evaluator/) Evaluates merged model weights across benchmark suites to prevent catastrophic interference and capability loss.
- [Model migration planner ↗](/agents/undominated-migration-planner/) Plan workload-specific model migrations while preserving required capabilities and defining observable rollback criteria.
- [Model Provenance Investigator ↗](/agents/undominated-model-provenance-investigator/) Investigates training data lineage, open-weights licensing boundaries, and attribution requirements across model releases.
- [MoE Serving Architect ↗](/agents/undominated-moe-serving-architect/) Specializes in Expert Parallelism (EP), Tensor Parallelism (TP), and expert capacity factor calibration for large MoE clusters.
- [Multi-agent systems economist ↗](/agents/undominated-multi-agent-systems-economist/) Designs multi-agent workflows to minimize redundant inter-agent chatter and prevent runaway token loops.
- [Multi-LoRA Serving Specialist ↗](/agents/undominated-multi-lora-serving-specialist/) Configures multi-adapter serving clusters serving hundreds of fine-tuned LoRA adapters concurrently on a single base model.
- [Multi-Needle Retrieval Validator ↗](/agents/undominated-retrieval-needle-validator/) Generates and evaluates multi-needle retrieval benchmarks to expose lost-in-the-middle context blindness in long-context models.
- [Multimodal streaming architect ↗](/agents/undominated-multimodal-streaming-architect/) Architects real-time streaming audio and video inference pipelines with bounded lookahead latency.
- [NCCL topology auditor ↗](/agents/undominated-nccl-topology-auditor/) Audits NVLink, NVSwitch, and InfiniBand rail-optimized communication topologies for distributed serving.
- [On-device performance auditor ↗](/agents/undominated-on-device-performance-auditor/) Audits thermal throttling, unified memory pressure, and battery consumption on consumer edge devices.
- [Population reviewer ↗](/agents/undominated-population-reviewer/) Review a count, rank or correlation before publication, so the computed rows are the population the sentence names.
- [Preference alignment auditor ↗](/agents/undominated-preference-alignment-auditor/) Audits reward models and preference datasets for length bias, sycophancy, and mode collapse.
- [Pricing source reviewer ↗](/agents/undominated-pricing-source-reviewer/) Review a provider price feed before any rate is admitted, including units, currency, tiers and prose quotes that are not USD.
- [Prompt Compression Economist ↗](/agents/undominated-prompt-compression-economist/) Audits client-side prompt compression pipelines to minimize billed input token volume without losing semantic fidelity.
- [Prompt firewall architect ↗](/agents/undominated-prompt-firewall-architect/) Constructs low-latency pre-inference guard firewalls to intercept injection and extraction attacks.
- [Provider Resilience Architect ↗](/agents/undominated-provider-resilience-architect/) Designs automatic failover, circuit breaking, and idempotency guarantees across redundant inference providers.
- [Quantization Evaluation Reviewer ↗](/agents/undominated-quantization-eval-reviewer/) Audits LLM evaluation protocols to verify whether published benchmark scores match the model's serving quantization or upstream unquantized weights.
- [Quantized KV Cache Calibrator ↗](/agents/undominated-quantized-kv-cache-calibrator/) Calibrates per-channel and per-group scale factors for sub-8-bit KV caches to prevent long-context reasoning drift.
- [Quote identity reviewer ↗](/agents/undominated-quote-identity-reviewer/) Review a proposed join between a vendor quote and a catalogue model, and refuse any match that is not exact.
- [RAG Context Economist ↗](/agents/undominated-rag-context-economist/) Optimizes context window packing, chunk overlap boundaries, and token budgets for enterprise RAG systems.
- [Reasoning budget planner ↗](/agents/undominated-reasoning-budget-planner/) Architect agent that models reasoning token expenditure, dynamically calibrates thinking budgets across prompt difficulty classes, and prevents runaway cost expansion.
- [Reasoning Trace Compressor ↗](/agents/undominated-reasoning-trace-compressor/) Audits chain-of-thought reasoning traces to detect circular deliberation loops, repetitive tokens, and distillation opportunities.
- [Reasoning verifier auditor ↗](/agents/undominated-reasoning-verifier-auditor/) Audits process reward model verifiers for false-positive validation passes and search path collapse.
- [Recurrent state auditor ↗](/agents/undominated-recurrent-state-auditor/) Audits recurrent hidden state numerical drift and precision degradation during continuous streaming.
- [Regulatory Compliance Officer ↗](/agents/undominated-regulatory-compliance-officer/) Audits AI deployments for EU AI Act, US Executive Order, and ISO 42001 governance and transparency frameworks.
- [Resource release verifier ↗](/agents/undominated-release-verifier/) Independently verify packaged resources, clean installation and meaningful public availability after a release.
- [Router Threshold Calibrator ↗](/agents/undominated-router-threshold-calibrator/) Calibrates draft model confidence thresholds to balance API cost savings against quality degradation.
- [Safety Refusal Calibrator ↗](/agents/undominated-safety-refusal-calibrator/) Calibrates safety classifier thresholds to minimize benign query refusals while maintaining strict compliance boundaries.
- [Schema Contract Verifier ↗](/agents/undominated-schema-contract-verifier/) Verifies tool schemas, argument enums, and parameter constraints to prevent runtime validation failures.
- [Serving Engine Tuner ↗](/agents/undominated-serving-engine-tuner/) Specializes in tuning vLLM, SGLang, and TensorRT-LLM parameters including chunked prefill, radix trees, and batching scheduling.
- [Sovereign AI TCO auditor ↗](/agents/undominated-sovereign-ai-tco-auditor/) Models national sovereign AI cluster CapEx/OpEx, power grid contracts, and 5-year hardware lifecycle TCO.
- [Sparse Attention Evaluator ↗](/agents/undominated-sparse-attention-evaluator/) Audits accuracy retention and memory bandwidth reduction across Native Sparse Attention (NSA) and block-sparse mechanisms.
- [Speculative Architecture Engineer ↗](/agents/undominated-speculative-architecture-engineer/) Architects speculative decoding topologies including Multi-Token Prediction (MTP), Medusa heads, and Eagle tree verifiers.
- [Speculative tree architect ↗](/agents/undominated-speculative-tree-architect/) Designs multi-candidate speculative draft trees to maximize generation speed on constrained GPUs.
- [Stack cost optimizer ↗](/agents/undominated-stack-cost-optimizer/) Full-stack AI system cost optimization specializing in multi-tier cascading, retrieval pruning, speculative drafting, and prompt caching to slash API spend while preserving benchmark quality.
- [Streaming Reliability Engineer ↗](/agents/undominated-streaming-reliability-engineer/) Specializes in Server-Sent Events (SSE) connection health, keep-alive heartbeat spacing, and client reconnection handling.
- [Sustainable inference architect ↗](/agents/undominated-sustainable-inference-architect/) Optimizes AI workload scheduling for renewable power availability and lowest carbon footprint.
- [Synthetic curation architect ↗](/agents/undominated-synthetic-curation-architect/) Architects synthetic training dataset filtering pipelines to eliminate contamination and redundancy.
- [Synthetic judge calibrator ↗](/agents/undominated-synthetic-judge-calibrator/) Evaluation scientist specializing in LLM-as-a-judge alignment, position bias mitigation, length normalization, and inter-rater agreement calibration against human experts.
- [Tail latency auditor ↗](/agents/undominated-tail-latency-auditor/) Profiles p99.9 tail latencies to eliminate micro-stalls caused by garbage collection and multi-tenant contention.
- [Tail latency SLA auditor ↗](/agents/undominated-tail-latency-sla-auditor/) Production observability auditor comparing provider Service Level Agreements against measured p95/p99 tail latency, serverless cold starts, and outage windows.
- [Ternary inference architect ↗](/agents/undominated-ternary-inference-architect/) Architects native ternary and low-bit compute pipelines for low-energy edge and cloud inference.
- [Test-time compute economist ↗](/agents/undominated-test-time-compute-economist/) Optimizes test-time compute allocation across search width and reasoning depth to balance accuracy and cost.
- [Tool Registry Architect ↗](/agents/undominated-tool-registry-architect/) Designs dynamic tool indexing and semantic retrieval to keep system prompt tokens minimal across large API catalogs.
- [Vision token economist ↗](/agents/undominated-vision-token-economist/) Optimizes vision patch resolution and temporal subsampling to minimize multi-modal token billing.
- [VRAM Fragmentation Analyst ↗](/agents/undominated-vram-fragmentation-analyst/) Analyzes PagedAttention block size allocation, CUDA graph memory pools, and virtual memory fragmentation to prevent GPU OOMs.

02 / THE SELECTION

## Find a fit. Read the reasoning.

Alphabetical by default. Every match is shown. Compare up to three before opening a full review.

 Filter these results Task Every category Accessibility Agent development API architecture API engineering Application integration Architecture and decisions Architecture documentation Browser and performance Bug reproduction Build and packaging Build and runtime diagnostics Change communication Change planning Changelog editing CI diagnosis CI maintenance Cloud architecture Code maintenance Code review Codebase understanding Creative tooling Cross-platform applications Data analysis Data and analytics Data and retrieval Data modeling Data visualization Database administration Database architecture Database operations Decision support Design and data Design systems Developer education Developer tools Diagnostics Documentation Documentation and knowledge Documentation contribution Documentation editing Embedded software Enterprise applications Evaluation Evaluation workflows Evidence review Finance operations Framework development Game audio Game design Game development Game server development Geospatial automation Geospatial design Geospatial operations Geospatial quality Identity systems Infrastructure Infrastructure and delivery Infrastructure orchestration Interactive programming Language and communication Language development Language-specific review Machine learning operations Maintenance planning Marketing analysis Mathematics Media engineering Meeting records Migration Mobile applications Model development Model evaluation Modernization and specifications Network diagnostics Observability Operations Operations and reliability Payments Performance Persistent work coordination Planning and delivery Planning workflow components Programming Project planning Pull-request labels Pull-request review Realtime systems Repository assessment Research and product Resilience testing Rust maintenance Sales enablement Security and governance Security and privacy Security operations Security query drafting Security review Security workflow components Service integration Spatial analysis System administration Systems performance Testing and reliability Testing and review Workflow integration Publisher Every publisher 0xSteph Affaan Mustafa affaan-m agency Agency Agents Agency Agents community Anthropic anthropics Astral Software Inc. awslabs ecc github GitHub GitHub community GitHub Next GitHub partners HashiCorp Microsoft Microsoft Corporation msitarzewski OpenAI Seth Hobson Stripe Svelte Trail of Bits Trail of Bits (Omar Inuwa) Undominated.ai Vercel voltagent VoltAgent wshobson wshobson/agents Zoom Documented host Every host Claude Code Codex Cursor GitHub Copilot GitHub Copilot CLI Grok Build Kimi Code Not established OpenCode VS Code Order Name · A–Z Name · Z–A Publisher · A–Z Review date · newest first
 Runtime, access and execution Runtime / platform Every environment Bash Docker / containers Node.js Not established Python / uv Rust toolchain Access described by source Every access scope Browser session Cloud account or infrastructure Database access Host-controlled permissions Local files Not established Read-only scope documented Repository access Execution path Every execution path Host-defined

Labels summarise reviewed source wording. A local process can still send data to external services. Read each review's prerequisites and permissions; these filters do not certify compatibility or enforce access.

**401** of 401 selected definitions

 Reset filters Copy this view ↗

 Resource / purpose Our selection note Use & inspect Compare

Migration · GitHub community

### [.NET solution upgrade planner](/agents/github-dotnet-upgrade/)

A solution-upgrade reference organizing framework discovery, dependency order and validation checkpoints.

 dotnet dependency-order upgrade-validation

**Why we selected it**It sequences independent libraries before shared components and application projects to expose compatibility issues incrementally.

**Weigh up**The embedded shell examples and netstandard migration rule are not universally appropriate; current support windows, consumer compatibility and multi-targeted projects require a real assessment.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-dotnet-upgrade/) Upstream setup linked MIT
 Compare .NET solution upgrade planner Add

Accessibility · github

### [Accessibility Expert](/agents/github-accessibility/)

Guides web accessibility work through keyboard, focus, screen-reader, zoom and contrast checks, with developer examples and a structured review checklist.

 wcag keyboard aria

**Why we selected it**Operating rules require an a11y pre-check before code, verification steps with edits, and rejecting requests that remove focus outlines or otherwise reduce access.

**Weigh up**The definition can edit files and run commands; it is broader than an advisory accessibility audit.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-accessibility/) Attributed definition available MIT
 Compare Accessibility Expert Add

Accessibility · github

### [Accessibility Runtime Tester](/agents/github-accessibility-runtime-tester/)

Exercises keyboard journeys, focus changes and form errors, then records reproducible accessibility findings and retest steps.

 keyboard navigation focus management forms

**Why we selected it**Requires observed runtime behaviour and explicitly rejects a Lighthouse pass as proof of accessibility.

**Weigh up**The body expects browser automation but the original allowlist does not enable the preferred Chrome DevTools or Playwright MCP tools. Configure and allow those tools in a working copy first.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-accessibility-runtime-tester/) Attributed definition available MIT
 Compare Accessibility Runtime Tester Add

Design and data · Agency Agents community

### [Accessible data visualization engineer](/agents/agency-engineering-data-visualization-engineer/)

A chart-design profile matching the analytical question to honest encodings and accessible interaction.

 charts accessibility uncertainty

**Why we selected it**It distinguishes zero-based bar lengths from deliberately bounded line-chart axes and asks whether aggregation hides multimodal data.

**Weigh up**SVG/canvas/WebGL count thresholds and frame-rate targets are heuristics, not measured limits; population prevalence claims and palette names do not prove accessibility for a specific chart.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-data-visualization-engineer/) Attributed definition available MIT
 Compare Accessible data visualization engineer Add

Security operations · VoltAgent

### [Active Directory security posture reviewer](/agents/voltagent-ad-security-reviewer/)

An AD review profile tracing privilege, delegation, protocol and service-account risks into a remediation plan.

 active-directory delegation authentication

**Why we selected it**The review distinguishes privileged-group membership from orphaned ACLs, delegation and service-account exposure.

**Weigh up**This is not a read-only tool profile: it declares Bash/Edit/Write and requests implementation scripts. A checklist does not prove exploitability or compliance.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-ad-security-reviewer/) Attributed definition available MIT
 Compare Active Directory security posture reviewer Add

Media engineering · Agency Agents community

### [Adaptive video delivery engineer](/agents/agency-engineering-video-streaming-engineer/)

A streaming-design profile connecting encoding, packaging, device playback and measured quality of experience.

 hls dash qoe

**Why we selected it**It treats segment length as a latency/cache/request-overhead tradeoff and requires testing the protected playback path on actual devices.

**Weigh up**The ffmpeg example writes to the null muxer and does not create the v360.mp4/v720.mp4 files consumed by the next command; it is an illustration, not an executable end-to-end pipeline. Storage and latency figures are not measured guarantees.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-video-streaming-engineer/) Upstream setup linked MIT
 Compare Adaptive video delivery engineer Add

Architecture and decisions · github

### [Adr Generator](/agents/github-adr-generator/)

Turns a concrete architecture decision into a numbered ADR with context, alternatives, consequences and references, asking for missing decision inputs first.

 adr docs-adr-path template

**Why we selected it**It will not start until title, context, decision, alternatives, and stakeholders are present, and it tells the agent to ask rather than invent those fields.

**Weigh up**The /docs/adr/ path is ambiguous outside its expected project layout; choose an explicit repository-relative output directory before use.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-adr-generator/) Attributed definition available MIT
 Compare Adr Generator Add

Security review · Trail of Bits

### [Adversarial modeler](/agents/trailofbits-adversarial-modeler/)

Pins Trail of Bits' differential-review agent that models high-risk changes and says not to run on low or medium risk diffs.

 security review diff

**Why we selected it**The catalogue has the differential-review skill and not this adversarial-modeler agent.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-adversarial-modeler/) Install command in review CC-BY-SA-4.0
 Compare Adversarial modeler Add

Agent development · Affaan Mustafa

### [Agent evaluator](/agents/ecc-agent-evaluator/)

Scores an agent answer on five axes and requires evidence for the score.

 evaluation rubric agents

**Why we selected it**The role scores another agent's answer and says not to re-perform the original task.

**Weigh up**The report must match scripts/evaluate.py, which is not contained in this file.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-agent-evaluator/) Attributed definition available MIT
 Compare Agent evaluator Add

Agent development · VoltAgent

### [Agent Memory Curator](/agents/voltagent-memory-curator/)

Maintains a confirmed agent memory store with dated facts, visible corrections and user-reviewed pruning proposals.

 agent memory corrections provenance

**Why we selected it**Requires confirming the existing store rather than creating a competing memory system, and forbids storing secrets.

**Weigh up**The file is a curation procedure, not a memory database, recall service or cross-session hook installer.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/voltagent-memory-curator/) Attributed definition available MIT
 Compare Agent Memory Curator Add

Agent development · Anthropic

### [Agent SDK verifier (Python)](/agents/anthropic-agent-sdk-verifier-py/)

Checks a Python Claude Agent SDK app for SDK usage, environment setup and secret handling, and reports PASS, PASS WITH WARNINGS or FAIL.

 claude-agent-sdk python verification

**Why we selected it**The environment checks are concrete: .env.example with ANTHROPIC_API_KEY, .env listed in .gitignore, and no API key hardcoded in source files.

**Weigh up**No tools field is declared, so in Claude Code it inherits every tool available to subagents, including write and shell tools.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-agent-sdk-verifier-py/) Attributed definition available Apache-2.0
 Compare Agent SDK verifier (Python) Add

Agent development · anthropics

### [Agent Sdk Verifier Ts](/agents/anthropic-agent-sdk-verifier-ts/)

Checks a TypeScript Claude Agent SDK project against its configuration, current SDK guidance, type-checking results and environment-variable hygiene before a structured readiness report.

 claude-agent-sdk typescript claimed-tool-execution

**Why we selected it**Checklist is SDK-specific: package name, "type":"module", engines, MCP/subagent/permissions patterns, ANTHROPIC_API_KEY in .env.example and .env gitignore.

**Weigh up**No tool allowlist is declared, so documentation retrieval and shell execution use inherited host permissions.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-agent-sdk-verifier-ts/) Attributed definition available Apache-2.0
 Compare Agent Sdk Verifier Ts Add

Agent development · VoltAgent

### [Agent-Log Knowledge Synthesizer](/agents/voltagent-knowledge-synthesizer/)

Finds recurring patterns in an explicitly scoped set of agent logs and writes cited findings with counts derived from the actual files.

 agent logs evidence synthesis workflow learning

**Why we selected it**Stops on an empty or unspecified source scope and distinguishes recurring evidence from a single unconfirmed anecdote.

**Weigh up**It cannot run analytics jobs or query remote services with its declared file tools; inputs must be accessible files.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/voltagent-knowledge-synthesizer/) Attributed definition available MIT
 Compare Agent-Log Knowledge Synthesizer Add

Repository assessment · GitHub community

### [AgentRC readiness report renderer](/agents/github-ai-readiness-reporter/)

Turns actual AgentRC assessment JSON and repository context into a static HTML report with policy-aware findings and remediation priorities.

 AgentRC repository configuration static reports

**Why we selected it**It requires real JSON input and retains that input in the report for inspection.

**Weigh up**The source invokes an unpinned GitHub package through npx and depends on a sibling HTML template; no standalone bundle is offered. Pin and review the executable separately.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/github-ai-readiness-reporter/) Upstream setup linked MIT
 Compare AgentRC readiness report renderer Add

Security and governance · awslabs

### [AI-DLC Compliance Agent](/agents/awslabs-aidlc-compliance/)

Organizes data classification, requirement-to-control mapping and compliance evidence into an advisory role within an AI-DLC project.

 control mapping data classification privacy

**Why we selected it**Connects each proposed control to its technical implementation and required evidence such as logs, configuration and test results.

**Weigh up**Requires the AI-DLC framework, active-space policies and resolved knowledge references; the raw persona download is not a complete installation.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/agents/awslabs-aidlc-compliance/) Attributed definition available MIT-0
 Compare AI-DLC Compliance Agent Add

Documentation · wshobson

### [API Documenter](/agents/wshobson-api-documenter/)

Builds API documentation as a contract-first artefact — OpenAPI 3.1 specifications, SDK generation and developer portals — with documentation-driven testing that validates examples and responses against the schema.

 API documentation OpenAPI contract-first

**Why we selected it**Treats the OpenAPI specification as the source of truth: contract-driven development, schema-validated examples, and documentation-driven testing with mock servers generated from the spec.

**Weigh up**A capability-list persona without an output schema or evidence gate; it does not itself verify that generated docs match a running API.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/wshobson-api-documenter/) Attributed definition available MIT
 Compare API Documenter Add

Architecture and decisions · Agency Agents

### [API Platform Engineer](/agents/agency-api-platform-engineer/)

Designs contract-first public APIs with a backward-compatibility check on every change, forcing breaking changes through versioning and a humane deprecation runway.

 API design OpenAPI breaking changes

**Why we selected it**Default requirement that every API change is checked against the contract for backward compatibility, with breaking changes routed through versioning and deprecation, never silent breaks.

**Weigh up**Convention choices (naming case, pagination style) are consistency mandates; adopting projects must pick and record their own standards.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-api-platform-engineer/) Attributed definition available MIT
 Compare API Platform Engineer Add

Documentation and knowledge · wshobson

### [API Reference Builder](/agents/wshobson-reference-builder/)

Builds a versioned API or configuration reference from an inventory of the implementation’s public interfaces.

 api-reference configuration documentation

**Why we selected it**Quality standards say every public interface is documented and that accuracy is verified against the implementation.

**Weigh up**The Haiku model alias and absent tool allowlist are host-specific configuration choices.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-reference-builder/) Attributed definition available MIT
 Compare API Reference Builder Add

System administration · GitHub community

### [Arch Linux maintenance guide](/agents/github-arch-linux-expert/)

An Arch-specific administration profile for rolling updates and package-state diagnosis.

 arch-linux pacman systemd

**Why we selected it**It distinguishes full rolling upgrades from unsupported partial-upgrade patterns and inspects recent package changes first.

**Weigh up**The declared shell/edit tools can change the real machine; no system snapshot, privilege boundary or package trust check is enforced by the Markdown.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-arch-linux-expert/) Attributed definition available MIT
 Compare Arch Linux maintenance guide Add

Architecture and decisions · anthropics

### [Architecture Critic](/agents/anthropic-architecture-critic/)

Challenges modernization designs and transformed code against actual requirements, failure paths and simpler alternatives, ending with prioritized actionable findings.

 architecture modernization adversarial-review

**Why we selected it**Separate review lenses distinguish architecture proposals from already-transformed code.

**Weigh up**Read-only shell use is an instruction; Bash remains available and must be constrained by the host.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-architecture-critic/) Attributed definition available Apache-2.0
 Compare Architecture Critic Add

Geospatial automation · Agency Agents community

### [ArcPy geoprocessing workflow designer](/agents/agency-gis-geoprocessing-specialist/)

Designs ArcPy toolbox and batch-processing workflows with parameter validation, explicit environments and lock cleanup.

 ArcPy Python toolbox batch processing

**Why we selected it**The definition calls for dependent-parameter validation and user-facing error/progress reporting before long-running processing.

**Weigh up**The source mixes legacy Data Driven Pages terminology into Pro guidance; current Esri documentation calls this Map Series and says it is not a geoprocessing toolset.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/agency-gis-geoprocessing-specialist/) Upstream setup linked MIT
 Compare ArcPy geoprocessing workflow designer Add

Migration · GitHub community

### [Arm workload migration assistant](/agents/github-arm-migration/)

An Arm migration workflow that checks source, dependency and container architecture assumptions through the Arm MCP service.

 arm64 portability containers

**Why we selected it**It distinguishes a language client package version from the corresponding server product version.

**Weigh up**Its body names learning_path_server although the embedded allowlist does not, uses a mutable latest image and mounts the workspace writable. CPU feature advice must be checked against the exact target; migration does not guarantee speedup.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-arm-migration/) Upstream setup linked MIT
 Compare Arm workload migration assistant Add

Service integration · VoltAgent

### [Authentication integration engineer](/agents/voltagent-auth-integration-engineer/)

Designs identity flows around actual providers, client types and tenant boundaries, including negative tests and staged rollout.

 authentication integration failure handling

**Why we selected it**The checklist follows assertion validation, token lifecycle, server-side data access and recovery flows rather than stopping at login success.

**Weigh up**The source is a broad design checklist, not a provider implementation or security guarantee; verify each flow against current provider/standard documentation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-auth-integration-engineer/) Attributed definition available MIT
 Compare Authentication integration engineer Add

Diagnostics · GitHub Next

### [AWF diagnosis](/agents/github-awf-diagnose/)

Fingerprints an Agentic Workflow Firewall failure, matches one finding, and reports the symptom, the finding id, and one next probe before naming a fix.

 firewall github-actions diagnostics

**Why we selected it**The procedure records unknown rather than guessing, classifies one failing boundary, and matches the narrowest finding before it names a remedy.

**Weigh up**The frontmatter has no tool allowlist. A host that grants write tools is not stopped by this file. Probes named in the catalog include docker exec, awf --version, findmnt, grep of a lock file, and gh aw logs. This review did not run them.

 Source reviewed

2 sources · 2026-10-13

[Read the full review ↗](/agents/github-awf-diagnose/) Upstream setup linked MIT
 Compare AWF diagnosis Add

Operations and reliability · GitHub

### [AWS Incident Triage](/agents/github-aws-incident-triage/)

Time-boxes an AWS alarm investigation and defaults to read-only operations.

 incident aws sre

**Why we selected it**The persona defaults to read-only work and forbids infrastructure mutation without explicit approval.

**Weigh up**No tool allowlist is declared. Enforce read-only AWS permissions; the source itself requires explicit approval before infrastructure mutation.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-aws-incident-triage/) Attributed definition available MIT
 Compare AWS Incident Triage Add

Testing and review · HashiCorp

### [AWS provider maintainer review](/agents/hashicorp-aws-provider-maintainer/)

A short review persona for AWS provider changes. It says not to open pull requests.

 terraform aws review

**Why we selected it**The file includes secrets in code, logs and version control in its review checklist.

**Weigh up**The sibling @contributor persona was not opened. This file is a checklist, not a complete provider workflow.

 Source reviewed

2 sources · 2026-10-13

[Read the full review ↗](/agents/hashicorp-aws-provider-maintainer/) Upstream setup linked MPL-2.0
 Compare AWS provider maintainer review Add

Cloud architecture · GitHub community

### [AWS serverless architecture planner](/agents/github-aws-serverless-architect/)

A serverless design profile for event flows, managed state and observable failure handling.

 aws serverless event-driven

**Why we selected it**It asks for current AWS primary guidance before recommending service patterns.

**Weigh up**Working examples are an output aspiration; IAM, quotas, retries, costs and service integrations must be validated in the target account.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-aws-serverless-architect/) Upstream setup linked MIT
 Compare AWS serverless architecture planner Add

Workflow integration · GitHub community

### [Azure Logic Apps workflow designer](/agents/github-azure-logic-apps-expert/)

A Logic Apps profile for JSON workflow definitions, connector integration and failure paths.

 logic-apps wdl azure

**Why we selected it**Its scope makes workflow definition structure and expressions explicit rather than treating integration as an opaque diagram.

**Weigh up**The gpt-4 alias and named Microsoft/Azure documentation tools may need host adaptation; connector authentication and workflow execution are not bundled.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-azure-logic-apps-expert/) Upstream setup linked MIT
 Compare Azure Logic Apps workflow designer Add

Security and governance · GitHub

### [Azure Policy analyzer](/agents/github-azure-policy-analyzer/)

Requires evidence in the report and has a guardrails heading against invented policy data.

 azure policy compliance

**Why we selected it**Guardrails forbid fabricated policy data and forbid Azure writes unless the user asks.

**Weigh up**Tools include edit, execute, and a wildcard azure-mcp/*, which is broader than the no-write guardrail.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-azure-policy-analyzer/) Attributed definition available MIT
 Compare Azure Policy analyzer Add

Infrastructure and delivery · github

### [Bicep Planning](/agents/github-bicep-plan/)

Writes Azure Bicep implementation plans as deterministic, machine-readable Markdown under a write-scope guardrail — only .bicep-planning-files/ — grounding every resource in Microsoft docs and pinning Azure Verified Module versions from their changelogs.

 Bicep Azure Verified Modules infrastructure as code

**Why we selected it**A hard write-scope guardrail: only files under .bicep-planning-files/ may be created or modified, and the plan itself is out of deployment scope — no pipelines, no processes, no next steps.

**Weigh up**A planner, not a reviewer: it produces the plan file and stops; validating or deploying the resulting Bicep is out of its declared scope.

 Source reviewed

4 sources · 2026-10-07

[Read the full review ↗](/agents/github-bicep-plan/) Attributed definition available MIT
 Compare Bicep Planning Add

Creative tooling · Agency Agents community

### [Blender add-on engineer](/agents/agency-blender-addon-engineer/)

A Blender tooling profile for asset validators, exporters and repeatable artist workflows.

 blender asset-validation export

**Why we selected it**It prefers the direct data API over context-sensitive operators and requires actionable cancellation instead of silent success.

**Weigh up**The snippets are illustrative and were not run in Blender; confirmation rules are prompt instructions, and omitted tools inherit host capabilities.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-blender-addon-engineer/) Attributed definition available MIT
 Compare Blender add-on engineer Add

Evaluation workflows · anthropics

### [Blind skill-output comparator](/agents/anthropic-skill-eval-comparator/)

Compares two anonymized task outputs against an explicit content and structure rubric, then writes a reasoned comparison JSON.

 evaluation blind comparison rubrics

**Why we selected it**The role keeps the skill identities hidden while comparing concrete output artifacts.

**Weigh up**This is an orchestrated role prompt without custom-agent YAML frontmatter; pass it to a bounded worker or adapt a separate working copy.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-skill-eval-comparator/) Attributed definition available Apache-2.0
 Compare Blind skill-output comparator Add

Modernization and specifications · anthropics

### [Business Rules Extractor](/agents/anthropic-business-rules-extractor/)

Extracts domain calculations, validation and policy rules from legacy code into concrete test scenarios with source references and uncertainty questions.

 legacy code business rules specifications

**Why we selected it**Separates business rules from infrastructure behavior and requires exact code locations.

**Weigh up**Observed legacy behavior is not automatically the business behavior that should be retained.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-business-rules-extractor/) Attributed definition available Apache-2.0
 Compare Business Rules Extractor Add

Security review · Trail of Bits

### [C review worker](/agents/trailofbits-c-review-worker/)

Pins the c-review producing worker that reads source, writes one part file, and states that it has no shell.

 c review worker

**Why we selected it**The catalogue has the c-review skill and not this producing worker.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-c-review-worker/) Install command in review CC-BY-SA-4.0
 Compare C review worker Add

Language development · Seth Hobson

### [C systems developer](/agents/wshobson-c-pro/)

A compact C profile centered on ownership, system-call errors and measured performance.

 c memory-ownership systems

**Why we selected it**The short checklist prioritizes allocation ownership and checking system-call return values.

**Weigh up**Every malloc needs free is shorthand rather than a lifetime proof; no compiler, test framework, debugger or Valgrind execution is supplied.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-c-pro/) Attributed definition available MIT
 Compare C systems developer Add

Testing and review · affaan-m

### [C# Reviewer](/agents/ecc-csharp-reviewer/)

Reviews C# changes by running dotnet build and dotnet format verification before reading the diff, then ranks findings from SQL injection and async misuse to nullable reference types and EF Core traps.

 csharp code review dotnet

**Why we selected it**Gates the review on executed commands — dotnet build and dotnet format --verify-no-changes run before the diff is read, so findings rest on toolchain output.

**Weigh up**Closing pointers to sibling dotnet-patterns and csharp-testing skills reference companion files that are not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-csharp-reviewer/) Attributed definition available MIT
 Compare C# Reviewer Add

Build and runtime diagnostics · Affaan Mustafa

### [C++ build error resolver](/agents/ecc-cpp-build-resolver/)

Diagnoses compilation, CMake, linking and template errors through a small-edit, rebuild and test loop.

 C++ diagnostics minimal fixes

**Why we selected it**It distinguishes missing symbols, duplicate definitions, include problems and template deduction failures.

**Weigh up**Its example clang-tidy command hardcodes C++17 and truncates/suppresses diagnostics; adapt it to the actual compile database and preserve complete logs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-cpp-build-resolver/) Upstream setup linked MIT
 Compare C++ build error resolver Add

Testing and review · affaan-m

### [C++ Reviewer](/agents/ecc-cpp-reviewer/)

Reviews C++ changes by running clang-tidy and cppcheck before reading the diff, then ranks findings from raw new/delete, buffer overflows and use-after-free to format-string attacks and integer overflow on untrusted input.

 cpp code review memory safety

**Why we selected it**Leads with memory safety as the CRITICAL tier — raw new/delete, C-style arrays and strcpy/sprintf without bounds, use-after-free and dangling iterators, uninitialized reads, missing RAII — which is the correct priority order for C++ review.

**Weigh up**The closing pointer to a sibling cpp-coding-standards skill references a companion file that is not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-cpp-reviewer/) Attributed definition available MIT
 Compare C++ Reviewer Add

Architecture documentation · Seth Hobson

### [C4 component documentation synthesizer](/agents/wshobson-c4-component/)

Groups code-level documentation into components with explicit responsibilities, interfaces and source-document links.

 C4 interfaces Mermaid

**Why we selected it**It explicitly scopes each component diagram inside a single container and records external dependencies separately.

**Weigh up**The definition supplies templates but requires your code-level documents; it does not include or run the sibling C4-Code agent.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-c4-component/) Attributed definition available MIT
 Compare C4 component documentation synthesizer Add

Architecture and decisions · wshobson

### [C4 System Context Documenter](/agents/wshobson-c4-context/)

Synthesizes system and component documentation into a stakeholder-facing context diagram, actor list and external-dependency map.

 C4 architecture documentation system boundaries

**Why we selected it**Defines a full c4-context.md output covering system purpose, personas, features, journeys and external systems.

**Weigh up**Assumes container, component and system documentation are available; the file does not include those inputs or the other C4 agents.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-c4-context/) Attributed definition available MIT
 Compare C4 System Context Documenter Add

Geospatial design · Agency Agents community

### [Cartography design reviewer](/agents/agency-gis-cartography-designer/)

Plans thematic map styling, label hierarchy and layouts for a defined audience and delivery medium.

 cartography labels visual hierarchy

**Why we selected it**It separates sequential, diverging and categorical encodings and connects basemap detail to the audience and subject.

**Weigh up**The sample style JSON is descriptive, not a validated MapLibre/ArcGIS import format.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-gis-cartography-designer/) Attributed definition available MIT
 Compare Cartography design reviewer Add

Security workflow components · Anthropic

### [Claude Security code explorer](/agents/anthropic-explore/)

A Claude Security search component that maps one code path for a caller and returns file/line evidence.

 code-exploration source-evidence security-review

**Why we selected it**Repository instructions, comments, filenames and commit messages are treated as evidence rather than commands to change the task.

**Weigh up**Read-only is a prompt policy: Bash remains declared and can execute writes unless the host enforces the stated command restrictions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-explore/) Upstream setup linked Proprietary — Anthropic internal-use terms
 Compare Claude Security code explorer Add

Security workflow components · Anthropic

### [Claude Security patch generator](/agents/anthropic-patch-generator/)

A security-fix component that stages one narrow change in an orchestrator-created scratch checkout.

 security-fixes scratch-workspace patch-artifact

**Why we selected it**It locates drifted findings by snippet and symbol rather than trusting old line numbers.

**Weigh up**The source stages all scratch changes with git add -A and has Bash/Edit/Write; its workspace-name check is not an OS-level containment boundary.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-patch-generator/) Upstream setup linked Proprietary — Anthropic internal-use terms
 Compare Claude Security patch generator Add

Security workflow components · Anthropic

### [Claude Security patch verifier](/agents/anthropic-patch-verifier/)

A security-patch verifier that derives the staged diff and separates tested behavior from source-only confidence.

 patch-review staged-diff security-fixes

**Why we selected it**It rejects unstaged/untracked changes, derives the diff with external drivers disabled and checks the pre-change exploit before judging a fix.

**Weigh up**PASS is a model judgment, not a security guarantee; project tests can execute code and dependencies, and the no-edit instruction does not sandbox Bash.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-patch-verifier/) Upstream setup linked Proprietary — Anthropic internal-use terms
 Compare Claude Security patch verifier Add

Interactive programming · GitHub community

### [Clojure REPL pair programmer](/agents/github-clojure-interactive-programming/)

Reads a Clojure source file, develops and checks expressions in a live REPL, then applies the change with structural editing tools.

 Clojure REPL debugging

**Why we selected it**It requires reproducing current behaviour and checking multiple inputs before modifying files.

**Weigh up**The definition assumes a live REPL and structural editing tools but configures neither. It is not a REPL server or editor extension.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-clojure-interactive-programming/) Attributed definition available MIT
 Compare Clojure REPL pair programmer Add

Operations and reliability · GitHub community

### [Cloud and SaaS Outage Triage](/agents/github-cloud-saas-outage-triage/)

Separates upstream cloud/SaaS incidents from application failures with a timestamped evidence snapshot before any code is changed.

 incident-triage outage-detection hypothesis-separation

**Why we selected it**Requires a timestamped dependency-health snapshot and separates confirmed facts, plausible hypotheses and unknowns before proposing code changes.

**Weigh up**Requires the OutageDeck MCP server (remote http) plus repository/log access; without it only the local-investigation half of the workflow runs.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/github-cloud-saas-outage-triage/) Attributed definition available MIT
 Compare Cloud and SaaS Outage Triage Add

Network diagnostics · Seth Hobson

### [Cloud network engineer](/agents/wshobson-network-engineer/)

Structures cloud and hybrid network diagnosis around layered connectivity, DNS resolution, TLS trust and observed traffic.

 DNS TLS routing

**Why we selected it**It requires tracing resolution from client to authoritative DNS and validating certificate chains.

**Weigh up**Packet captures and flow logs may contain sensitive data; give the host only the intended interfaces, accounts and diagnostic targets.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-network-engineer/) Attributed definition available MIT
 Compare Cloud network engineer Add

Architecture and decisions · anthropics

### [Code Architect](/agents/anthropic-code-architect/)

Turns observed repository conventions into a concrete feature blueprint with file changes, interfaces, trade-offs and an implementation sequence.

 architecture implementation plans data flow

**Why we selected it**Requires existing patterns and conventions to be supported by file-and-line references before proposing a design.

**Weigh up**The prompt asks for one decisive design; use another review process when competing designs or unresolved requirements need comparison.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-code-architect/) Attributed definition available Apache-2.0
 Compare Code Architect Add

Codebase understanding · anthropics

### [Code Explorer](/agents/anthropic-code-explorer/)

Traces an existing feature from entry points through state changes and storage, producing a source-linked map for the next developer.

 architecture code navigation dependencies

**Why we selected it**Requires call-chain and data-transformation tracing, so the output goes beyond a directory summary.

**Weigh up**It produces an explanatory map rather than implementing changes or proving behavior with executed tests.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-code-explorer/) Attributed definition available Apache-2.0
 Compare Code Explorer Add

Code maintenance · anthropics

### [Code Simplifier](/agents/anthropic-code-simplifier/)

Refines recently changed code for clearer structure and naming while explicitly keeping its behavior and scope intact.

 refactoring readability JavaScript

**Why we selected it**Limits the default pass to code changed in the current session and explicitly prioritizes behavior preservation.

**Weigh up**Its embedded coding preferences target JavaScript, TypeScript and React; they need review against other languages and the project’s own conventions.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-code-simplifier/) Attributed definition available Apache-2.0
 Compare Code Simplifier Add

Code review · Trail of Bits

### [Code slice worker](/agents/trailofbits-code-slice-worker/)

Pins the Trailmark worker that answers from one source packet, returns a single JSON object, and says it cannot read the repository.

 trailmark slice json

**Why we selected it**The agents index has no entry for plugins/trailmark/agents/code-slice-worker.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-code-slice-worker/) Install command in review CC-BY-SA-4.0
 Compare Code slice worker Add

Developer education · Seth Hobson

### [Code tutorial designer](/agents/wshobson-tutorial-engineer/)

Turns code-backed learning goals into progressive tutorials with runnable examples, practice and troubleshooting checkpoints.

 tutorials exercises onboarding

**Why we selected it**Its sequence introduces a minimal example before guided practice, variations and independent challenges.

**Weigh up**The source provides educational heuristics, not evidence validating learning-style categories or completion-time estimates.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-tutorial-engineer/) Attributed definition available MIT
 Compare Code tutorial designer Add

Codebase understanding · Agency Agents

### [Codebase Archaeologist](/agents/agency-codebase-archaeologist/)

Audits codebases touched by many AI sessions for silent logic mismatches, dead code and doc-vs-code divergence, producing findings only.

 drift-detection doc-vs-code multi-session-audit

**Why we selected it**Explicitly does not rewrite or refactor; it produces precise, evidenced, prioritized findings plus a maintained drift registry answering which files are safe to build on.

**Weigh up**The file declares no tools allowlist; run it with host-default tools restricted to read-only, since the role is findings-only by instruction, not by enforcement.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-codebase-archaeologist/) Attributed definition available MIT
 Compare Codebase Archaeologist Add

Codebase understanding · agency

### [Codebase Onboarding Engineer](/agents/agency-codebase-onboarding-engineer/)

Orients new developers in an unfamiliar repository with a fixed three-level briefing — one line, five minutes, deep dive — where every statement names the files it was read from and unvisited files are listed as not inspected.

 onboarding codebase orientation execution tracing

**Why we selected it**Evidence discipline is structural, not aspirational: it may never state that a module owns behaviour without pointing at the implementing file, and a partial answer must list which files were inspected and which were not.

**Weigh up**Strictly read-only and descriptive: it will not evaluate code quality, suggest changes, or test that documented setup steps actually run.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-codebase-onboarding-engineer/) Attributed definition available MIT
 Compare Codebase Onboarding Engineer Add

Documentation and knowledge · GitHub community

### [CodeTour Guide Builder](/agents/github-code-tour/)

Plans and writes guided code walkthroughs with file references and a maintenance checklist.

 codetour onboarding vscode

**Why we selected it**The schema marks the tour title and each step description as required.

**Weigh up**No tool allowlist is declared; host permissions determine file access and command execution.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/github-code-tour/) Attributed definition available MIT
 Compare CodeTour Guide Builder Add

Pull-request review · OpenAI

### [Codex Rust review](/agents/openai-codex-rust-review/)

A Codex label prompt for one codex-rs pull request: a short change summary, then a friendly review that pushes mixed changes apart and flags unsafe and crate placement.

 rust pull-request codex

**Why we selected it**The review has to ask for a one-to-two sentence change summary and a one-to-two sentence review, and it pushes back when one pull request mixes a refactor with a new feature.

**Weigh up**This is a repository-specific Codex review prompt for codex-rs; adapt crate assumptions deliberately for other Rust projects.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/openai-codex-rust-review/) Upstream setup linked Apache-2.0
 Compare Codex Rust review Add

Model evaluation · GitHub partners

### [Comet Opik](/agents/github-comet-opik/)

Instruments an LLM app with Opik, versions its prompts, and investigates traces, token cost and latency through the Opik MCP server.

 llm observability tracing prompt versioning

**Why we selected it**It does not continue with MCP commands until a configuration path is confirmed, validates setup with masked keys, and never initialises git or rewrites repository history.

**Weigh up**The Bronze, Silver and Gold instrumentation levels are the file's own scheme, not an external standard.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-comet-opik/) Install command in review MIT
 Compare Comet Opik Add

Documentation · anthropics

### [Comment Analyzer](/agents/anthropic-comment-analyzer/)

Checks comments and docstrings against implementation behavior, then separates factual errors, worthwhile improvements and obsolete explanations.

 comments docstrings pull requests

**Why we selected it**Explicitly cross-checks signatures, side effects, error conditions and complexity claims against source code.

**Weigh up**This is advisory review: the body explicitly forbids modifying code or comments.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-comment-analyzer/) Attributed definition available Apache-2.0
 Compare Comment Analyzer Add

Change communication · Affaan Mustafa

### [Commit message reviewer](/agents/ecc-commit-reviewer/)

Derives a commit message from staged changes and repository history, flagging breaking contracts and mixed concerns without creating a commit.

 git commit messages breaking changes

**Why we selected it**It infers conventions from recent non-merge subjects instead of forcing a fixed subject length.

**Weigh up**Recent history can contain inconsistent conventions; inspect the inferred style before accepting the message.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-commit-reviewer/) Attributed definition available MIT
 Compare Commit message reviewer Add

Payments · Stripe

### [Company researcher](/agents/stripe-company-researcher/)

Stripe Claude agent that reads a company URL or description and maps the business to a Connect integration shape with a confidence cap for description-only input.

 stripe connect research

**Why we selected it**The catalogue's Stripe skill is stripe-pay, not this Connect research agent.

**Weigh up**This review did not execute the agent or fetch a company site.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/stripe-company-researcher/) Upstream setup linked MIT
 Compare Company researcher Add

Security and governance · 0xSteph

### [Compliance mapper](/agents/pentest-compliance-mapper/)

Maps a finding to a control only as far as the finding supports, and names the frameworks it will not pretend to certify.

 compliance controls findings

**Why we selected it**The honesty rule says to map only what the finding supports and not to claim a control passed or failed beyond the evidence.

**Weigh up**The file says to confirm the current control revision before citing numbers, and it does not bundle those standards.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/pentest-compliance-mapper/) Attributed definition available MIT
 Compare Compliance mapper Add

Planning workflow components · Seth Hobson

### [Conductor artifact validator](/agents/wshobson-conductor-validator/)

A Conductor review profile checking project context, track metadata and status consistency.

 conductor project-context consistency-checks

**Why we selected it**It cross-checks track registry entries against directories, plans and metadata rather than trusting a completion checkbox alone.

**Weigh up**It claims read-only operation but declares Bash; directory/grep examples are not an enforced shell allowlist, and prompt heuristics may drift from the installed Conductor version.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-conductor-validator/) Upstream setup linked MIT
 Compare Conductor artifact validator Add

Change planning · GitHub community

### [Context Architect](/agents/github-context-architect/)

Maps the files, dependency paths, existing patterns and tests for a proposed change before requesting permission to implement it.

 dependency mapping multi-file changes implementation planning

**Why we selected it**The required context map separates directly changed files from related files and describes why each belongs in scope.

**Weigh up**The definition can edit files, run terminal commands and fetch the web. Its plan-first wording is a prompt rule, not a read-only sandbox.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-context-architect/) Attributed definition available MIT
 Compare Context Architect Add

Pull-request review · GitHub

### [Contribution checker](/agents/github-contribution-checker/)

Reads one pull request against that repository's contributing guide and returns one JSON verdict from checklist answers.

 pull-request contributing review

**Why we selected it**The agent must answer from the pull request metadata, diff, and CONTRIBUTING.md, and must not browse the rest of the repo.

**Weigh up**user-invokable is false: an orchestrator must call the role.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-contribution-checker/) Upstream setup linked MIT
 Compare Contribution checker Add

Resilience testing · VoltAgent

### [Controlled failure-experiment designer](/agents/voltagent-chaos-engineer/)

Frames failure experiments around a steady-state hypothesis, bounded impact, observable recovery and explicit stop controls.

 chaos experiments game days recovery

**Why we selected it**The workflow begins in non-production and expands scope gradually rather than beginning with combined failures.

**Weigh up**The profile provides no executable safety controller or permission boundary; the host must enforce the approved failure targets and abort mechanism.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-chaos-engineer/) Upstream setup linked MIT
 Compare Controlled failure-experiment designer Add

Security operations · Agency Agents community

### [Credential lifecycle and leak-response planner](/agents/agency-security-secrets-credential-engineer/)

A credential-lifecycle profile connecting detection, ownership, provider revocation and controlled rotation.

 secrets rotation workload-identity

**Why we selected it**It distinguishes removing a key from source from revoking it at the provider and asks for an exposure-window usage audit.

**Weigh up**Short lifetimes do not make blast radius near zero; sample scanner versions and grants require environment-specific verification. Revocation, deployment and history rewriting are consequential actions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-security-secrets-credential-engineer/) Upstream setup linked MIT
 Compare Credential lifecycle and leak-response planner Add

Security review · 0xSteph

### [Crypto Analyzer](/agents/pentest-crypto-analyzer/)

Reviews cryptographic design and code for weak primitives and mishandled keys, and points exploitation elsewhere.

 cryptography review authorized-testing

**Why we selected it**The hard refusal is defeating cryptography outside the authorized scope or weakening production cryptography.

**Weigh up**Read/search/web tools support advisory review; the prompt is not a cryptographic implementation or assurance proof.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/pentest-crypto-analyzer/) Attributed definition available MIT
 Compare Crypto Analyzer Add

Build and runtime diagnostics · Affaan Mustafa

### [Dart/Flutter build error resolver](/agents/ecc-dart-build-resolver/)

Diagnoses analyzer, platform build, package-resolution and generated-code failures with bounded changes.

 Dart/Flutter diagnostics minimal fixes

**Why we selected it**The workflow separates null/type errors from pub solver conflicts, build_runner output and Android/iOS configuration.

**Weigh up**Its examples include force unwraps, dependency overrides and deletion of generated outputs; do not apply these without establishing the intended data and generator contract.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-dart-build-resolver/) Upstream setup linked MIT
 Compare Dart/Flutter build error resolver Add

Data and analytics · wshobson/agents

### [Data Engineer](/agents/wshobson-data-engineer/)

A broad design prompt for batch and streaming pipelines, data quality, schema evolution and operational handoffs.

 data-engineering pipelines streaming

**Why we selected it**Covers failure handling, incremental processing and schema evolution alongside the happy-path transformation.

**Weigh up**The file supplies instructions, not an executable pipeline or verified expertise across every listed cloud and engine.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-data-engineer/) Attributed definition available MIT
 Compare Data Engineer Add

Security and privacy · Trail of Bits

### [Data Flow Analyzer](/agents/trailofbits-data-flow-analyzer/)

Traces a suspected vulnerability from sink to sources with trust levels and validation points, producing structured read-only evidence.

 data-flow trust-boundaries vuln-verification

**Why we selected it**Declares only Read, Grep and Glob and states read-only explicitly; the four-phase trace (sink, sources with trust levels, per-validation pass/fail/bypass, full path) is checkable line by line.

**Weigh up**Designed as a Phase-1 worker for the fp-check skill; used standalone the caller must supply the bug description (claim, class, file:line, trigger, impact) as dispatch input.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/trailofbits-data-flow-analyzer/) Attributed definition available CC-BY-SA-4.0
 Compare Data Flow Analyzer Add

Database architecture · Seth Hobson

### [Database architecture designer](/agents/wshobson-database-architect/)

Designs schemas, storage choices and migration plans from application access patterns and operational constraints.

 schema access patterns migration

**Why we selected it**The role defaults to advisory work and prohibits file changes or migration execution unless explicitly requested.

**Weigh up**The broad product inventory is not a current compatibility matrix; verify exact engine/provider support before selecting a design.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-database-architect/) Attributed definition available MIT
 Compare Database architecture designer Add

Data and retrieval · wshobson

### [Database Cloud Optimization Database Optimizer](/agents/wshobson-database-optimizer/)

Investigates database bottlenecks from query plans and workload evidence, then proposes query, index, caching or partitioning changes with validation.

 query-optimization indexing explain-analyze

**Why we selected it**Behavioral trait “Measures performance first using appropriate profiling tools before making optimizations” is the right order for this role.

**Weigh up**This is an implementation-capable role and it declares no tool allowlist; database credentials and migration authority must be scoped in the host.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-database-optimizer/) Attributed definition available MIT
 Compare Database Cloud Optimization Database Optimizer Add

Database operations · Seth Hobson

### [Database reliability administrator](/agents/wshobson-database-admin/)

Plans database availability and maintenance around tested recovery, observed resource limits and documented operational procedures.

 backups recovery replication

**Why we selected it**It calls for restoring backups regularly rather than treating backup-job success as recovery evidence.

**Weigh up**The role spans many engines without supplying engine-specific runbooks or validated commands; select the exact deployment before acting.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-database-admin/) Attributed definition available MIT
 Compare Database reliability administrator Add

Operations and reliability · Agency Agents

### [Database Reliability Engineer](/agents/agency-database-reliability-engineer/)

Keeps stateful datastores available and recoverable with tested restores, drilled failovers and lock-budgeted online migrations, each carrying a written back-out plan.

 database reliability backups failover

**Why we selected it**Pairs backfill and rollback rules explicitly: batched backfills kept out of exclusive-lock transactions, plus a written back-out plan and blast-radius estimate for every migration, failover and large delete.

**Weigh up**The RPO and RTO figures in the template are illustrative targets, not guarantees; each project must set and then prove its own numbers with drills.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-database-reliability-engineer/) Attributed definition available MIT
 Compare Database Reliability Engineer Add

Data and retrieval · affaan-m

### [Database Reviewer](/agents/ecc-database-reviewer/)

Reviews PostgreSQL queries, schemas and migrations for performance, integrity and Row Level Security, reporting findings only.

 postgresql row-level-security query-review

**Why we selected it**Declares only Read, Grep, Glob and Bash (no Write/Edit), so the review-only posture is enforced by the tool list, not just by instruction.

**Weigh up**Diagnostic queries need a readable DATABASE_URL; the definition does not gate who may supply production credentials.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-database-reviewer/) Attributed definition available MIT
 Compare Database Reviewer Add

System administration · GitHub community

### [Debian maintenance guide](/agents/github-debian-linux-expert/)

A Debian administration profile emphasizing package state, reversible changes and vendor-file preservation.

 debian apt systemd

**Why we selected it**It distinguishes interactive apt usage from apt-get scripting and records package pinning when suites are mixed.

**Weigh up**The profile’s default firewall and support preferences are not a compatibility guarantee; terminal/edit access remains capable of changing services and packages.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-debian-linux-expert/) Attributed definition available MIT
 Compare Debian maintenance guide Add

Documentation · Microsoft

### [Deep Wiki catalogue architect](/agents/microsoft-wiki-architect/)

A documentation component that builds a code-cited wiki outline and audience-specific onboarding structure.

 wiki onboarding information-architecture

**Why we selected it**Every catalogue prompt must name source file/line references and diagram/table explanations retain source provenance.

**Weigh up**Its suggested HEAD branch command does not discover the remote default branch; pin the actual revision before constructing citations. Diagram quotas do not prove clarity.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/microsoft-wiki-architect/) Upstream setup linked MIT
 Compare Deep Wiki catalogue architect Add

Security query drafting · GitHub community

### [Defender Scout KQL](/agents/github-defender-scout-kql/)

Drafts and explains Defender Advanced Hunting queries from a security question or existing query, with time-window, projection and join checks.

 KQL Microsoft Defender threat hunting

**Why we selected it**The role separates query generation, inspection, optimisation suggestions and explanation, and supplies a repeatable response format.

**Weigh up**No query execution tool is configured. “Validates” in the upstream description means model inspection here; syntax, table availability and detection quality were not measured.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-defender-scout-kql/) Attributed definition available MIT
 Compare Defender Scout KQL Add

Documentation and knowledge · GitHub community

### [Demonstrate Understanding](/agents/github-demonstrate-understanding/)

Checks a developer’s understanding of a codebase through focused questions and evidence-backed feedback.

 learning code-comprehension onboarding

**Why we selected it**The role is questioning, and the close says the goal is understanding rather than testing.

**Weigh up**This is an interactive tutoring role; it requires the learner to answer and cannot independently demonstrate their knowledge.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-demonstrate-understanding/) Attributed definition available MIT
 Compare Demonstrate Understanding Add

Infrastructure and delivery · wshobson

### [Deploy with Verification](/agents/wshobson-deploy-with-verification/)

Refuses to say shipped until the live system confirms the new revision.

 deployment-gate live-verification ship-discipline

**Why we selected it**A test failure stops the flow, and the words deployed and shipped are forbidden until live verification and the state-doc update both succeed.

**Weigh up**Tools are Bash, Read, and Edit, so the file can change the state doc and run the deploy command.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-deploy-with-verification/) Attributed definition available MIT
 Compare Deploy with Verification Add

Design systems · Seth Hobson

### [Design system architect](/agents/wshobson-design-system-architect/)

A profile for organizing design tokens, component APIs and multi-brand theming.

 design-tokens components theming

**Why we selected it**It distinguishes primitive, semantic and component tokens instead of treating every token as a raw colour.

**Weigh up**Figma, Style Dictionary and visual-regression services are suggested ecosystem tools; the profile does not configure or authenticate them.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-design-system-architect/) Attributed definition available MIT
 Compare Design system architect Add

Security review · 0xSteph

### [Detection engineer](/agents/pentest-detection-engineer/)

Writes detection content for a named technique. It is not a licence to attack a system.

 detection siem authorized-testing

**Why we selected it**Every rule must include the Sigma-shaped fields in the file, including log source, false positives, and level.

**Weigh up**Tools include Write, Edit, WebFetch, and WebSearch, so the file can change the workspace and use the network.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/pentest-detection-engineer/) Attributed definition available MIT
 Compare Detection engineer Add

Developer tools · Agency Agents community

### [Developer CLI tooling engineer](/agents/agency-developer-tooling-engineer/)

Designs command interfaces with stable machine output, actionable errors, configuration precedence and measured startup cost.

 CLI scriptability distribution

**Why we selected it**The role treats flags, JSON output and exit codes as versioned interfaces and requires explicit deprecation paths for changes.

**Weigh up**Startup budgets and time-saved examples are illustrative targets, not measured results for your tool.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-developer-tooling-engineer/) Attributed definition available MIT
 Compare Developer CLI tooling engineer Add

Architecture and decisions · github

### [Devils Advocate](/agents/github-devils-advocate/)

Stress-tests a proposal through one objection at a time, then switches to a balanced recap when the user ends the debate.

 devils-advocate one-objection end-game

**Why we selected it**A clear dialogue protocol keeps each challenge focused and gives the user an explicit way to stop adversarial mode.

**Weigh up**It deliberately challenges rather than neutrally weighs a proposal during debate; use the final recap to recover balance.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-devils-advocate/) Attributed definition available MIT
 Compare Devils Advocate Add

Browser and performance · github

### [Devtools Regression Investigator](/agents/github-devtools-regression-investigator/)

Reproduces browser regressions and links screenshots, console or network evidence to likely code paths, returning a structured bug report before any requested fix.

 devtools-mcp bug-report no-fix-default

**Why we selected it**The file forbids declaring root cause without browser evidence or code correlation, and forbids treating a flaky repro as solved.

**Weigh up**Chrome DevTools MCP and optional Playwright are described but not installed or explicitly named in the tool allowlist; configure the required browser tools separately.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-devtools-regression-investigator/) Attributed definition available MIT
 Compare Devtools Regression Investigator Add

Operations and reliability · Seth Hobson

### [DGX Spark ops engineer](/agents/wshobson-dgx-spark-ops-engineer/)

Diagnoses one named hardware stack and does not generalise its checks to every GPU.

 nvidia cuda hardware

**Why we selected it**Hardware identity is checked before any other diagnosis, and a Spark finding must cite a G-number.

**Weigh up**The checks depend on spark-environment-setup, spark-training-gotchas, and spark-memory-thermal-ops, which this file does not contain.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-dgx-spark-ops-engineer/) Attributed definition available MIT
 Compare DGX Spark ops engineer Add

Testing and review · GitHub partners

### [Diffblue Cover Java Unit Test Agent](/agents/github-diffblue-cover/)

Collects the Java packages, classes or methods to cover, runs Diffblue Cover through its MCP server, reports the result and commits the tests.

 java unit tests diffblue

**Why we selected it**Tools are limited to the DiffblueCover MCP server. Test generation and validation are delegated to Diffblue Cover rather than written by the model.

**Weigh up**Step 4 commits the generated tests with no review step in between. Review the diff first.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-diffblue-cover/) Install command in review MIT
 Compare Diffblue Cover Java Unit Test Agent Add

Code maintenance · Trail of Bits

### [Dimension propagator](/agents/trailofbits-dimension-propagator/)

Propagates dimensional comments through assigned files, refuses executable edits, and reports mismatches instead of fixing them.

 claude-code dimensional-analysis comments-only

**Why we selected it**It requires a status for every assigned file and says not to skip a file silently.

**Weigh up**A Markdown profile does not register a native subagent by itself.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-dimension-propagator/) Install command in review CC-BY-SA-4.0
 Compare Dimension propagator Add

Testing and review · affaan-m

### [Django Reviewer](/agents/ecc-django-reviewer/)

Reviews Django changes for ORM, migration-safety, DRF, Celery and security pitfalls with severity-graded findings and merge-blocking approval criteria.

 Django DRF ORM

**Why we selected it**Migration-safety rules are rollback-aware: RunPython requires reverse code, column drops go two-phase across deployments, and every model change must carry a migration.

**Weigh up**Referenced companion skills such as django-patterns, django-security and django-tdd are not bundled with the standalone file; treat those pointers as optional.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-django-reviewer/) Attributed definition available MIT
 Compare Django Reviewer Add

Infrastructure and delivery · voltagent

### [Docker Expert](/agents/voltagent-docker-expert/)

Reviews and rebuilds Dockerfiles for production — multi-stage builds, layer caching, non-root execution, distroless bases — and pairs image optimization with supply-chain hardening: SBOMs, cosign signing, SLSA provenance and CIS benchmark compliance.

 Docker Dockerfile review multi-stage builds

**Why we selected it**The review loop is concrete: read existing Dockerfiles and compose files, analyze security posture and build performance, then implement — with .dockerignore, HEALTHCHECK, BuildKit and non-root execution named as first-class checks.

**Weigh up**Its excellence checklist prescribes fixed numeric targets (images under 100MB, builds under 5 minutes, cache hit rate over 80%, CIS over 90%) that many legitimate workloads cannot meet; treat them as prompts, not gates.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/voltagent-docker-expert/) Attributed definition available MIT
 Compare Docker Expert Add

Documentation · wshobson

### [Documentation Generation Docs Architect](/agents/wshobson-docs-architect/)

Builds a structured architecture manual from an existing codebase, covering design rationale, component interactions, operational behavior and paths into the source.

 architecture-docs markdown codebase-analysis

**Why we selected it**Output contract is specific: Markdown, heading hierarchy, code blocks, tables, links as file_path:line_number, 10-section skeleton.

**Weigh up**The source favors extensive manuals; choose a bounded audience and scope to avoid documentation that is costly to maintain.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-docs-architect/) Attributed definition available MIT
 Compare Documentation Generation Docs Architect Add

Evidence review · GitHub community

### [Doublecheck](/agents/github-doublecheck/)

Extracts the claims in AI-generated text, searches for sources, and reports links and risk flags for a person to check, without issuing verdicts.

 verification hallucination sources

**Why we selected it**Tools are web_search and web_fetch only. The agent reads and searches; it cannot edit files or run commands.

**Weigh up**The pipeline itself is in the doublecheck skill, skills/doublecheck/SKILL.md, which the agent follows; that skill was not opened.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-doublecheck/) Attributed definition available MIT
 Compare Doublecheck Add

Observability · GitHub community

### [Dynatrace evidence-guided incident analyst](/agents/github-dynatrace-expert/)

A Dynatrace investigation reference connecting traces, exceptions, deployments and current security findings.

 dynatrace incident-analysis dql

**Why we selected it**It asks to inspect exception span events and correlate logs, metrics and traces rather than infer cause from one aggregate.

**Weigh up**The definition embeds a development-tenant URL; never send a real token there by copying it unchanged. DQL examples, latest-scan assumptions and wildcard MCP capabilities require validation against the actual tenant.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-dynatrace-expert/) Upstream setup linked MIT
 Compare Dynatrace evidence-guided incident analyst Add

Finance operations · Anthropic

### [Earnings reviewer](/agents/anthropic-earnings-reviewer/)

Updates a coverage model from an earnings print and drafts the post-earnings note, marking any figure without a FactSet, Daloopa or filing source as [UNSOURCED].

 equity research earnings sourced figures

**Why we selected it**Every number must cite a source. A figure that cannot be sourced from FactSet, Daloopa or a filing is marked [UNSOURCED] rather than filled in.

**Weigh up**Declared tools include Write and Edit, and it updates the live coverage workbook through the model-update skill. Work on a copy.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-earnings-reviewer/) Attributed definition available Apache-2.0
 Compare Earnings reviewer Add

Service integration · VoltAgent

### [Email delivery infrastructure engineer](/agents/voltagent-email-deliverability-engineer/)

Organizes email authentication, provider events, suppression and monitoring around an observed sending profile.

 email integration failure handling

**Why we selected it**The workflow connects SPF/DKIM/DMARC changes to provider events, global suppression and transactional-versus-bulk domain separation.

**Weigh up**The fixed performance thresholds and success-message percentages are illustrative aspirations, not measured outcomes or universal provider requirements.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-email-deliverability-engineer/) Upstream setup linked MIT
 Compare Email delivery infrastructure engineer Add

Embedded software · GitHub community

### [Embedded C code reviewer and implementer](/agents/github-embedded-c-engineer/)

Reviews or implements embedded C against the existing compiler, MCU constraints and project analysis rules.

 C static analysis MCU

**Why we selected it**The role preserves compiler flags and target settings unless requested, avoids generated RTE/MCAL code and checks that new files enter the build.

**Weigh up**No licensed coding standard, compiler, static analyzer or hardware test fixture is bundled.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-embedded-c-engineer/) Attributed definition available MIT
 Compare Embedded C code reviewer and implementer Add

Identity systems · Agency Agents community

### [Enterprise identity and authorization designer](/agents/agency-engineering-identity-access-engineer/)

Plans enterprise identity flows, session revocation and tenant authorization with explicit failure-path tests.

 SSO SCIM sessions

**Why we selected it**The source consumes the login state before async exchange and explicitly requires atomic consumption in shared session stores.

**Weigh up**The code contains application-owned helpers and incomplete WebAuthn ceremony wiring; use maintained protocol libraries and verify current APIs.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-identity-access-engineer/) Upstream setup linked MIT
 Compare Enterprise identity and authorization designer Add

Operations and reliability · VoltAgent

### [Error Coordinator](/agents/voltagent-error-coordinator/)

Mines logs and agent output for recurring failure and cascade patterns, citing evidence paths and refusing to invent quantities.

 failure-patterns evidence-gate recovery-playbooks

**Why we selected it**Requires every reported count to be Grep/Glob-counted with path:line evidence, a two-independent-source minimum for patterns, and explicitly forbids reporting recovery rates, MTTR or cascades prevented.

**Weigh up**No Bash tool is declared, so mining is limited to what Read/Glob/Grep can see; live detection, retries and circuit-breaking are explicitly out of scope.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/voltagent-error-coordinator/) Attributed definition available MIT
 Compare Error Coordinator Add

Architecture and decisions · wshobson

### [Event Sourcing Architect](/agents/wshobson-event-sourcing-architect/)

Plans event-sourced systems through aggregate boundaries, immutable event records, projections, sagas and event-versioning decisions.

 event sourcing CQRS sagas

**Why we selected it**Covers the practical linkage between command handling, read projections and cross-aggregate workflows.

**Weigh up**The role assumes event sourcing is appropriate; it does not compare simpler persistence designs first.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-event-sourcing-architect/) Attributed definition available MIT
 Compare Event Sourcing Architect Add

Code review · Anthropic

### [Expert Rust Code Reviewer](/agents/buffa-rust-code-reviewer/)

Reviews a Rust diff for ownership, unsafe invariants, concurrency, error handling and public APIs, with compiler or Clippy checks for testable findings.

 rust code-review safety

**Why we selected it**The source covers ownership, unsafe contracts, async cancellation, lock ordering, secret-bearing Debug output and dependency/MSRV concerns in one review checklist.

**Weigh up**The source contains 18 review categories. Its Excellent/Good/Needs Improvement/Poor labels are subjective report labels, not measured quality scores.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/buffa-rust-code-reviewer/) Upstream setup linked Apache-2.0
 Compare Expert Rust Code Reviewer Add

Security review · Trail of Bits

### [Exploitability verifier](/agents/trailofbits-exploitability-verifier/)

Pins the fp-check phase-2 agent that stays read-only while deciding whether a suspected bug is exploitable, and that skips a proof the bug class does not need.

 security review read-only

**Why we selected it**The agents catalogue has no sourcePath for plugins/fp-check/agents/exploitability-verifier.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-exploitability-verifier/) Install command in review CC-BY-SA-4.0
 Compare Exploitability verifier Add

Language-specific review · Affaan Mustafa

### [F# code reviewer](/agents/ecc-fsharp-reviewer/)

Reviews F# changes for exhaustive domain modelling, computation-expression flow, disposal and safe boundaries.

 F# functional design pattern matching

**Why we selected it**It checks incomplete union matches, smart constructors, Option/Result handling and async binding.

**Weigh up**Function-length and nesting thresholds are style heuristics; immutable/functional rewrites and sequence materialization must preserve semantics and measured resource costs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-fsharp-reviewer/) Upstream setup linked MIT
 Compare F# code reviewer Add

Testing and review · affaan-m

### [FastAPI Reviewer](/agents/ecc-fastapi-reviewer/)

Reviews FastAPI changes for async blocking, dependency wiring, schema exposure and test setup, with file references and explicit unverified risks.

 FastAPI Python async correctness

**Why we selected it**Focuses on framework-specific failure modes such as blocking clients in async routes, incorrect test overrides and sensitive response fields.

**Weigh up**Its severity checklist includes architectural preferences that require context; an inline database session is not automatically a demonstrated vulnerability.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-fastapi-reviewer/) Attributed definition available MIT
 Compare FastAPI Reviewer Add

Code review · Anthropic

### [Feature-dev code reviewer](/agents/anthropic-code-reviewer/)

Reviews the unstaged git diff for bugs and against CLAUDE.md rules, and reports only issues it rates 80 or higher.

 code review claude-md bugs

**Why we selected it**The frontmatter tools are Glob, Grep, LS, Read, NotebookRead, WebFetch, TodoWrite, WebSearch, KillShell and BashOutput. No Write, Edit or Bash tool is declared, so the review role does not include changing files.

**Weigh up**The 0 to 100 confidence is the model's own rating of each issue, not a measured precision. The threshold of 80 hides lower-rated findings; it does not prove they are false.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-code-reviewer/) Attributed definition available Apache-2.0
 Compare Feature-dev code reviewer Add

Research and product · msitarzewski

### [Feedback Synthesizer](/agents/agency-product-feedback-synthesizer/)

Organizes a supplied customer-feedback corpus into themes, product priorities and audience-specific reports for product and support teams.

 customer-feedback thematic-analysis product-research

**Why we selected it**Specifies separate executive, product-team and customer-success deliverables rather than one undifferentiated summary.

**Weigh up**The definition's accuracy, growth and service-level targets are aspirations; none were demonstrated by this source review.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/agency-product-feedback-synthesizer/) Attributed definition available MIT
 Compare Feedback Synthesizer Add

Security review · 0xSteph

### [Fix Verifier](/agents/pentest-fix-verifier/)

Retests a declared finding after a patch, and only during authorized testing.

 verification remediation authorized-testing

**Why we selected it**Commands against a target are refused until the user declares scope.

**Weigh up**Bash/Write/Edit are available, so declared target scope and non-destructive rules require host enforcement.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/pentest-fix-verifier/) Attributed definition available MIT
 Compare Fix Verifier Add

Code maintenance · Trail of Bits

### [Fixer](/agents/trailofbits-fixer/)

Applies dispatched blocking fixes only inside the workflow's scope globs, and records a verdict instead of skipping a finding or discarding the worktree.

 claude-code code-improver scope-limit

**Why we selected it**The description limits dispatch to the code-improver workflow and says the agent is not for ad-hoc editing.

**Weigh up**A Markdown profile does not register a native subagent by itself.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-fixer/) Install command in review CC-BY-SA-4.0
 Compare Fixer Add

Cross-platform applications · Seth Hobson

### [Flutter application engineer](/agents/wshobson-flutter-expert/)

Plans Flutter widget architecture, native integration and testing around the actual target platforms.

 Flutter widgets platform channels

**Why we selected it**The profile pairs widget identity and rebuild concerns with real-device profiling and platform-channel boundaries.

**Weigh up**The definition references a 2025 ecosystem and Riverpod 2.x; verify installed package APIs rather than treating its inventory as current guidance.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-flutter-expert/) Attributed definition available MIT
 Compare Flutter application engineer Add

Testing and review · affaan-m

### [Flutter Reviewer](/agents/ecc-flutter-reviewer/)

Reviews Flutter and Dart changes state-management-agnostically — detecting the project's BLoC, Riverpod, Provider or other setup first — then ranks widget rebuild, architecture and security findings with a per-severity verdict table.

 flutter dart code review

**Why we selected it**Adapts to the project's chosen state management (BLoC, Riverpod, Provider, GetX, MobX, Signals or built-in) and its routing and DI approach before reviewing, explicitly to avoid flagging idiomatic usage of a different solution as a violation.

**Weigh up**The closing pointer to a sibling flutter-dart-code-review skill references a companion file that is not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-flutter-reviewer/) Attributed definition available MIT
 Compare Flutter Reviewer Add

Security review · 0xSteph

### [Forensics analyst](/agents/pentest-forensics-analyst/)

Starts from evidence acquisition and chain of custody, not from a guessed timeline.

 forensics evidence custody

**Why we selected it**Behavioral rules require hashes, chain of custody, and work on copies rather than original evidence.

**Weigh up**Use only with evidence the caller is allowed to handle; this file is not that authorization.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/pentest-forensics-analyst/) Attributed definition available MIT
 Compare Forensics analyst Add

Browser and performance · github

### [Frontend Performance Investigator](/agents/github-frontend-performance-investigator/)

Diagnoses a specific slow web flow from traces, network activity and code paths, then produces prioritized fixes with a validation method for each.

 core-web-vitals lighthouse devtools

**Why we selected it**Requires a concrete reproduction path and recorded environment assumptions before recommending optimizations.

**Weigh up**Chrome DevTools MCP and the optional Playwright fallback require separate configuration; neither is explicitly included in this file’s tool allowlist.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-frontend-performance-investigator/) Attributed definition available MIT
 Compare Frontend Performance Investigator Add

Codebase understanding · Trail of Bits (Omar Inuwa)

### [Function Analyzer](/agents/trailofbits-function-analyzer/)

Builds a line-cited account of one function’s invariants, assumptions and callee dependencies before a later security review.

 audit preparation invariants call chains

**Why we selected it**Requires reading callees and their branches before treating a precondition as enforced; function names are explicitly insufficient evidence.

**Weigh up**The file requires sibling analysis formats and domain references plus a resolved {baseDir}; the download alone does not install the plugin.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/agents/trailofbits-function-analyzer/) Attributed definition available CC-BY-SA-4.0
 Compare Function Analyzer Add

Game development · Agency Agents community

### [Game economy designer](/agents/agency-economy-designer/)

A game-economy profile that connects currency sources and sinks to simulated player cohorts.

 virtual-economy simulation telemetry

**Why we selected it**Each currency needs a purpose, source, sink and rationale linked to a curve or simulation.

**Weigh up**Sample balances, ratios and simulation durations are illustrative design targets, not validated outcomes or universal game-economy constants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-economy-designer/) Attributed definition available MIT
 Compare Game economy designer Add

Game design · Agency Agents community

### [Game level layout designer](/agents/agency-level-designer/)

Creates level and encounter specifications that can be tested as grey boxes before art production.

 blockout encounters playtesting

**Why we selected it**The workflow asks for before/after layout evidence tied to playtest observations and marks gameplay-critical geometry for the art team.

**Weigh up**Fixed visibility/timing thresholds and success percentages in the source are aspirational examples, not validated outcomes.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-level-designer/) Attributed definition available MIT
 Compare Game level layout designer Add

Game development · Agency Agents community

### [Game narrative systems designer](/agents/agency-narrative-designer/)

A game-narrative profile for branch maps, character voice and coherent optional lore.

 narrative dialogue branching

**Why we selected it**It maps branch structure before writing lines and requires a dramatic function for each dialogue node.

**Weigh up**The sample is labeled Ink/Yarn/generic and is not validated language-specific syntax; persona experience claims and success targets are not evidence.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-narrative-designer/) Attributed definition available MIT
 Compare Game narrative systems designer Add

Geospatial operations · Agency Agents community

### [GIS analyst](/agents/agency-gis-analyst/)

Handles scoped map production, layer hygiene and basic spatial queries with provenance and export checks.

 GIS maps data quality

**Why we selected it**It distinguishes basic buffer/clip/query work from statistical modelling and automated ETL.

**Weigh up**A matching CRS label is insufficient evidence of correct coordinates; verify spatial plausibility and suitable distance/area units.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-gis-analyst/) Attributed definition available MIT
 Compare GIS analyst Add

Geospatial quality · Agency Agents community

### [GIS data quality reviewer](/agents/agency-gis-qa-engineer/)

Structures geospatial QA around reproducible feature-level findings, metadata, topology and delivery checks.

 topology CRS metadata

**Why we selected it**It distinguishes declared CRS from actual coordinate plausibility and compares completeness to expected rows/extent.

**Weigh up**The Python examples contain pass-only stubs; there is no executable validation suite in the definition.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-gis-qa-engineer/) Attributed definition available MIT
 Compare GIS data quality reviewer Add

Code maintenance · agency

### [Git Workflow Master](/agents/agency-git-workflow-master/)

Establishes branch hygiene with copy-safe commands — trunk-based versus Git Flow diagrams, --no-track branch creation, worktrees for parallel work, force-with-lease over force-push — and warns before every destructive operation.

 Git branching strategy conventional commits

**Why we selected it**The commands are copy-safe and explain their own sharp edges: --no-track is justified (a new branch must not inherit origin/main as upstream) and worktree creation is shown instead of a second checkout of the same branch.

**Weigh up**A workflow guide, not an auditor: it does not inspect an existing repository's history or branch state and report hygiene findings.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-git-workflow-master/) Attributed definition available MIT
 Compare Git Workflow Master Add

Infrastructure and delivery · github

### [Github Actions Expert](/agents/github-github-actions-expert/)

Designs and reviews GitHub Actions workflows around minimal token permissions, immutable action references, OIDC, deployment concurrency and validation.

 github-actions supply-chain oidc

**Why we selected it**Action pinning section forbids `@main`/`@latest`/moving tags, requires full commit SHA plus a version comment, and explains tag-move supply-chain risk.

**Weigh up**The GitHub tool wildcard and terminal access can perform repository actions; the definition itself does not enforce a read-only review.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-github-actions-expert/) Attributed definition available MIT
 Compare Github Actions Expert Add

CI maintenance · GitHub

### [GitHub Actions Node runtime upgrade](/agents/github-actions-node-runtime-upgrade/)

Nine-step upgrade of a JavaScript or TypeScript GitHub Action to a newer Node runtime, treated as a breaking major version.

 github-actions node upgrade

**Why we selected it**The upgrade treats a Node runtime change as a major version bump in package.json.

**Weigh up**Edit and terminal tools can modify the action and run project npm scripts; inspect script side effects.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-actions-node-runtime-upgrade/) Upstream setup linked MIT
 Compare GitHub Actions Node runtime upgrade Add

Documentation editing · GitHub

### [GitHub Docs builder writer](/agents/github-docs-builder-writer/)

Writes GitHub Docs for the Builder persona and keeps enterprise-admin material out of that article.

 documentation builders github

**Why we selected it**Builder content is for people doing the work themselves, and organization-wide administration is sent to the Driver persona.

**Weigh up**Frontmatter sets include-custom-instructions and does not name tools.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-docs-builder-writer/) Upstream setup linked MIT
 Compare GitHub Docs builder writer Add

Documentation editing · GitHub

### [GitHub Docs content pipeline update](/agents/github-docs-content-pipeline-update/)

Updates official reference articles from ephemeral source docs and refuses instructions in those docs that ask for secrets or unrelated actions.

 documentation reference github

**Why we selected it**Missing prompt fields stop the run, and edits are limited to TARGET_ARTICLES plus reusables.

**Weigh up**The security section says there is no shell, while step 4 still says to run npm run lint-content and a content render test.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-docs-content-pipeline-update/) Upstream setup linked MIT
 Compare GitHub Docs content pipeline update Add

Documentation editing · GitHub

### [GitHub Docs driver writer](/agents/github-docs-driver-writer/)

Writes Driver documentation for people who administer GitHub at enterprise scale, and flags specific high-risk claims for a writer to verify.

 documentation enterprise github

**Why we selected it**The audience is people who administer GitHub, and the file says to flag one risky claim rather than a whole article.

**Weigh up**The file sets include-custom-instructions and does not show those instructions.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-docs-driver-writer/) Upstream setup linked MIT
 Compare GitHub Docs driver writer Add

Documentation editing · GitHub

### [GitHub Docs GHES release notes](/agents/github-docs-ghes-release-notes/)

Drafts GitHub Enterprise Server release notes from a releases issue or a changelog pull request.

 release-notes ghes github

**Why we selected it**A private-preview title is skipped and returns an empty list, and the word deprecated is forbidden.

**Weigh up**The file tells the agent not to ask follow-up questions when invoked programmatically.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-docs-ghes-release-notes/) Upstream setup linked MIT
 Compare GitHub Docs GHES release notes Add

Documentation editing · GitHub

### [GitHub Docs readability editor](/agents/github-docs-readability-editor/)

Edits only the markdown files it is given, and keeps a sentence when a shorter wording would change the meaning.

 documentation editing readability

**Why we selected it**Edits are limited to the specific markdown files provided. The file says not to move or delete files, and to keep the original sentence when an edit would change its meaning.

**Weigh up**The definition requests a pull request and grants edit, execute and github/* capabilities. Select a restricted host policy for a local editing pass; prose scope is not a tool sandbox.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/github-docs-readability-editor/) Attributed definition available MIT
 Compare GitHub Docs readability editor Add

Finance operations · Anthropic

### [GL reconciler](/agents/anthropic-gl-reconciler/)

Compares general ledger and subledger balances for a trade date, traces each break and drafts an exception report for controller sign-off.

 reconciliation general ledger fund accounting

**Why we selected it**Declared tools are Read, Grep, Glob and the internal-gl and subledger MCP servers. The file says it produces a report and that ledger adjustments need human approval outside the agent.

**Weigh up**The reader, critic and resolver workers named in the body are defined in managed-agent-cookbooks/gl-reconciler/subagents/, not in the plugin's agents directory. Installed as a plugin, the split between untrusted readers and the Write-holding resolver depends on that setup.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-gl-reconciler/) Install command in review Apache-2.0
 Compare GL reconciler Add

Build and runtime diagnostics · Affaan Mustafa

### [Go build error resolver](/agents/ecc-go-build-resolver/)

Resolves Go compiler, module, vet and linter failures while keeping changes bounded to the reported build problem.

 Go diagnostics minimal fixes

**Why we selected it**The workflow checks compilation before narrowing into interfaces, imports, cycles and module resolution.

**Weigh up**go mod tidy, go get and cache cleaning can change dependencies or local state; review their scope before execution.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-go-build-resolver/) Upstream setup linked MIT
 Compare Go build error resolver Add

Testing and review · affaan-m

### [Go Reviewer](/agents/ecc-go-reviewer/)

Reviews Go changes by running go vet, staticcheck and the diff first, then ranks findings from SQL injection and ignored errors to goroutine leaks, channel deadlocks and non-idiomatic patterns.

 go code review concurrency

**Why we selected it**Runs go vet and staticcheck before reviewing and lists golangci-lint, -race builds and govulncheck as diagnostic commands, so findings are grounded in executed tooling.

**Weigh up**The closing pointer to a sibling golang-patterns skill references a companion file that is not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-go-reviewer/) Attributed definition available MIT
 Compare Go Reviewer Add

API architecture · Seth Hobson

### [GraphQL schema and resolver architect](/agents/wshobson-graphql-architect/)

Plans GraphQL schemas and resolver behaviour with batching, authorization, evolution and testing considerations.

 GraphQL resolvers federation

**Why we selected it**The definition covers DataLoader/N+1 concerns alongside field authorization, subscriptions and schema evolution.

**Weigh up**No GraphQL server, schema registry or framework dependency is included.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-graphql-architect/) Attributed definition available MIT
 Compare GraphQL schema and resolver architect Add

Agent development · affaan-m

### [Harness Optimizer](/agents/ecc-harness-optimizer/)

Tunes agent configuration with an explicit evaluation definition, repeated trials, baseline checks and rollback instructions for failed experiments.

 eval-harness hooks pass-at-k

**Why we selected it**Explicit non-goals: no product-code rewrites; no slash-command invocation; run node scripts/harness-audit.js instead.

**Weigh up**Requires the upstream-style scripts/harness-audit.js, tests/run-all.js and skills/eval-harness/SKILL.md; a standalone download cannot run that workflow by itself.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-harness-optimizer/) Attributed definition available MIT
 Compare Harness Optimizer Add

Language development · Seth Hobson

### [Haskell typed-design developer](/agents/wshobson-haskell-pro/)

A Haskell profile that keeps pure logic separate from IO and favors total functions.

 haskell property-testing stm

**Why we selected it**It asks for safe total alternatives to partial functions and language extensions only when their purpose is explained.

**Weigh up**High-assurance wording describes intent; it is not a formal verification result or a compiled package.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-haskell-pro/) Attributed definition available MIT
 Compare Haskell typed-design developer Add

Agent development · Anthropic

### [Hookify conversation analyzer](/agents/anthropic-conversation-analyzer/)

Reads a Claude Code conversation for user corrections and proposes regex hook rules, graded by severity, for the user to choose from.

 hooks corrections regex

**Why we selected it**Tools are Read and Grep only. The agent returns findings, and the /hookify command then asks which rules to create.

**Weigh up**The regex patterns are the model's proposals. They were not compiled or tested against a transcript here, and a broad pattern can block legitimate commands.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-conversation-analyzer/) Attributed definition available Apache-2.0
 Compare Hookify conversation analyzer Add

Cloud architecture · Seth Hobson

### [Hybrid-cloud architecture planner](/agents/wshobson-hybrid-cloud-architect/)

Plans workload placement, connectivity and recovery across public, private and edge environments using explicit constraints.

 hybrid cloud data gravity disaster recovery

**Why we selected it**The response weighs data gravity, latency, operational needs and cost before assigning workloads to environments.

**Weigh up**The broad provider/product inventory may contain dated names and does not prove integration support; verify current availability and contracts for each selected service.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-hybrid-cloud-architect/) Attributed definition available MIT
 Compare Hybrid-cloud architecture planner Add

Testing and review · wshobson

### [Hypothesis Debugging Investigator](/agents/wshobson-team-debugger/)

Investigates one assigned bug hypothesis and sends the team lead a cited account of supporting evidence, contradictions and remaining gaps.

 hypothesis testing debugging agent teams

**Why we selected it**Defines confirmation, falsification and ambiguous evidence before investigation, reducing one-sided hypothesis confirmation.

**Weigh up**Depends on a lead and the host’s messaging/task tools. The single file does not create a team or an orchestration workflow.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-team-debugger/) Attributed definition available MIT
 Compare Hypothesis Debugging Investigator Add

Operations and reliability · Seth Hobson

### [Incident Responder](/agents/wshobson-incident-responder/)

Runs the first five minutes of an incident as assessment and communication, not as an immediate change.

 incident sre postmortem

**Why we selected it**The first section is a five-minute sequence: severity, a single incident commander, then stabilization.

**Weigh up**The Sonnet model alias and absent tool allowlist are host-specific.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-incident-responder/) Attributed definition available MIT
 Compare Incident Responder Add

Game audio · Agency Agents community

### [Interactive game audio planner](/agents/agency-game-audio-engineer/)

Plans event-driven game audio, state parameters, voice budgets and target-hardware profiling.

 FMOD Wwise adaptive music

**Why we selected it**It connects gameplay state to middleware parameters and tests transitions such as combat, death and scene changes.

**Weigh up**The budgets, codecs and middleware-only rules are example policies, not measured platform requirements or universal audio guidance.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-game-audio-engineer/) Upstream setup linked MIT
 Compare Interactive game audio planner Add

Code maintenance · Agency Agents

### [Internationalization Engineer](/agents/agency-i18n-engineer/)

Makes codebases translation-ready: complete ICU messages instead of concatenated fragments, CLDR-backed formatting, logical-property layouts that survive RTL, and pseudo-localization wired into CI so hardcoded strings fail the build.

 i18n ICU MessageFormat CLDR

**Why we selected it**States eight concrete engineering rules — no concatenated fragments, CLDR plurals through ICU, Intl-only formatting, logical CSS properties, expansion budgeting, translator context, Unicode normalization, locale negotiation — each tied to the failure it prevents.

**Weigh up**The success metrics (zero hardcoded strings, clarification requests below 2 per 1,000 strings) are targets for the codebase, not measured outcomes of running this agent.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/agency-i18n-engineer/) Attributed definition available MIT
 Compare Internationalization Engineer Add

Infrastructure · Agency Agents community

### [IoT fleet and staged-update architect](/agents/agency-engineering-iot-fleet-engineer/)

A fleet-design profile for intermittent devices, scoped identity and health-gated firmware rollouts.

 iot ota device-identity

**Why we selected it**It combines bounded edge buffering with original timestamps and sequence-based backend deduplication.

**Weigh up**A/B partition diagrams do not prove a device is unbrickable; bootloader, flash, power-loss and recovery behavior require hardware testing. Rollout sizes are examples.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-iot-fleet-engineer/) Upstream setup linked MIT
 Compare IoT fleet and staged-update architect Add

Testing and review · affaan-m

### [Java Reviewer](/agents/ecc-java-reviewer/)

Detects Spring Boot versus Quarkus from the build file first and runs the framework build check, then reviews Java changes against framework-specific rules spanning JPA, Panache, MongoDB, security and concurrency.

 java code review spring boot

**Why we selected it**Framework detection is an explicit first step — the build file is read and [SPRING] or [QUARKUS] rulesets applied, with both-present treated as a finding and neither-present noted as ambiguity — so framework-specific rules are never applied blind.

**Weigh up**Closing pointers to sibling springboot-patterns and quarkus-patterns skills reference companion files that are not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-java-reviewer/) Attributed definition available MIT
 Compare Java Reviewer Add

Security and governance · GitHub partners

### [JFrog Security Agent](/agents/github-jfrog-security-agent/)

Checks a dependency upgrade against the organisation's JFrog Curation policy before recommending it, then applies CVE-specific remediation guidance.

 dependencies curation policy cve

**Why we selected it**Before any change it must check the upgrade version against the organisation's Curation Policy with a JFrog MCP tool, and recommend only the policy-compliant version.

**Weigh up**It is told to use JFrog MCP tools exclusively and not npm audit, CodeQL or the GitHub Advisory Database, so a finding is not cross-checked against a second source.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-jfrog-security-agent/) Install command in review MIT
 Compare JFrog Security Agent Add

Project planning · Agency Agents community

### [Jira delivery traceability steward](/agents/agency-project-management-jira-workflow-steward/)

A delivery-planning profile linking a confirmed Jira ticket to branch, commit, PR and release evidence.

 jira git-workflow delivery-evidence

**Why we selected it**The profile refuses to invent ticket identifiers and separates Git-facing work from unrelated tasks that need no Jira process.

**Weigh up**The supplied hook only checks name patterns; it does not verify a Jira issue exists or that branch and commit IDs match, and release subjects bypass its commit regex. Its develop/main convention is not universal.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-project-management-jira-workflow-steward/) Upstream setup linked MIT
 Compare Jira delivery traceability steward Add

Research and product · github

### [Jobs-to-be-Done UX Planner](/agents/github-se-ux-designer/)

Turns user context and jobs to be done into a journey map, flow specification and design handoff documents.

 UX planning jobs to be done journey maps

**Why we selected it**Starts by asking about users, context and pain points instead of treating a requested interface feature as the underlying goal.

**Weigh up**The agent drafts research artifacts; it does not conduct interviews, validate personas or create Figma designs.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-se-ux-designer/) Attributed definition available MIT
 Compare Jobs-to-be-Done UX Planner Add

Language development · Seth Hobson

### [Julia scientific-code developer](/agents/wshobson-julia-pro/)

A Julia profile emphasizing type-stable numerical code and reproducible package environments.

 julia numerical-computing type-stability

**Why we selected it**Its constraints require Pkg APIs rather than hand-editing Project.toml and explicitly request type-stability inspection.

**Weigh up**The version and ecosystem descriptions are the prompt author’s scope, not a tested compatibility matrix; GPU and scientific packages are not included.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-julia-pro/) Attributed definition available MIT
 Compare Julia scientific-code developer Add

Testing and review · affaan-m

### [Kotlin Reviewer](/agents/ecc-kotlin-reviewer/)

Reviews Kotlin and Android/KMP changes for coroutine cancellation mistakes, Flow and Compose recomposition traps and clean-architecture violations, reporting only findings it holds with more than 80% confidence.

 kotlin android code review

**Why we selected it**Encodes noise control as a rule — only findings held above 80% confidence are reported — and closes with a per-severity verdict table whose Block verdict is bound to any CRITICAL or HIGH issue.

**Weigh up**The clean-architecture module rules assume a domain/data/presentation layering; projects with other layouts will get spurious boundary findings.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-kotlin-reviewer/) Attributed definition available MIT
 Compare Kotlin Reviewer Add

Finance operations · Anthropic

### [KYC screener](/agents/anthropic-kyc-screener/)

Extracts an onboarding packet, runs the firm's KYC rules and sanctions, PEP and adverse-media screening, and packages gaps for compliance sign-off.

 kyc aml sanctions screening

**Why we selected it**Each KYC rule result carries pass or fail with an evidence reference. The agent recommends a risk rating, and the file says the compliance officer decides.

**Weigh up**Screening results and match confidence come from the firm's screening MCP and its lists. Their coverage was not assessed.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-kyc-screener/) Attributed definition available Apache-2.0
 Compare KYC screener Add

Code maintenance · GitHub community

### [LaunchDarkly Flag Cleanup](/agents/github-launchdarkly-flag-cleanup/)

Removes obsolete feature flags by reading each environment’s live LaunchDarkly configuration first, deriving the forward value from what is actually served, and opening a PR that preserves production behaviour.

 feature flags launchdarkly flag cleanup

**Why we selected it**Gates every removal on live evidence: per-environment flag configuration, lifecycle status and code references come from the LaunchDarkly MCP tools, and inconsistent state across critical environments stops the removal.

**Weigh up**Requires the LaunchDarkly MCP server and an LD_ACCESS_TOKEN; the frontmatter mcp-servers block is Copilot-specific configuration and needs porting to other hosts.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/github-launchdarkly-flag-cleanup/) Attributed definition available MIT
 Compare LaunchDarkly Flag Cleanup Add

Codebase understanding · anthropics

### [Legacy Analyst](/agents/anthropic-legacy-analyst/)

Builds an evidence-linked account of an unfamiliar legacy system by tracing entry points, stable data structures and actual control flow.

 legacy systems dependency maps uncertainty

**Why we selected it**Requires source citations and explicitly distinguishes observed behavior from inferred intent.

**Weigh up**The role is an analyst, not a migration implementer or an executable behavior test.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-legacy-analyst/) Attributed definition available Apache-2.0
 Compare Legacy Analyst Add

Model development · Seth Hobson

### [LLM fine-tuning architect](/agents/wshobson-llm-finetuning-architect/)

A fine-tuning planning component that requires a baseline and can recommend a retrieval or prompting alternative.

 fine-tuning training-brief evaluation-gates

**Why we selected it**It owns planning phases and must hand off a written brief rather than silently train or invent dataset-size guidance.

**Weigh up**No model, dataset rights, hardware or evaluation harness is bundled; a training plan does not establish that fine-tuning helps.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-llm-finetuning-architect/) Upstream setup linked MIT
 Compare LLM fine-tuning architect Add

Model evaluation · Seth Hobson

### [LLM Fine-Tuning Eval Engineer](/agents/wshobson-llm-finetuning-eval-engineer/)

Owns the pre-training evaluation baseline and post-training checkpoint verdict, with explicit per-trace records and no authority to train or automatically retrain.

 evaluation fine-tuning gate

**Why we selected it**Defines a stable eval/ measuring set outside disposable runs/ outputs and requires full assistant completions in the trace records consumed downstream.

**Weigh up**This Markdown profile does not install an evaluation harness, companion skills or infrastructure, and declares model: sonnet with no tool allowlist. Host defaults and permissions remain decisive.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-llm-finetuning-eval-engineer/) Attributed definition available MIT
 Compare LLM Fine-Tuning Eval Engineer Add

Model development · Seth Hobson

### [LLM fine-tuning training engineer](/agents/wshobson-llm-finetuning-training-engineer/)

A training component that follows an approved brief and hands checkpoint promotion to a separate evaluator.

 training dataset-validation export-checks

**Why we selected it**It decodes packed examples to inspect formatting and requires a hardware/environment preflight before launching a job.

**Weigh up**The source demands committing configuration before training; that is a separate repository mutation requiring task authorization. GPU jobs, downloads and checkpoints incur cost and consume storage.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-llm-finetuning-training-engineer/) Upstream setup linked MIT
 Compare LLM fine-tuning training engineer Add

Finance operations · Anthropic

### [LP statement auditor](/agents/anthropic-statement-auditor/)

Ties out a batch of LP capital-account statements against the fund NAV pack and recommends pass or hold for each statement.

 audit tie-out fund accounting

**Why we selected it**Declared tools are Read, Grep, Glob and the nav MCP server. It recommends pass or hold, and the file says investor relations distributes only after human sign-off.

**Weigh up**The statement-reader and flagger workers are defined in managed-agent-cookbooks/statement-auditor/subagents/, not in the plugin agent file.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-statement-auditor/) Attributed definition available Apache-2.0
 Compare LP statement auditor Add

Accessibility · github

### [Markdown Accessibility Assistant](/agents/github-markdown-accessibility-assistant/)

Reviews existing Markdown for accessible headings, links, lists and image descriptions, while reserving meaning-changing rewrites for human approval.

 markdown accessibility markdownlint

**Why we selected it**Mission forbids generating docs from scratch and limits work to improving existing markdown, which is a real role boundary.

**Weigh up**The scope is selected Markdown accessibility practices, not full web accessibility conformance.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-markdown-accessibility-assistant/) Attributed definition available MIT
 Compare Markdown Accessibility Assistant Add

Mathematics · Anthropic

### [Math proof worker, deep](/agents/anthropic-math-proof-worker-deep/)

Pins the higher-effort math-proof worker that answers one question per launch and writes the answer to a file the orchestrator reads.

 claude math proof

**Why we selected it**The catalogue has math-proof-worker and math-proof-judge and not this deep worker.

**Weigh up**This review did not execute the resource.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-math-proof-worker-deep/) Upstream setup linked Apache-2.0
 Compare Math proof worker, deep Add

Mathematics · Anthropic

### [Math-proof judge](/agents/anthropic-math-proof-judge/)

Runs one named step of a math-proof siege: writes only the files that step names, keeps notes under 4000 words, and requires proof.md to stand alone.

 proof mathematics review

**Why we selected it**Each launch is one step with no memory except the named files, and every query file must stand alone because the worker sees only that query plus the problem statement.

**Weigh up**This is one seat in the siege protocol. A standalone copy cannot orchestrate the workflow, and ledger bookkeeping is not a mathematical proof checker.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-math-proof-judge/) Upstream setup linked Apache-2.0
 Compare Math-proof judge Add

Mathematics · Anthropic

### [Math-proof worker](/agents/anthropic-math-proof-worker/)

Answers one self-contained mathematics question into a file, separates proved claims from sketches and open questions, and appends the task's end marker only when finished.

 proof mathematics reasoning

**Why we selected it**The answer file has to separate what is proved, what is only sketched or conjectured, and what remains open, and a literature result must be labeled as cited from memory.

**Weigh up**Read, Write and Edit are the only declared tools; no code execution or web access is available to verify calculations or literature.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-math-proof-worker/) Upstream setup linked Apache-2.0
 Compare Math-proof worker Add

Meeting records · Agency Agents community

### [Meeting notes extractor](/agents/agency-meeting-notes-specialist/)

Extracts explicit decisions, assigned actions and unresolved questions from meeting material without filling missing facts.

 meeting notes decisions action items

**Why we selected it**It distinguishes agreement from discussion and refuses to infer an owner from who usually handles a topic.

**Weigh up**The original frontmatter name contains spaces; adapt it to a valid Claude Code name in a separate working copy.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-meeting-notes-specialist/) Attributed definition available MIT
 Compare Meeting notes extractor Add

Documentation · Seth Hobson

### [Mermaid diagram author](/agents/wshobson-mermaid-expert/)

A diagram-authoring profile that asks for readable Mermaid source and a rendered check.

 mermaid diagrams architecture

**Why we selected it**It chooses the diagram type from the data and explicitly asks for a rendering test before delivery.

**Weigh up**No renderer is bundled; a model can emit invalid syntax, and a requested preview is not evidence that rendering happened.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-mermaid-expert/) Attributed definition available MIT
 Compare Mermaid diagram author Add

Infrastructure · VoltAgent

### [Microsoft 365 workload automation planner](/agents/voltagent-m365-admin/)

A Microsoft 365 profile for scoped mailbox, collaboration and license-lifecycle automation.

 microsoft-365 graph exchange

**Why we selected it**It distinguishes Graph from Exchange Online connection requirements before changing workload objects.

**Weigh up**No tenant connector, admin consent or module is bundled; Bash and edit permissions can make real account, access or license changes when credentials exist.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-m365-admin/) Attributed definition available MIT
 Compare Microsoft 365 workload automation planner Add

Documentation contribution · GitHub community

### [Microsoft Learn contribution guide](/agents/github-microsoft-learn-contributor/)

Guides a documentation contribution through article structure, Microsoft style, metadata and review feedback.

 Microsoft Learn documentation style

**Why we selected it**It distinguishes conceptual articles, tutorials, quickstarts and reference material before reviewing structure.

**Weigh up**The legacy MCP/tool aliases need mapping to the installed client; the definition does not configure the Learn connection.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/github-microsoft-learn-contributor/) Upstream setup linked MIT
 Compare Microsoft Learn contribution guide Add

Game server development · Seth Hobson

### [Minecraft server plugin engineer](/agents/wshobson-minecraft-bukkit-pro/)

Develops version-aware server plugin plans covering events, commands, configuration and measured tick performance.

 Paper Bukkit plugins

**Why we selected it**The source requires server/build inspection and profiling before optimization, and distinguishes Paper APIs from Bukkit/Spigot fallbacks.

**Weigh up**Official Paper guidance warns that world-state APIs are unsafe from asynchronous tasks; Folia requires its own schedulers.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-minecraft-bukkit-pro/) Attributed definition available MIT
 Compare Minecraft server plugin engineer Add

Model development · Seth Hobson

### [ML serving and lifecycle engineer](/agents/wshobson-ml-engineer/)

A production-ML planning and implementation profile covering serving, feature validation and model lifecycle checks.

 model-serving mlops monitoring

**Why we selected it**It includes holdout and temporal validation alongside online comparisons, rather than treating offline accuracy as the only deployment criterion.

**Weigh up**Listed serving frameworks are not bundled or verified current; production-ready wording is a target, and example throughput is not a measured result.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-ml-engineer/) Attributed definition available MIT
 Compare ML serving and lifecycle engineer Add

Model evaluation · Affaan Mustafa

### [MLE Reviewer](/agents/ecc-mle-reviewer/)

Reviews an ML change for leakage, reproducibility and serving safety, and starts by checking the diff is reviewable.

 ml review production

**Why we selected it**The decision line is APPROVE, APPROVE WITH WARNINGS, or BLOCK, and BLOCK includes leakage or a missing rollback.

**Weigh up**Bash can execute repository code; use existing approved tools and inspect test side effects. The prompt forbids installing new packages without approval.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-mle-reviewer/) Attributed definition available MIT
 Compare MLE Reviewer Add

Machine learning operations · Seth Hobson

### [MLOps pipeline engineer](/agents/wshobson-mlops-engineer/)

Plans reproducible training and serving infrastructure with artifact lineage, approval gates and operational monitoring.

 lineage model registry deployment

**Why we selected it**It connects dataset/model versioning and lineage to registry promotion and rollback rather than treating deployment as a one-step upload.

**Weigh up**This broad instruction profile includes no runnable pipeline, cloud account or vetted tool integration.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-mlops-engineer/) Attributed definition available MIT
 Compare MLOps pipeline engineer Add

Operations and reliability · Agency Agents

### [Mobile Release Engineer](/agents/agency-mobile-release-engineer/)

Engineers the signing-to-store path for iOS and Android with phased rollouts and a forward-fix-only recovery model, since shipped binaries cannot be rolled back.

 mobile release code signing fastlane

**Why we selected it**States the no-rollback constraint explicitly and requires phased rollouts with pre-defined halt-on-crash-spike thresholds plus a forward-fix path before shipping.

**Weigh up**Fastlane, match or secrets-manager storage, store accounts and CI runners must be configured in the host project; the file supplies the workflow, not credentials.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-mobile-release-engineer/) Attributed definition available MIT
 Compare Mobile Release Engineer Add

Data and retrieval · github

### [MongoDB Performance Advisor](/agents/github-mongodb-performance-advisor/)

Combines repository query patterns with read-only MongoDB diagnostics to explain query plans and index trade-offs.

 MongoDB query plans indexes

**Why we selected it**Stops when a read-only MongoDB MCP connection is unavailable instead of fabricating database observations.

**Weigh up**Requires the MongoDB MCP server configured read-only; Atlas Performance Advisor also needs the appropriate account access.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/agents/github-mongodb-performance-advisor/) Attributed definition available MIT
 Compare MongoDB Performance Advisor Add

Architecture and decisions · Seth Hobson

### [Monorepo architect](/agents/wshobson-monorepo-architect/)

Chooses a monorepo tool from the repository's constraints instead of naming one by fashion.

 monorepo builds ci

**Why we selected it**The workflow says to assess codebase size and team structure before selecting Nx, Turborepo, Bazel, or Lerna.

**Weigh up**The file does not install Nx, Turborepo, Bazel, or Lerna.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-monorepo-architect/) Upstream setup linked MIT
 Compare Monorepo architect Add

Mobile applications · Seth Hobson

### [Native iOS application engineer](/agents/wshobson-ios-developer/)

Plans native SwiftUI/UIKit work with lifecycle, persistence, accessibility and device validation concerns.

 SwiftUI UIKit accessibility

**Why we selected it**It includes SwiftUI/UIKit interoperability, background work and storage choices rather than treating the UI in isolation.

**Weigh up**The source targets an iOS 18/Xcode 16-era baseline; confirm SDK availability and platform policies for the actual project.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-ios-developer/) Attributed definition available MIT
 Compare Native iOS application engineer Add

Modernization and specifications · github

### [Neon Migration Specialist](/agents/github-neon-migration-specialist/)

Tests schema changes on a temporary Neon database branch and prepares migration files for a separate production rollout.

 Neon PostgreSQL database migrations

**Why we selected it**Explicitly forbids running migrations on the main Neon database branch and separates database branches from Git branches.

**Weigh up**Workflow adjustment is required: the description promises automated production application and zero downtime, while the body prohibits main-branch migrations. Use only the test-branch workflow, with no downtime guarantee.

 Source reviewed

7 sources · 2026-10-13

[Read the full review ↗](/agents/github-neon-migration-specialist/) Attributed definition available MIT
 Compare Neon Migration Specialist Add

Data and retrieval · GitHub partners

### [Neon Performance Analyzer](/agents/github-neon-performance-analyzer/)

Finds slow Postgres queries on a temporary Neon database branch, tests fixes on a second branch, and reports before-and-after metrics in a pull request.

 postgres neon query plans

**Why we selected it**Analysis and tests run on Neon database branches with a four-hour TTL, never the main database branch, and both branches are deleted at the end.

**Weigh up**If pg_stat_statements is missing, it enables the extension on the analysis branch and tells the user.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-neon-performance-analyzer/) Install command in review MIT
 Compare Neon Performance Analyzer Add

Infrastructure and delivery · affaan-m

### [Network Config Reviewer](/agents/ecc-network-config-reviewer/)

Audits router and switch configuration — Cisco IOS-style interfaces, ACLs, VTY, AAA, SNMP and routing blocks — returning severity-ranked findings with quoted evidence and a PASS/WARNING/BLOCK verdict.

 network configuration Cisco IOS ACLs

**Why we selected it**Anchors every finding to a quoted config snippet or block, and separates hard blockers from best-practice improvements before issuing a PASS/WARNING/BLOCK verdict.

**Weigh up**Scoped to Cisco IOS and IOS-XE style configuration; other vendors’ syntaxes are out of scope.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-network-config-reviewer/) Attributed definition available MIT
 Compare Network Config Reviewer Add

Operations and reliability · GitHub community

### [New Relic Incident Response Agent](/agents/github-new-relic-incident-response/)

Assesses a New Relic alert, investigates traces, errors and deployments, and proposes a code fix only after the engineer agrees to each phase.

 incident response new relic observability

**Why we selected it**If the New Relic MCP server is unavailable or misconfigured, it stops and names the missing server instead of guessing.

**Weigh up**The example incident report contains illustrative figures, such as a 15% error rate and an 8.5s trace. They show the format and are not results.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/github-new-relic-incident-response/) Attributed definition available MIT
 Compare New Relic Incident Response Agent Add

Operations and reliability · wshobson/agents

### [Observability Engineer](/agents/wshobson-observability-engineer/)

A planning prompt for telemetry coverage, service objectives, alert design and incident runbooks.

 observability slo telemetry

**Why we selected it**Connects metrics, logs and traces with service-level indicators and actionable incident response.

**Weigh up**This is a broad instruction profile, not an installed collector, dashboard, integration or compliance control.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-observability-engineer/) Attributed definition available MIT
 Compare Observability Engineer Add

Changelog editing · GitHub partners

### [Octopus Deploy release notes](/agents/github-octopus-release-notes/)

Reads the last release deployed to an Octopus project and environment and writes Markdown release notes from its commits.

 release notes octopus deploy MCP

**Why we selected it**The Octopus MCP tool list is read-only: every allowed tool is a get_ or list_ call, such as list_releases_for_project and get_release_by_id.

**Weigh up**It fetches commit diffs from GitHub, but no GitHub tool is declared. Whether that step works depends on the host's tools.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-octopus-release-notes/) Install command in review MIT
 Compare Octopus Deploy release notes Add

Planning and delivery · GitHub

### [One-shot feature issue planner](/agents/github-one-shot-feature-issue-planner/)

Writes one issue-ready plan and states operating rules before the workflow.

 planning issues scope

**Why we selected it**The operating rules forbid follow-up questions and forbid code changes.

**Weigh up**The no-questions rule can hide a missing fact; the file requires that fact to be labeled as an assumption.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-one-shot-feature-issue-planner/) Attributed definition available MIT
 Compare One-shot feature issue planner Add

Security and privacy · affaan-m

### [Open-Source Sanitizer](/agents/ecc-opensource-sanitizer/)

Independently audits a project before open-source release — 20+ secret-pattern scans, PII and internal-reference detection, dangerous-file checks, .env.example completeness, a git-history audit and a list of files that do not read as text — issuing PASS, PASS WITH WARNINGS or FAIL where any critical finding fails the release.

 secrets scanning PII open-source release

**Why we selected it**It is an adversarial second stage by design: it never trusts the forker’s work, re-scans every text file itself, and a single critical finding in any category is an overall FAIL.

**Weigh up**Regex scanning produces false positives by design — the definition accepts false positives over false negatives, and high-entropy heuristics are flagged for manual review rather than auto-failing.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-opensource-sanitizer/) Attributed definition available MIT
 Compare Open-Source Sanitizer Add

Modernization and specifications · GitHub

### [Oracle-to-PostgreSQL migration expert](/agents/github-oracle-to-postgres-migration-expert/)

Phases an Oracle-to-PostgreSQL migration and keeps the source as the behaviour to match.

 oracle postgresql migration

**Why we selected it**The file forbids applying database changes for the user and says to hand over scripts instead.

**Weigh up**Tools include edit and execute, so the no-direct-database-change rule is an instruction.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-oracle-to-postgres-migration-expert/) Upstream setup linked MIT
 Compare Oracle-to-PostgreSQL migration expert Add

Operations and reliability · GitHub partners

### [PagerDuty Incident Responder](/agents/github-pagerduty-incident-responder/)

Pulls a PagerDuty incident, correlates it with commits from the 24 hours before it started, and proposes a fix or rollback pull request.

 incident response pagerduty root cause

**Why we selected it**It forms a triage hypothesis by root-cause category (code change, configuration, dependency, infrastructure) and compares the incident start with deployment times before searching code.

**Weigh up**Declared tools include github/create_pull_request, create_issue, create_branch and create_or_update_file, which write to GitHub. Remove them unless a pull request is intended.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-pagerduty-incident-responder/) Install command in review MIT
 Compare PagerDuty Incident Responder Add

Marketing analysis · Agency Agents community

### [Paid search query analyst](/agents/agency-paid-media-search-query-analyst/)

A query-audit profile that requires actual account reports before suggesting negative keywords or expansion opportunities.

 search-terms negative-keywords intent-analysis

**Why we selected it**It considers account, campaign and ad-group negative scopes and cross-campaign overlap rather than producing one undifferentiated exclusion list.

**Weigh up**The source also instructs pushing negatives through an available integration; that can change paid campaigns. Zero conversions alone does not prove wasted spend, and percentage reduction targets are unmeasured.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-paid-media-search-query-analyst/) Upstream setup linked MIT
 Compare Paid search query analyst Add

Application integration · Agency Agents community

### [Payments and billing engineer](/agents/agency-payments-billing-engineer/)

Models payment mutations, subscriptions and fulfillment as retryable state machines with durable webhook intake and reconciliation.

 payments architecture validation

**Why we selected it**The example separates verified event acceptance from leased processing and only marks completion after side effects succeed.

**Weigh up**The inbox adapter, scheduler, domain handlers and ledger schema are application dependencies, not implemented by the prompt. Example API versions, PCI scope claims and business thresholds need current provider/qualified review; no payments were run.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-payments-billing-engineer/) Upstream setup linked MIT
 Compare Payments and billing engineer Add

Browser and performance · wshobson

### [Performance Engineer](/agents/wshobson-performance-engineer/)

Runs performance work measurement-first — establish a baseline, profile, then optimize — across browser Core Web Vitals, backend hot paths and load tests, with budgets and regression gates to hold the gains.

 performance Core Web Vitals profiling

**Why we selected it**The response protocol is measurement-first by construction: establish a performance baseline with comprehensive measurement and profiling before any optimization, then validate improvements and set budgets to prevent regression.

**Weigh up**A capability-list persona: it prescribes the measurement discipline in prose but carries no enforced evidence-citation contract, unlike a log-grounded monitor.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/wshobson-performance-engineer/) Attributed definition available MIT
 Compare Performance Engineer Add

Operations and reliability · voltagent

### [Performance Monitor](/agents/voltagent-performance-monitor/)

Reads existing metric, log and output files to surface performance anomalies, then writes an evidence-cited observability plan — every reported number must have been read from a file or counted, never invented.

 performance observability log analysis

**Why we selected it**Binds every reported figure to file evidence — a number may only be stated if it was read from a file or counted with Grep/Glob, and each finding carries path:line citations plus a high/medium/low confidence grade.

**Weigh up**Analyses only files that already exist; it cannot collect live metrics, query time-series databases or build dashboards.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/voltagent-performance-monitor/) Attributed definition available MIT
 Compare Performance Monitor Add

Testing and review · affaan-m

### [PHP Reviewer](/agents/ecc-php-reviewer/)

Reviews PHP changes by running PHPStan, Psalm and Pint where available, then ranks findings from SQL injection and mass assignment to Eloquent N+1, with Laravel, Livewire and Filament framework checks.

 php code review Laravel

**Why we selected it**Is the one reviewer in the family whose approval criteria bind to the automated checks — Block on any failed PHPStan, Psalm, PHPUnit or Pint run OR any CRITICAL/HIGH finding — so code the tools reject can never be approved.

**Weigh up**Closing pointers to sibling laravel-patterns, laravel-security and laravel-tdd skills reference companion files that are not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-php-reviewer/) Attributed definition available MIT
 Compare PHP Reviewer Add

Modernization and specifications · anthropics

### [Pilot-Driven Uplift Migrator](/agents/anthropic-uplift-migrator/)

Applies an approved pilot playbook to one migration unit and returns build evidence, playbook gaps and shared-file needs to the coordinating owner.

 version upgrades pilot playbook minimal changes

**Why we selected it**A missing pilot playbook is an explicit no-edit stop condition, while every gap must be reported even when the worker resolved it.

**Weigh up**Requires analysis/<system>/PLAYBOOK.md and DELTA_CATALOG.md plus an assigned unit. The agent and workflow prompt instruct checking the playbook; the JavaScript itself does not independently read or attest its existence or approval.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-uplift-migrator/) Attributed definition available Apache-2.0
 Compare Pilot-Driven Uplift Migrator Add

Operations and reliability · GitHub

### [Platform SRE for Kubernetes](/agents/github-platform-sre-kubernetes/)

Asks for the cluster facts before a deploy and treats security defaults as non-negotiable.

 kubernetes sre rollouts

**Why we selected it**Every change must include a plan, validation, rollout, and a rollback, and images must not use the latest tag.

**Weigh up**Tools include edit/editFiles and terminalCommand, so the file can change manifests and run kubectl.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-platform-sre-kubernetes/) Attributed definition available MIT
 Compare Platform SRE for Kubernetes Add

Testing and review · github

### [Playwright Test Explorer](/agents/github-playwright-tester/)

Explores a working interface through Playwright before generating and running TypeScript tests for its observed user flows.

 Playwright browser testing test generation

**Why we selected it**Prohibits writing test code until the agent has navigated the interface and identified its actual flows.

**Weigh up**Requires a configured Playwright MCP connection and a reachable application; the file does not install a browser server or the test framework.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-playwright-tester/) Attributed definition available MIT
 Compare Playwright Test Explorer Add

Agent development · Anthropic

### [Plugin agent creator](/agents/anthropic-agent-creator/)

Turns a description of a needed agent into an agents/<identifier>.md file with frontmatter, triggering examples and a system prompt.

 agents plugins frontmatter

**Why we selected it**Its own tools are Write and Read only, and its quality standards ask for least-privilege tool selection in the agent it writes.

**Weigh up**The file also offers to omit tools for full access. Unless you set the list, an agent it writes can inherit every tool.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-agent-creator/) Attributed definition available Apache-2.0
 Compare Plugin agent creator Add

Agent development · Anthropic

### [Plugin skill reviewer](/agents/anthropic-plugin-skill-reviewer/)

Reviews a skill file for structure, description triggers and progressive disclosure.

 skills review claude

**Why we selected it**Frontmatter tools are only Read, Grep and Glob, so the declared role does not include Write, Edit or Bash.

**Weigh up**The file is a Claude Code agent definition. It does not install a skill or certify one. A Markdown profile does not register a native subagent by itself.

 Source reviewed

2 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-plugin-skill-reviewer/) Upstream setup linked Apache-2.0
 Compare Plugin skill reviewer Add

Security and governance · wshobson

### [Policy Enforcer](/agents/wshobson-policy-enforcer/)

Authors Cedar rules for what an agent may do, and audits an existing policy instead of assuming it is enforced.

 cedar authorization tool-governance

**Why we selected it**The help steps start by asking for the risk profile and then prefer allow-listing over deny-listing.

**Weigh up**Frontmatter sets model to opus and does not declare tools.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-policy-enforcer/) Attributed definition available MIT
 Compare Policy Enforcer Add

Evaluation · Anthropic

### [Post-hoc skill analyzer](/agents/anthropic-skill-analyzer/)

Skill-creator agent that reads a finished blind comparison, then opens both skills and transcripts to say why the winner won.

 skills evaluation comparison

**Why we selected it**The catalogue has the skill-creator grader and not this post-hoc analyzer.

**Weigh up**This review did not execute the agent.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-skill-analyzer/) Upstream setup linked Apache-2.0
 Compare Post-hoc skill analyzer Add

Database administration · GitHub community

### [PostgreSQL extension operator](/agents/github-postgresql-dba/)

A small Copilot profile that routes database work through the PostgreSQL extension’s tools.

 postgresql vscode database-tools

**Why we selected it**The first gate checks that ms-ossdata.vscode-pgsql is installed and enabled before using its tools.

**Weigh up**This is a thin routing profile without backup verification, destructive-action gates or an enforced read-only mode; claimed DBA tasks are not validated implementations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-postgresql-dba/) Upstream setup linked MIT
 Compare PostgreSQL extension operator Add

Data modeling · GitHub community

### [Power BI data model planner](/agents/github-power-bi-data-modeling-expert/)

A Power BI profile for model grain, relationships and storage-mode decisions.

 power-bi star-schema relationships

**Why we selected it**It requires consistent fact-table grain and explicitly separates fact and dimension characteristics.

**Weigh up**The profile requires Microsoft documentation MCP and legacy tool aliases; it does not configure that server or prove a PBIX model correct.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-power-bi-data-modeling-expert/) Upstream setup linked MIT
 Compare Power BI data model planner Add

Data analysis · GitHub community

### [Power BI DAX reviewer](/agents/github-power-bi-dax-expert/)

A DAX-focused profile for formula semantics, readability and calculation debugging.

 power-bi dax filter-context

**Why we selected it**It distinguishes fully qualified column references from unqualified measure references.

**Weigh up**The prompt’s broad optimization rules are suggestions, not measurements; documentation-tool availability and DAX execution remain external requirements.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/github-power-bi-dax-expert/) Upstream setup linked MIT
 Compare Power BI DAX reviewer Add

Performance · GitHub community

### [Power BI performance investigator](/agents/github-power-bi-performance-expert/)

A Power BI profile separating query, model, report and capacity performance investigations.

 power-bi capacity query-performance

**Why we selected it**The profile separates DAX/query work from visual rendering, model size and capacity pressure.

**Weigh up**Example queries and target thresholds were not run; performance improvement depends on representative data, capacity and repeated measurements.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-power-bi-performance-expert/) Upstream setup linked MIT
 Compare Power BI performance investigator Add

Data visualization · GitHub community

### [Power BI report designer](/agents/github-power-bi-visualization-expert/)

A Power BI visualization profile for report hierarchy, interactions and accessible layouts.

 power-bi report-design accessibility

**Why we selected it**It distinguishes executive, analytical and operational report layouts rather than prescribing a single dashboard for every audience.

**Weigh up**Embedded-report and Business Central snippets are separate integration examples, not a ready-to-deploy report; custom visuals and tenant permissions need review.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-power-bi-visualization-expert/) Upstream setup linked MIT
 Compare Power BI report designer Add

Programming · VoltAgent

### [PowerShell 7 cross-platform automation engineer](/agents/voltagent-powershell-7-expert/)

A scripting profile emphasizing portable paths, structured CI output and explicit tenant context.

 powershell cross-platform cloud-automation

**Why we selected it**It checks subscription/tenant context and module compatibility before cloud automation.

**Weigh up**The referenced .NET 6/7 knowledge is not a current runtime requirement; module portability and WhatIf/Confirm behavior must be verified per command.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-powershell-7-expert/) Attributed definition available MIT
 Compare PowerShell 7 cross-platform automation engineer Add

Security operations · VoltAgent

### [PowerShell automation hardening reviewer](/agents/voltagent-powershell-security-hardening/)

A PowerShell security profile for remoting boundaries, credential handling and sanitized operational logs.

 powershell remoting least-privilege

**Why we selected it**It considers scheduled tasks, WinRM endpoints and automation service accounts as part of the script’s security context.

**Weigh up**Execution Policy is not an authorization boundary; logging can itself capture sensitive values, and this profile grants shell and edit tools. Named compliance baselines are not bundled.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-powershell-security-hardening/) Attributed definition available MIT
 Compare PowerShell automation hardening reviewer Add

Code review · Anthropic

### [PR toolkit code reviewer](/agents/anthropic-pr-code-reviewer/)

Pins the pr-review-toolkit code reviewer, which defaults to unstaged git diff and tells itself to drop issues below a confidence cutoff.

 claude review diff

**Why we selected it**The catalogue has feature-dev's code-reviewer at a different path and not this pr-review-toolkit agent.

**Weigh up**This review did not execute the resource.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-pr-code-reviewer/) Upstream setup linked Apache-2.0
 Compare PR toolkit code reviewer Add

Security and privacy · agency

### [Privacy Engineer](/agents/agency-privacy-engineer/)

Implements privacy as code — PII discovery across every store including logs and caches, consent enforced at the write path, fan-out deletion pipelines with verification scans, and re-identification testing before anything is called anonymized.

 privacy engineering GDPR PII discovery

**Why we selected it**Every rule is an engineering control with a named failure mode: consent must gate the write rather than just set a flag, deletion must fan out to replicas, indexes, caches, third parties and backups with an audit record, and retention must expire by automated job.

**Weigh up**Engineering guidance, not legal advice; the legal-basis and retention decisions it demands still need a qualified reviewer per jurisdiction.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-privacy-engineer/) Attributed definition available MIT
 Compare Privacy Engineer Add

Operations and reliability · wshobson

### [Prod Logs Health Check](/agents/wshobson-prod-logs-health-check/)

Pulls recent production logs after a deploy or load test and reports errors grouped by root cause, counting distinct failures separately from retries — treating raw logs, not dashboards, as the only acceptable primary source.

 log analysis incident response production

**Why we selected it**Makes raw logs the mandatory primary source and refuses to present inference as fact — if logs were not checked, the finding must say so before anything is presented.

**Weigh up**The definition is a template: the {{LOG_QUERY}} and {{PROJECT_SPECIFIC_MARKERS}} placeholders must be pointed at the project’s real log source before use.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/wshobson-prod-logs-health-check/) Attributed definition available MIT
 Compare Prod Logs Health Check Add

Operations · Agency Agents community

### [Production incident coordination planner](/agents/agency-engineering-incident-response-commander/)

A response-coordination profile with role, timeline, mitigation and follow-up templates.

 incident-command runbooks postmortems

**Why we selected it**It separates commander, technical lead, communications and scribe responsibilities so troubleshooting and external updates have clear owners.

**Weigh up**The sample severity thresholds, timing and error-budget policy are organization-specific templates; the profile does not grant emergency production or messaging authority.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-incident-response-commander/) Upstream setup linked MIT
 Compare Production incident coordination planner Add

Security workflow components · Seth Hobson

### [Protect MCP receipt verifier](/agents/wshobson-receipt-verifier/)

A receipt-review component that separates valid signatures, invalid signatures and undecidable verification.

 signed-receipts offline-verification provenance

**Why we selected it**The profile uses the external public key rather than trusting a key embedded in an untrusted receipt.

**Weigh up**A signature failure can mean a wrong key or malformed record, so the source’s tampering attribution must be softened. Signed tool names do not prove policy enforcement or actual tool effects.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-receipt-verifier/) Upstream setup linked MIT
 Compare Protect MCP receipt verifier Add

Testing and review · anthropics

### [Pull Request Test Analyzer](/agents/anthropic-pr-test-analyzer/)

Maps a pull request to its tests and identifies meaningful missing failure cases, brittle assertions and uncovered behavioral contracts.

 tests pull requests regressions

**Why we selected it**Prioritizes tests by concrete regressions they would prevent rather than chasing line coverage.

**Weigh up**Its internal numerical criticality rubric is a prioritization instruction, not a measured quality score or a catalogue rating.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-pr-test-analyzer/) Attributed definition available Apache-2.0
 Compare Pull Request Test Analyzer Add

Data and analytics · GitHub community

### [PySpark Expert Agent](/agents/github-spark-performance/)

Reviews PySpark pipeline code for distributed-execution anti-patterns with confidence-graded hypotheses, Spark-native fixes, and a ban on inventing runtime evidence.

 PySpark Spark performance review

**Why we selected it**Evidence discipline is explicit: it must not invent Spark UI metrics or runtime evidence, and must ask for the minimum evidence such as explain output, stage symptoms, sizing and AQE state needed to confirm.

**Weigh up**Static heuristics without cluster evidence stay hypotheses; confirm Medium and Low confidence findings against explain plans and the Spark UI before acting.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/github-spark-performance/) Attributed definition available MIT
 Compare PySpark Expert Agent Add

Data and analytics · GitHub community

### [Python Notebook Sample Builder](/agents/github-python-notebook-sample-builder/)

Builds a new Python demonstration notebook from snippets checked in the selected development environment.

 python jupyter examples

**Why we selected it**The file says not to put code in a notebook until it has been run in the terminal.

**Weigh up**The prompt assumes a development container and broad package-install permissions; do not apply that assumption to an arbitrary host.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-python-notebook-sample-builder/) Attributed definition available MIT
 Compare Python Notebook Sample Builder Add

Testing and review · affaan-m

### [Python Reviewer](/agents/ecc-python-reviewer/)

Reviews Python changes by running ruff, mypy, black and bandit where available before reading the diff, then ranks findings from f-string SQL injection and bare except to type-hint gaps and un-Pythonic patterns.

 python code review type hints

**Why we selected it**Structures the review around executed diagnostics — ruff, mypy, pylint and black --check run before the diff is read, and the documented command set adds bandit and pytest with coverage, so findings rest on tool output rather than opinion.

**Weigh up**The closing pointer to a sibling python-patterns skill references a companion file that is not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-python-reviewer/) Attributed definition available MIT
 Compare Python Reviewer Add

Build and runtime diagnostics · Affaan Mustafa

### [PyTorch build error resolver](/agents/ecc-pytorch-build-resolver/)

Traces tensor shapes, devices and gradient paths to diagnose a bounded training or inference crash.

 PyTorch diagnostics minimal fixes

**Why we selected it**The workflow starts at the failing line, traces shapes through layers, then reruns the failing script and checks autograd.

**Weigh up**Several fix-table suggestions can change semantics: clamping embedding indices, adding retain_graph or changing layer widths must be justified by the model/data contract.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-pytorch-build-resolver/) Upstream setup linked MIT
 Compare PyTorch build error resolver Add

Testing and review · github

### [QA Test Planner and Investigator](/agents/github-qa-subagent/)

Builds a requirement-linked test plan, explores failure paths and reports reproducible bugs separately from potential improvements.

 QA test planning exploratory testing

**Why we selected it**Organizes tests by boundary, negative, failure, concurrency and security cases, then prioritizes by risk.

**Weigh up**It grants broad edit, execute, delegation and web tool categories; the role’s focus is not a technical read-only restriction.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-qa-subagent/) Attributed definition available MIT
 Compare QA Test Planner and Investigator Add

Data and retrieval · affaan-m

### [Rag Pipeline Reviewer](/agents/ecc-rag-pipeline-reviewer/)

Reviews retrieval pipelines for grounding, pruning, fallback behavior and evaluation policy, returning a structured approval, conditional approval or block decision.

 rag reranking ragas

**Why we selected it**Role boundary is negative as well as positive: do not rewrite the LLM answer prompt; hand off to named specialists.

**Weigh up**The read-only Bash rule is an instruction; the host must enforce the intended access boundary.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-rag-pipeline-reviewer/) Attributed definition available MIT
 Compare Rag Pipeline Reviewer Add

Testing and review · affaan-m

### [React Reviewer](/agents/ecc-react-reviewer/)

Reviews React and JSX changes for hook correctness, dangerouslySetInnerHTML and URL-scheme security, server/client component boundaries, key stability and render performance — reporting findings without rewriting code.

 react code review hooks

**Why we selected it**Owns an explicit scope table that splits React-specific lanes (hooks, dangerouslySetInnerHTML, server/client boundaries, NEXT_PUBLIC leaks) from the generic TypeScript reviewer, so the two roles compose instead of duplicating.

**Weigh up**Full .tsx coverage needs the sibling typescript-reviewer for generic type-safety lanes; this file reviews React-specific concerns only.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-react-reviewer/) Attributed definition available MIT
 Compare React Reviewer Add

Documentation · VoltAgent

### [Readme Generator](/agents/voltagent-readme-generator/)

Builds a repository README from inspected manifests, scripts, tests and entry points, explicitly rejecting guessed commands, APIs and configuration.

 readme documentation repository-analysis

**Why we selected it**Requires setup commands, configuration and usage examples to be extracted from actual repository evidence.

**Weigh up**The opening context-manager request assumes a coordinator not supplied by the standalone file. Provide the repository purpose and audience directly when using it alone.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/voltagent-readme-generator/) Attributed definition available MIT
 Compare Readme Generator Add

Realtime systems · Agency Agents community

### [Realtime collaboration protocol designer](/agents/agency-engineering-realtime-collaboration-engineer/)

Plans collaborative-state protocols around replay, operation identity, convergence tests and bounded fan-out.

 sync presence CRDT

**Why we selected it**It separates ephemeral presence TTLs from durable document operations and explicitly rejects unbounded slow-consumer queues.

**Weigh up**The snippets omit application-owned durable queue, operation application and authentication helpers; there is no complete sync engine here.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-realtime-collaboration-engineer/) Upstream setup linked MIT
 Compare Realtime collaboration protocol designer Add

Model evaluation · GitHub

### [Research Harness Engineer](/agents/github-research-harness-engineer/)

Treats a reported score as guilty until a null model and a published baseline have been checked.

 evaluation benchmarks research

**Why we selected it**The file requires a null model and a reproduced baseline before any improvement claim.

**Weigh up**No tool allowlist or executable harness is included; datasets, metrics and compute must be supplied.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/github-research-harness-engineer/) Attributed definition available MIT
 Compare Research Harness Engineer Add

Research and product · msitarzewski

### [Research Synthesist](/agents/agency-research-synthesist/)

Builds an auditable synthesis that traces repeated claims to their origin and separates independent agreement, disagreement and missing evidence.

 literature review source quality citations

**Why we selected it**Explicitly rejects counting repeated citations to one study as independent corroboration.

**Weigh up**The frontmatter name is the display name “Research Synthesist” and its color is the hex value #9333EA, which is not one of the eight documented Claude Code colors; adapt both in a working copy.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/agency-research-synthesist/) Attributed definition available MIT
 Compare Research Synthesist Add

Security workflow components · Seth Hobson

### [Review governance policy author](/agents/wshobson-review-policy-author/)

A policy-authoring component for identifying which review, merge and CI-edit commands need an approval gate.

 cedar review-approval policy-authoring

**Why we selected it**It distinguishes raw-command substring matching from reliable identity or semantic authorization: no human_approved attribute is available.

**Weigh up**The approval flag bypasses policy until removed; a writable flag is not independently verified human approval. String matching can be bypassed, and the plugin deliberately permits some other public writes.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-review-policy-author/) Upstream setup linked MIT
 Compare Review governance policy author Add

Code review · Anthropic

### [Rust API Ergonomics Reviewer](/agents/anthropics-rust-api-ergonomics-reviewer/)

Reviews a Rust library from the downstream user’s side, and confirms a suspected lint with cargo before reporting it.

 rust api ergonomics

**Why we selected it**The role is limited to what a downstream Rust user types, sees in compiler output, and can misuse. Correctness bugs, performance and unsafe soundness are left to other review.

**Weigh up**Bash is enabled. The git/cargo allowlist and prohibition on repository edits live in prompt text; they are not an operating-system sandbox.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropics-rust-api-ergonomics-reviewer/) Upstream setup linked Apache-2.0
 Compare Rust API Ergonomics Reviewer Add

Build and runtime diagnostics · Affaan Mustafa

### [Rust build error resolver](/agents/ecc-rust-build-resolver/)

Resolves Rust compilation, ownership, trait and Cargo-feature errors with a minimal-change verification loop.

 Rust diagnostics minimal fixes

**Why we selected it**It inspects duplicate dependencies and enabled features, preferring a targeted package update to a full lockfile refresh.

**Weigh up**Cloning, RefCell, added lifetime bounds and edition changes are contextual proposals, not interchangeable compiler fixes. Preserve API semantics and MSRV.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-rust-build-resolver/) Upstream setup linked MIT
 Compare Rust build error resolver Add

Security review · Trail of Bits

### [Rust review dedup judge](/agents/trailofbits-rust-review-dedup-judge/)

Pins the rust-review dedup judge that merges only obvious duplicates, aborts when the finding list cannot be loaded, and does not declare a shell.

 rust review dedup

**Why we selected it**The agents index has the c-review worker and not plugins/rust-review/agents/rust-review-dedup-judge.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-rust-review-dedup-judge/) Install command in review CC-BY-SA-4.0
 Compare Rust review dedup judge Add

Security review · Trail of Bits

### [Rust review FP judge](/agents/trailofbits-rust-review-fp-judge/)

Pins the rust-review judge that runs after dedup, aborts when it cannot obtain a finding list, and must not invent the SARIF file.

 rust security review

**Why we selected it**The agents catalogue has no sourcePath for plugins/rust-review/agents/rust-review-fp-judge.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-rust-review-fp-judge/) Install command in review CC-BY-SA-4.0
 Compare Rust review FP judge Add

Security review · Trail of Bits

### [Rust review worker](/agents/trailofbits-rust-review-worker/)

Pins the rust-review worker that aborts a malformed or primer spawn, writes findings only inside its scope root, and does not filter them by severity.

 rust security review

**Why we selected it**The agents catalogue has no sourcePath for plugins/rust-review/agents/rust-review-worker.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-rust-review-worker/) Install command in review CC-BY-SA-4.0
 Compare Rust review worker Add

Testing and review · affaan-m

### [Rust Reviewer](/agents/ecc-rust-reviewer/)

Reviews Rust changes by running cargo check, clippy, fmt and test before reading the diff, then ranks findings from unchecked unwrap and unjustified unsafe to ownership, concurrency and allocation issues.

 rust code review ownership

**Why we selected it**Gates the review on executed commands — cargo check, clippy with -D warnings, fmt --check and cargo test must run before review begins, so findings rest on tool output rather than opinion.

**Weigh up**The closing pointer to a sibling rust-patterns skill references a companion file that is not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-rust-reviewer/) Attributed definition available MIT
 Compare Rust Reviewer Add

Security review · Trail of Bits

### [Rust source analyzer](/agents/trailofbits-2b-rust-source-analyzer/)

Pins the zeroize-audit Rust source analyzer that keeps a weak reference match, merges shared JSON without replacing C or C++ entries, and continues after rustdoc failure.

 rust zeroize source-analysis

**Why we selected it**The agents index has no entry for plugins/zeroize-audit/agents/2b-rust-source-analyzer.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-2b-rust-source-analyzer/) Install command in review CC-BY-SA-4.0
 Compare Rust source analyzer Add

Rust maintenance · Agency Agents community

### [Rust workspace refactoring specialist](/agents/agency-rust-refactoring-specialist/)

Plans and completes coherent Rust refactors while tracing public contracts, feature gates and observable behaviour.

 Rust refactoring compatibility

**Why we selected it**It treats drop timing, lock scope, cancellation, serialization and error behaviour as contracts, not just function signatures.

**Weigh up**The profile requires explicit authorization for destructive Git operations, publishing/deployment and other named sensitive changes; these are prompt instructions, so reconcile them with task authorization and effective host permissions before execution.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-rust-refactoring-specialist/) Attributed definition available MIT
 Compare Rust workspace refactoring specialist Add

Enterprise applications · GitHub community

### [Salesforce Apex and trigger engineer](/agents/github-salesforce-apex-triggers/)

Plans Apex changes from existing org patterns, with sharing/data-access review and positive, negative and bulk tests.

 Apex triggers bulk testing

**Why we selected it**It inspects sfdx-project.json, package.xml and existing handlers/factories before choosing a service, selector or asynchronous pattern.

**Weigh up**The pinned model alias and legacy tool names need mapping to supported Copilot capabilities.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-salesforce-apex-triggers/) Attributed definition available MIT
 Compare Salesforce Apex and trigger engineer Add

Modernization and specifications · anthropics

### [Scaffolder](/agents/anthropic-scaffolder/)

Creates one modernization service from an approved architecture and specification, including its domain model, API stubs and rule-linked acceptance tests.

 modernization scaffolding acceptance-tests

**Why we selected it**Limits the intended work to one caller-selected service directory so independently scaffolded services do not overwrite one another.

**Weigh up**Requires REIMAGINED_ARCHITECTURE.md, AI_NATIVE_SPEC.md and the caller’s modernized service path; the complete modernization workflow is not included.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-scaffolder/) Attributed definition available Apache-2.0
 Compare Scaffolder Add

Language development · Seth Hobson

### [Scala effects and distributed-systems developer](/agents/wshobson-scala-pro/)

A Scala profile for effect boundaries, typed domain models and distributed streams.

 scala effect-systems pekko

**Why we selected it**The profile separates Cats Effect or ZIO effects from pure domain models and calls out explicit error channels.

**Weigh up**It lists many alternative stacks without selecting dependency versions; scalability language is aspirational and not benchmark evidence.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-scala-pro/) Attributed definition available MIT
 Compare Scala effects and distributed-systems developer Add

Security review · Anthropic

### [Scan inventory](/agents/anthropic-scan-inventory/)

Pins the Claude Security cartographer that partitions one tree and must place every listed top-level directory on a scanned or skipped ledger.

 claude security inventory

**Why we selected it**The agents index has no entry for plugins/claude-security/agents/scan-inventory.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-scan-inventory/) Install command in review Proprietary — Anthropic internal-use terms
 Compare Scan inventory Add

Security review · Anthropic

### [Scan loader](/agents/anthropic-scan-loader/)

Pins the Claude Security loader whose only input is one directory plus one file name, and that returns that JSON unchanged.

 claude security json

**Why we selected it**The agents index has no entry for plugins/claude-security/agents/scan-loader.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-scan-loader/) Install command in review Proprietary — Anthropic internal-use terms
 Compare Scan loader Add

Security review · Anthropic

### [Scan redactor](/agents/anthropic-scan-redactor/)

Pins the Claude Security redactor that edits nothing unless the dispatch names three specific report files, and that tells itself not to repeat a secret in the reply.

 claude security redaction

**Why we selected it**The agents index has no entry for plugins/claude-security/agents/scan-redactor.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-scan-redactor/) Install command in review Proprietary — Anthropic internal-use terms
 Compare Scan redactor Add

Security review · Anthropic

### [Scan verifier](/agents/anthropic-scan-verifier/)

Pins the Claude Security voter that takes one candidate finding and tries to disprove it, with a false-positive default and a file-and-line citation rule.

 claude security verification

**Why we selected it**The agents index has no repository and sourcePath entry for plugins/claude-security/agents/scan-verifier.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-scan-verifier/) Install command in review Proprietary — Anthropic internal-use terms
 Compare Scan verifier Add

Security and governance · github

### [Se: Responsible Ai](/agents/github-se-responsible-ai-code/)

Screens user-facing changes for accessibility, privacy and exclusion concerns, then documents decisions and escalation needs in numbered responsible-AI records.

 bias privacy accessibility

**Why we selected it**Step 2–4 give concrete tests: culturally varied names/ages/edge strings, keyboard vs clickable div, alt text, minimal vs excessive data collection, unbundled consent.

**Weigh up**The illustrative name and demographic examples are screening prompts, not validated fairness tests or a compliance assessment.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-se-responsible-ai-code/) Attributed definition available MIT
 Compare Se: Responsible Ai Add

Documentation · github

### [Se: Tech Writer](/agents/github-se-technical-writer/)

Turns code and design context into audience-specific documentation, tutorials, articles and decision records using explicit structures and a verification checklist.

 technical-writing templates adr

**Why we selected it**Content-type templates are fully specified, including ADR status/deciders/consequences/alternatives and task-oriented user-guide workflows with verification checkpoints.

**Weigh up**The frontmatter permits file editing and web retrieval but does not name an execution tool; testing or compiling examples needs a separate runner.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-se-technical-writer/) Attributed definition available MIT
 Compare Se: Tech Writer Add

Accessibility · Agency Agents

### [Section 508 Accessibility Specialist](/agents/agency-section-508-specialist/)

Audits and remediates web accessibility against the correct legal baseline (508 equals WCAG 2.0 AA) with assistive-technology testing, and reports honest VPAT conformance.

 accessibility WCAG Section 508

**Why we selected it**WCAG criterion references were screened against current W3C text with no misidentification found, including 1.3.1 Info and Relationships (A) and the 4.5:1 and 3:1 contrast thresholds, unlike the excluded a11y-architect's 2.4.11 error.

**Weigh up**The 30 to 40 percent automated-tool coverage figures are the author's estimates, not independently measured here; treat them as cautionary guidance.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-section-508-specialist/) Attributed definition available MIT
 Compare Section 508 Accessibility Specialist Add

Security and governance · anthropics

### [Security Auditor](/agents/anthropic-security-auditor/)

Reviews application code with a stack-specific security checklist, requiring source locations, exploit scenarios, concrete remediation and masked secrets in each finding.

 application-security owasp cwe

**Why we selected it**Demands a plausible exploit scenario and a concrete code-level fix rather than unsupported vulnerability labels.

**Weigh up**Bash and package auditors depend on host permissions and tool availability; the definition does not enforce its read-only boundary.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-security-auditor/) Attributed definition available Apache-2.0
 Compare Security Auditor Add

Browser and performance · ecc

### [SEO Specialist](/agents/ecc-seo-specialist/)

Audits technical SEO from the repository's actual files — crawl blockers, canonical loops, redirect chains, malformed JSON-LD, heading hierarchy — and reports each finding as a severity-ranked issue with file location and exact fix.

 technical SEO structured data canonical URLs

**Why we selected it**The audit is file-grounded and severity-ranked: critical crawl and index blockers, canonical loops and redirect chains outrank cosmetic issues, and every finding must carry a path:line or URL location plus an exact fix.

**Weigh up**Reads source files; it does not crawl the deployed site or fetch live index state, so runtime-only issues (server headers, production redirect behaviour) need separate verification.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-seo-specialist/) Attributed definition available MIT
 Compare SEO Specialist Add

Infrastructure and delivery · Seth Hobson

### [Service mesh expert](/agents/wshobson-service-mesh-expert/)

Treats a mesh change as traffic, security and observability, not as a sidecar install.

 service-mesh istio linkerd

**Why we selected it**The workflow orders topology, mTLS and authorization, observability, traffic rules, failover tests, and runbooks.

**Weigh up**Frontmatter sets model to opus and does not declare tools or install Istio or Linkerd.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-service-mesh-expert/) Attributed definition available MIT
 Compare Service mesh expert Add

Security and governance · Trail of Bits

### [Sharp Edges Analyzer](/agents/trailofbits-sharp-edges-analyzer/)

Evaluates APIs, configurations and library interfaces for misuse resistance — probing zero, empty and negative edge cases and modelling three adversary types before reporting design-level security findings, each with a minimal misuse example.

 security threat modeling API design

**Why we selected it**Turns threat modelling into a repeatable four-phase procedure — surface identification, systematic edge-case probing (zero/empty/null, negative values, type confusion, defaults, error paths), threat modelling against three named adversary models, and validation that requires reproducing the misuse and confirming exploitability before reporting.

**Weigh up**The language-specific footgun guides it reads on demand live in sibling reference files inside the same plugin (plugins/sharp-edges/skills/sharp-edges/references/), not in the agent definition itself.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/trailofbits-sharp-edges-analyzer/) Attributed definition available CC-BY-SA-4.0
 Compare Sharp Edges Analyzer Add

Code review · Affaan Mustafa

### [Silent failure hunter](/agents/ecc-silent-failure-hunter/)

Looks for swallowed errors and bad fallbacks, and requires an output format.

 errors fallbacks review

**Why we selected it**The hunt list names empty catches, log-and-forget handling, and fallbacks that hide a failure.

**Weigh up**Tools include Bash, while the output is a report rather than a required code edit.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-silent-failure-hunter/) Attributed definition available MIT
 Compare Silent failure hunter Add

Evaluation · Anthropic

### [Skill eval grader](/agents/anthropic-skill-eval-grader/)

Grades each expectation pass or fail from cited evidence, treats uncertainty as a failure, and writes grading.json.

 evals grading skills

**Why we selected it**The inputs are expectations, a transcript path, and an outputs directory, and each expectation is pass or fail.

**Weigh up**This plain Markdown role has no native frontmatter or tool allowlist; provide it through an orchestrator with appropriate output inspection tools.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-skill-eval-grader/) Upstream setup linked Apache-2.0
 Compare Skill eval grader Add

Testing and review · Trail of Bits

### [Skill reviewer fixture](/agents/trailofbits-skill-reviewer/)

Reviews one Claude Code skill from a loop dispatch, writes nothing, and leaves a rejected ledger finding closed unless the evidence is new.

 claude-code skill-review read-only

**Why we selected it**The description says it reviews one skill per dispatch and is not for general code review.

**Weigh up**A Markdown profile does not register a native subagent by itself.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-skill-reviewer/) Install command in review CC-BY-SA-4.0
 Compare Skill reviewer fixture Add

Language and communication · Agency Agents community

### [Spanish–English context translator](/agents/agency-language-translator/)

A bilingual drafting profile that carries meaning, formality and regional context into Spanish–English translations.

 spanish english register

**Why we selected it**It preserves names and brands unless an established localized equivalent or user request applies.

**Weigh up**Text-generated pronunciation is approximate, regional generalizations need review, and this profile does not provide certified translation or a qualified clinical interpreter.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-language-translator/) Attributed definition available MIT
 Compare Spanish–English context translator Add

Data and analytics · Agency Agents

### [Spatial Data Engineer](/agents/agency-spatial-data-engineer/)

A geospatial ETL planning prompt centered on source preservation, explicit coordinate systems and transformation checks.

 geospatial etl crs

**Why we selected it**Requires original files to be preserved and transformations to write to a new location.

**Weigh up**The frontmatter name “Spatial Data Engineer” contains spaces. Current Claude Code documentation describes name as a unique identifier, with examples such as code-reviewer, and forbids only “:”. Give the working copy an identifier such as spatial-data-engineer; this download remains byte-identical to upstream.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/agency-spatial-data-engineer/) Attributed definition available MIT
 Compare Spatial Data Engineer Add

Spatial analysis · Agency Agents community

### [Spatial data scientist](/agents/agency-gis-spatial-data-scientist/)

A spatial-analysis profile that connects geographic patterns to diagnostics, uncertainty and reproducible research.

 spatial-statistics geospatial uncertainty

**Why we selected it**It explicitly tests spatial dependence in residuals and sensitivity to aggregation boundaries rather than treating a visually persuasive map as evidence.

**Weigh up**The blanket wording about non-spatial models is overbroad: appropriateness depends on assumptions and diagnostics. No model is fitted by the profile itself and named Python/R/GIS packages are not bundled.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-gis-spatial-data-scientist/) Attributed definition available MIT
 Compare Spatial data scientist Add

Modernization and specifications · affaan-m

### [Spec Miner](/agents/ecc-spec-miner/)

Extracts a selected brownfield capability into source-linked OpenSpec requirements and invariants while limiting writes to the specification directory.

 openspec brownfield requirements

**Why we selected it**Write may only create openspec/specs/<capability>/spec.md; Bash must stay read-only—rare path-scoped reviewer-writer.

**Weigh up**Its output is tailored to OpenSpec; a different specification workflow requires adaptation.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-spec-miner/) Attributed definition available MIT
 Compare Spec Miner Add

Documentation and knowledge · GitHub community

### [Specification Writer](/agents/github-specification/)

Develops implementation specifications with explicit requirements, interfaces, constraints and acceptance examples.

 specifications requirements acceptance-tests

**Why we selected it**The specification must be self-contained Markdown and must follow the template sections in the file.

**Weigh up**File-edit, test and web tools are declared; constrain them to the agreed documentation task.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-specification/) Attributed definition available MIT
 Compare Specification Writer Add

Testing and review · Trail of Bits (Omar Inuwa)

### [Specification-to-Code Checker](/agents/trailofbits-spec-compliance-checker/)

Checks one quoted requirement against its implementation paths and records the enforcement evidence, gaps and unresolved questions.

 specifications requirements call chains

**Why we selected it**Separates implemented, partially enforced, contradicted, absent, stronger-than-specified and undecidable requirements instead of forcing a binary pass/fail.

**Weigh up**The file requires the plugin’s sibling analysis format and domain references; {baseDir} must resolve before use.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/agents/trailofbits-spec-compliance-checker/) Attributed definition available CC-BY-SA-4.0
 Compare Specification-to-Code Checker Add

Media engineering · Agency Agents community

### [Speech transcript pipeline designer](/agents/agency-engineering-voice-ai-integration-engineer/)

A speech-pipeline reference covering audio validation, chunked ASR, speaker assignment and structured output.

 transcription diarization subtitles

**Why we selected it**It preserves timestamps and low-confidence review flags rather than silently deleting uncertain speech.

**Weigh up**The sample requests word timestamps but discards them in its segment object, and whole-segment overlap trimming can lose boundary content. Local-only medical claims and improvement percentages are unsupported generalizations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-voice-ai-integration-engineer/) Upstream setup linked MIT
 Compare Speech transcript pipeline designer Add

Data and analytics · wshobson/agents

### [SQL Pro](/agents/wshobson-sql-pro/)

A SQL review prompt covering query plans, schema design, indexing and read/write performance tradeoffs.

 sql query-plans indexes

**Why we selected it**Asks for usage patterns and realistic data before treating an index or rewrite as an optimization.

**Weigh up**SQL features and tuning advice are not portable across all named engines. Supply the exact engine, version, schema and workload.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-sql-pro/) Attributed definition available MIT
 Compare SQL Pro Add

Security and governance · GitHub partners

### [StackHawk Security Onboarding](/agents/github-stackhawk-security-onboarding/)

Decides whether a repository is a deployed web app or API, and if so opens a pull request with a stackhawk.yml and a GitHub Actions scan workflow.

 dast api security github actions

**Why we selected it**Its first step assesses attack surface: it declines for libraries and documentation or configuration repositories, offers a review when stackhawk.yml already exists, and asks when unsure.

**Weigh up**The workflow template pins actions/checkout@v3 and stackhawk/hawkscan-action@v2 by tag, not by commit SHA.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/github-stackhawk-security-onboarding/) Install command in review MIT
 Compare StackHawk Security Onboarding Add

Data analysis · Seth Hobson

### [Statistical analysis and experiment scientist](/agents/wshobson-data-scientist/)

An analysis profile that connects data profiling, statistical assumptions and validation to a concrete business question.

 statistics experiments reproducibility

**Why we selected it**It explicitly separates statistical from practical significance and calls for assumption checks and robustness validation.

**Weigh up**The long methods list is aspirational expertise, not evidence that a method was correctly applied; observational data alone cannot establish causal effects.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-data-scientist/) Attributed definition available MIT
 Compare Statistical analysis and experiment scientist Add

Security and governance · 0xSteph

### [STIG analyst](/agents/pentest-stig-analyst/)

Writes a STIG-shaped finding and a keep-open justification, and does not certify the system.

 stig hardening compliance

**Why we selected it**The finding format includes impact, a risk-to-remediate score, what could break, remediation, and a scriptable verification.

**Weigh up**A formatted finding is not a certification, and the file does not claim one.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/agents/pentest-stig-analyst/) Attributed definition available MIT
 Compare STIG analyst Add

Research and product · msitarzewski

### [Study Design and Evidence Statistician](/agents/agency-statistician/)

Examines the chain from research question and measurement to comparison, analysis and decision, making assumptions and uncertainty explicit.

 study design statistics causal inference

**Why we selected it**Separates descriptive, predictive and causal questions before choosing a study or interpreting a result.

**Weigh up**The prompt does not supply data, a statistical runtime or a validated analysis package. Calculations require suitable tools and reproducible inputs.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/agency-statistician/) Attributed definition available MIT
 Compare Study Design and Evidence Statistician Add

Framework development · Svelte

### [Svelte File Editor](/agents/svelte-file-editor/)

A focused Svelte editing prompt that consults current documentation and iterates with the Svelte MCP static checker.

 svelte components documentation

**Why we selected it**Separates Svelte component work into a focused agent context with relevant documentation.

**Weigh up**This listing recommends the configured Svelte MCP path. The prompt’s fallback CLI and normalized tool-name variants were not runtime-tested; map names to the tools your host actually exposes.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/agents/svelte-file-editor/) Attributed definition available MIT
 Compare Svelte File Editor Add

Build and runtime diagnostics · Affaan Mustafa

### [Swift build error resolver](/agents/ecc-swift-build-resolver/)

Diagnoses Swift/Xcode compilation, package resolution and concurrency errors, with explicit stops for signing or ownership redesign.

 Swift diagnostics minimal fixes

**Why we selected it**It distinguishes SPM resolution, protocol/type failures, actor isolation and Sendable issues.

**Weigh up**Xcode diagnostics require the appropriate Apple toolchain and available destinations; signing identities are local account information.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/ecc-swift-build-resolver/) Upstream setup linked MIT
 Compare Swift build error resolver Add

Testing and review · affaan-m

### [Swift Reviewer](/agents/ecc-swift-reviewer/)

Reviews Swift changes by running swift build, swiftlint and swift test first — stopping to report if any fail — then ranks findings from force unwrapping and actor-isolation races to ARC cycles and release-build assertion traps.

 swift code review iOS

**Why we selected it**Runs the hardest gate in the family — swift build, swiftlint and swift test must all pass or the review stops to report — so the reviewer never approves code the toolchain rejects.

**Weigh up**Closing pointers to sibling swift rules and skills (swift-concurrency-6-2, swiftui-patterns, swift-protocol-di-test) reference companion files that are not part of this standalone definition.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-swift-reviewer/) Attributed definition available MIT
 Compare Swift Reviewer Add

Testing and review · github

### [Systematic Debugging](/agents/github-debug-mode/)

Reproduces an application bug, tests root-cause hypotheses and verifies a minimal fix against the original failure.

 debugging reproduction root cause

**Why we selected it**Requires reproduction and an expected-versus-actual report before changing code.

**Weigh up**The procedure is a general debugging framework, so the caller must provide a concrete symptom and a usable reproduction environment.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-debug-mode/) Attributed definition available MIT
 Compare Systematic Debugging Add

Decision support · Trail of Bits

### [Tarot draw](/agents/trailofbits-draw/)

Pins the let-fate-decide agent that makes one script call for a twelve-house spread and returns a short verdict, or a fixed line if that call fails.

 planning tarot entropy

**Why we selected it**The agents catalogue has no sourcePath for plugins/let-fate-decide/agents/draw.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-draw/) Install command in review CC-BY-SA-4.0
 Compare Tarot draw Add

Testing and reliability · GitHub community

### [TDD Green Phase](/agents/github-tdd-green/)

Implements the smallest behavior change needed to satisfy an existing failing test.

 tdd green tests

**Why we selected it**Green-phase rules say to implement only the current issue and not to modify the failing test.

**Weigh up**Green tests demonstrate only the asserted examples; hidden requirements and untested behavior still need review.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-tdd-green/) Attributed definition available MIT
 Compare TDD Green Phase Add

Testing and reliability · GitHub community

### [TDD Red Phase](/agents/github-tdd-red/)

Writes a failing test tied to a requirement before implementation work begins.

 tdd red tests

**Why we selected it**The red phase says to write one failing test at a time and never to start edits without user confirmation.

**Weigh up**An issue number inferred from a branch name must be verified against the intended repository and issue.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-tdd-red/) Attributed definition available MIT
 Compare TDD Red Phase Add

Testing and reliability · GitHub community

### [TDD Refactor Phase](/agents/github-tdd-refactor/)

Improves a tested implementation through small changes while preserving the existing behavior checks.

 tdd refactor tests

**Why we selected it**Refactoring is allowed only after tests are green, and only after the user confirms the plan.

**Weigh up**Security suggestions and passing tests are not a security audit or proof of behavioral equivalence.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-tdd-refactor/) Attributed definition available MIT
 Compare TDD Refactor Phase Add

Creative tooling · Agency Agents community

### [Technical art pipeline planner](/agents/agency-technical-artist/)

A cross-engine technical-art profile linking asset handoff to measured rendering budgets.

 technical-art asset-budgets lod

**Why we selected it**It puts asset budgets before content production and requires in-engine review under target lighting.

**Weigh up**The sample shader and numeric budget tables are examples, not portable working assets or universal requirements; the fixed LOD-count rule needs project-specific judgment.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-technical-artist/) Upstream setup linked MIT
 Compare Technical art pipeline planner Add

Sales enablement · Agency Agents community

### [Technical evaluation and POC designer](/agents/agency-sales-engineer/)

A presales planning profile that turns buyer requirements into measurable proof-of-concept criteria and a focused demo.

 technical-discovery poc evidence-based-demos

**Why we selected it**The POC template agrees success criteria, scope and measurement methods before setup and includes an interim alignment review.

**Weigh up**Example benchmarks, timelines and customer outcomes are illustrative; deal-closing pressure must not justify omitting a failed criterion or inventing a reference.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-sales-engineer/) Attributed definition available MIT
 Compare Technical evaluation and POC designer Add

Research and product · github

### [Technical Spike Research Mode](/agents/github-research-technical-spike/)

Investigates a supplied technical-spike document through cited documentation, repository examples and separately approved experiments, recording findings and dead ends as work proceeds.

 spike documentation experimentation

**Why we selected it**Stops when no spike document is provided and ties the work to explicit research questions and success criteria.

**Weigh up**The recursive research policy has no fixed time or cost budget; define a stopping condition for the chosen spike.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-research-technical-spike/) Attributed definition available MIT
 Compare Technical Spike Research Mode Add

Documentation · Agency Agents

### [Technical Writer](/agents/agency-technical-writer/)

Writes developer documentation with a tested-snippet rule and docs-as-code pipeline guidance, so examples and versioned docs stay runnable instead of drifting.

 technical writing developer documentation API references

**Why we selected it**Requires every code example to be tested before it ships and docs to match the software version they describe, deprecating rather than deleting old docs.

**Weigh up**The 5-second, 30-second and 15-minute usability bars are author heuristics, not measured outcomes; treat them as editorial guidance.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/agency-technical-writer/) Attributed definition available MIT
 Compare Technical Writer Add

Maintenance planning · GitHub community

### [Technical-debt remediation planner](/agents/github-tech-debt-remediation-plan/)

Turns a specified maintenance problem into a concise Markdown remediation plan with prerequisites, ordered steps and verification methods.

 technical debt testing gaps documentation

**Why we selected it**The body limits the role to a remediation plan and says the work is analysis only, with no code modifications.

**Weigh up**The frontmatter still lists edit, command, test, browser, and web/fetch tools, so the analysis-only sentence is not a tool allowlist.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-tech-debt-remediation-plan/) Upstream setup linked MIT
 Compare Technical-debt remediation planner Add

Framework development · wshobson

### [Temporal Python Pro](/agents/wshobson-temporal-python-pro/)

Implements durable workflows on the Temporal Python SDK — deterministic workflow code, activity heartbeats and retry policies, the three worker execution patterns, saga compensation and testing strategies for long-running processes.

 Temporal workflow orchestration durable execution

**Why we selected it**The three worker execution patterns (async activities, sync multithreaded, sync multiprocess) are matched to workload types, with the stated anti-pattern that blocking the async event loop turns async programs into serial execution.

**Weigh up**A builder persona, not a reviewer; beyond its testing-strategy section it has no verification gate on what it produces.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/wshobson-temporal-python-pro/) Attributed definition available MIT
 Compare Temporal Python Pro Add

Infrastructure and delivery · GitHub partners

### [Terraform Agent](/agents/github-terraform-agent/)

Resolves provider and module versions from the Terraform registry before writing code, then manages HCP Terraform workspaces and runs through the Terraform MCP server.

 terraform hcp terraform registry

**Why we selected it**Versions are resolved with get_latest_provider_version or get_latest_module_version before code is written, and the private registry is searched before the public one when a token is present.

**Weigh up**The MCP server runs hashicorp/terraform-mcp-server:latest in Docker; the tag is not pinned.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/agents/github-terraform-agent/) Install command in review MIT
 Compare Terraform Agent Add

Infrastructure and delivery · github

### [Terraform Iac Reviewer](/agents/github-terraform-iac-reviewer/)

Reviews and drafts Terraform changes with a plan summary, impact assessment, validation sequence, approval before apply, and an explicit recovery discussion.

 terraform iac-review state-safety

**Why we selected it**Every change must include plan summary (add/change/destroy counts), risk assessment, validation commands, and a rollback strategy.

**Weigh up**Terminal and editing access can change infrastructure. Approval before apply is an instruction, not an enforced host permission boundary.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-terraform-iac-reviewer/) Attributed definition available MIT
 Compare Terraform Iac Reviewer Add

Infrastructure orchestration · VoltAgent

### [Terragrunt orchestration engineer](/agents/voltagent-terragrunt-expert/)

Organizes Terragrunt units, stacks, includes and dependencies with attention to state and multi-environment execution.

 Terragrunt dependency graphs state

**Why we selected it**It distinguishes explicit stack blueprints from directory-based stacks and separates dependency outputs from ordering.

**Weigh up**The source gives version-sensitive CLI/HCL examples and an undefined DRY percentage; verify syntax and report actual changes rather than repeating example metrics.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-terragrunt-expert/) Attributed definition available MIT
 Compare Terragrunt orchestration engineer Add

Infrastructure and delivery · github

### [Terratest Module Testing](/agents/github-terratest-module-testing/)

Designs Terraform module tests around outputs, validation failures and isolated setup and cleanup, with cloud applies explicitly gated.

 Terraform Terratest Go

**Why we selected it**Distinguishes success paths, expected failures and staged integration tests rather than treating every module test as a deployment.

**Weigh up**The original tool list declares only legacy codebase and terminalCommand aliases. Map them to current read/search/execute tools and explicitly add an editor for writing tests; verify its pinned model is available.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/github-terratest-module-testing/) Attributed definition available MIT
 Compare Terratest Module Testing Add

Testing and review · anthropics

### [Test Engineer](/agents/anthropic-test-engineer/)

Writes characterization tests and dual-run harnesses that pin legacy behavior before modernization, preserving unresolved target behavior as explicitly pending tests.

 characterization-tests legacy-oracle dual-run-harness

**Why we selected it**The body pins tests to literal inputs/outputs and dual-run comparison against legacy or a recorded trace, not to spec-as-intent.

**Weigh up**Frontmatter grants Write, Edit, and unrestricted Bash; the modernized/-only and never-edit-legacy/ rules are prompt text, not a sandbox.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-test-engineer/) Attributed definition available Apache-2.0
 Compare Test Engineer Add

Security review · Trail of Bits

### [Test generator](/agents/trailofbits-6-test-generator/)

Pins the zeroize-audit test generator that stops when the final findings report is missing and still writes an empty manifest when nothing is confirmed.

 tests harness makefile

**Why we selected it**The agents index has no entry for plugins/zeroize-audit/agents/6-test-generator.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-6-test-generator/) Install command in review CC-BY-SA-4.0
 Compare Test generator Add

Security and governance · wshobson

### [Threat Modeling Expert](/agents/wshobson-threat-modeling-expert/)

Structures a security design review around trust boundaries, data flows, attack paths, mitigations and residual risks.

 threat modeling STRIDE trust boundaries

**Why we selected it**Provides a concrete sequence from scope and assets through STRIDE and attack trees to documented residual risk.

**Weigh up**This is a design-review role, not a scanner, penetration test or compliance certificate.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-threat-modeling-expert/) Attributed definition available MIT
 Compare Threat Modeling Expert Add

Security and privacy · GitHub community

### [Trojan Skill Hunter](/agents/github-trojan-skill-hunter/)

Reviews agent instructions, hooks and MCP configuration as untrusted text before installation.

 prompt-injection skills mcp

**Why we selected it**The file says reviewed content is untrusted data and must not be executed, fetched, or installed.

**Weigh up**Prompt instructions cannot make a model immune to prompt injection or replace isolated tooling and least-privilege access.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/github-trojan-skill-hunter/) Attributed definition available MIT
 Compare Trojan Skill Hunter Add

Security review · Trail of Bits

### [TU compiler analyzer](/agents/trailofbits-3-tu-compiler-analyzer/)

Pins the zeroize-audit per-file compiler analyzer that stops without compile flags, refuses a finding that lacks the evidence it names, and deletes that unit's temporary artifacts.

 compiler ir assembly

**Why we selected it**The agents index has no entry for plugins/zeroize-audit/agents/3-tu-compiler-analyzer.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-3-tu-compiler-analyzer/) Install command in review CC-BY-SA-4.0
 Compare TU compiler analyzer Add

Testing and review · anthropics

### [Type Design Analyzer](/agents/anthropic-type-design-analyzer/)

Reviews domain types by identifying their invariants, checking where those invariants are enforced, and weighing safer designs against complexity and compatibility.

 invariants encapsulation pr-review

**Why we selected it**Fixed per-type report: invariants list, four rated axes with justification, Strengths, Concerns, Recommended Improvements.

**Weigh up**Its numerical design rubric is subjective guidance, not a measured quality score or compiler result.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/anthropic-type-design-analyzer/) Attributed definition available Apache-2.0
 Compare Type Design Analyzer Add

Testing and review · affaan-m

### [TypeScript Reviewer](/agents/ecc-typescript-reviewer/)

Reviews TypeScript/JavaScript diffs with merge-readiness, typecheck and lint gates first, reporting findings without rewriting code.

 typescript type-safety review-gates

**Why we selected it**Establishes review scope without hard-coding main, then stops and reports on red CI, merge conflicts, failed typecheck/lint or empty scope instead of reviewing blindly.

**Weigh up**Runs tsc/eslint via Bash; the project's own check commands execute, so sandbox or resource consequences belong to the host configuration.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-typescript-reviewer/) Attributed definition available MIT
 Compare TypeScript Reviewer Add

Evidence review · Undominated.ai

### [Undominated · 3D parallelism architect](/agents/undominated-3d-parallelism-architect/)

Architects balanced 3D parallelism configurations (TP, PP, DP, SP) for massive LLM serving clusters.

 serving 3d-parallelism megatron

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Produces architectural blueprints and configuration matrices; does not provision physical clusters.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-3d-parallelism-architect/) Attributed definition available MIT
 Compare Undominated · 3D parallelism architect Add

Evidence review · Undominated.ai

### [Undominated · Adversarial Red Teamer](/agents/undominated-adversarial-red-teamer/)

Classifies supplied reports of prompt-injection and jailbreak failures. It does not generate bypasses or run attacks.

 red-teamer adversarial jailbreak-testing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Does not produce payloads, bypass steps, or a claim that a model is safe.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-adversarial-red-teamer/) Attributed definition available MIT
 Compare Undominated · Adversarial Red Teamer Add

Evidence review · Undominated.ai

### [Undominated · Agent cascade failure auditor](/agents/undominated-agent-cascade-failure-auditor/)

Audits multi-agent autonomous chains for failure cascades, hallucinated handoffs, and infinite retry loops.

 evaluation multi-agent failure-cascades

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates task failure probabilities and handoff schema schemas; does not execute agent tool steps.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-agent-cascade-failure-auditor/) Attributed definition available MIT
 Compare Undominated · Agent cascade failure auditor Add

Evidence review · Undominated.ai

### [Undominated · Agent State Budget Architect](/agents/undominated-agent-state-budget-architect/)

Architects conversation state pruning, sliding context windows, and tool output summarization to control multi-turn token costs.

 agent-state context-budget compaction

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs state compaction algorithms. Does not write domain-specific business application logic.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-agent-state-budget-architect/) Attributed definition available MIT
 Compare Undominated · Agent State Budget Architect Add

Evidence review · Undominated.ai

### [Undominated · Agent trajectory pruning specialist](/agents/undominated-trajectory-pruning-specialist/)

Multi-turn log auditor specializing in identifying conversational bloat, redundant tool executions, memory leaks, and obsolete context across agent trajectories.

 agents pruning logs

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Modifies no session storage directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-trajectory-pruning-specialist/) Attributed definition available MIT
 Compare Undominated · Agent trajectory pruning specialist Add

Evidence review · Undominated.ai

### [Undominated · Agent workflow economist](/agents/undominated-agent-workflow-economist/)

Autonomous agent economist specializing in multi-step agent orchestration efficiency, tool schema minimization, function call consolidation, and token-preserving memory architectures.

 agents workflows economics

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Executes no code directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-agent-workflow-economist/) Attributed definition available MIT
 Compare Undominated · Agent workflow economist Add

Evidence review · Undominated.ai

### [Undominated · AI resource curator](/agents/undominated-resource-curator/)

Review skills, agents and MCP servers against a concrete use case, with pinned identity, rights and runtime evidence.

 curation skills agents

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-resource-curator/) Install command in review MIT
 Compare Undominated · AI resource curator Add

Evidence review · Undominated.ai

### [Undominated · Attention Architecture Economist](/agents/undominated-attention-architecture-economist/)

Models serving economics and hardware footprint trade-offs across Multi-Head Attention (MHA), Grouped-Query Attention (GQA), and Multi-Head Latent Attention (MLA).

 mha gqa mla

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Models memory bandwidth and KV capacity math. Does not assess architectural training convergence.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-attention-architecture-economist/) Attributed definition available MIT
 Compare Undominated · Attention Architecture Economist Add

Evidence review · Undominated.ai

### [Undominated · Attention Sink Custodian](/agents/undominated-attention-sink-custodian/)

Manages initial token attention sink preservation and sliding window buffers in infinite-horizon streaming generation.

 attention-sink streaming-llm kv-cache

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Configures attention sink preservation. Does not modify model base architecture.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-attention-sink-custodian/) Attributed definition available MIT
 Compare Undominated · Attention Sink Custodian Add

Evidence review · Undominated.ai

### [Undominated · Batch pipeline architect](/agents/undominated-batch-pipeline-architect/)

Systems architect specializing in asynchronous batch inference pipelines, SLA deadline management, partial batch ingestion, and automated synchronous fallback cascades.

 batch pipelines architecture

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Does not submit batch jobs or manage cloud infrastructure.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-batch-pipeline-architect/) Attributed definition available MIT
 Compare Undominated · Batch pipeline architect Add

Evidence review · Undominated.ai

### [Undominated · Benchmark rigor auditor](/agents/undominated-benchmark-rigor-auditor/)

Evaluation integrity specialist auditing public benchmark leaderboards for test set contamination, cherry-picked task splits, and uncalibrated significance claims.

 benchmarks rigor evaluation

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Treats published claims as hypotheses to verify.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-benchmark-rigor-auditor/) Attributed definition available MIT
 Compare Undominated · Benchmark rigor auditor Add

Evidence review · Undominated.ai

### [Undominated · Cache retention evaluator](/agents/undominated-cache-retention-evaluator/)

Audits needle-in-a-haystack retrieval accuracy under aggressive KV cache compression strategies.

 evaluation needle-in-haystack retrieval

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates pass rates on synthetic needle-in-a-haystack and long-context benchmarks; does not generate answers.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-cache-retention-evaluator/) Attributed definition available MIT
 Compare Undominated · Cache retention evaluator Add

Evidence review · Undominated.ai

### [Undominated · Canary Rollout Commander](/agents/undominated-canary-rollout-commander/)

Orchestrates traffic splitting, statistical drift detection, and automated rollbacks for model migrations.

 canary-rollout traffic-splitting automated-rollback

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Orchestrates routing policies and statistical health monitoring.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-canary-rollout-commander/) Attributed definition available MIT
 Compare Undominated · Canary Rollout Commander Add

Evidence review · Undominated.ai

### [Undominated · Chunked Prefill Tuner](/agents/undominated-chunked-prefill-tuner/)

Calibrates chunked prefill batch parameters to achieve target ITL p99 while maintaining prefill throughput.

 chunked-prefill itl-tuning vllm-config

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Tunes engine flags and scheduling parameters.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-chunked-prefill-tuner/) Attributed definition available MIT
 Compare Undominated · Chunked Prefill Tuner Add

Evidence review · Undominated.ai

### [Undominated · Comparison editor](/agents/undominated-comparison-editor/)

Edit model-comparison copy so ties, same-seller tiers and dropped requirements are not published as dominance.

 comparison wording pricing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/undominated-comparison-editor/) Install command in review MIT
 Compare Undominated · Comparison editor Add

Evidence review · Undominated.ai

### [Undominated · Constrained Decoding Optimizer](/agents/undominated-constrained-decoding-optimizer/)

Optimizes JSON schema compilation, regex FSM caching, and token masking to maximize structured output throughput.

 constrained-decoding json-schema fsm

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Optimizes FSM compilation and vocabulary masking. Does not alter JSON Schema semantics.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-constrained-decoding-optimizer/) Attributed definition available MIT
 Compare Undominated · Constrained Decoding Optimizer Add

Evidence review · Undominated.ai

### [Undominated · Context parallelism planner](/agents/undominated-context-parallelism-planner/)

Plans context-parallel serving topologies for 1M+ token context windows using Ring and Ulysses algorithms.

 serving context-parallelism ring-attention

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs cluster layout and network bandwidth contracts; does not allocate GPU memory dynamically.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-context-parallelism-planner/) Attributed definition available MIT
 Compare Undominated · Context parallelism planner Add

Evidence review · Undominated.ai

### [Undominated · Continuous Eval Guardian](/agents/undominated-continuous-eval-guardian/)

Maintains continuous regression evaluation harnesses across production endpoints to detect silent capability degradation.

 continuous-eval regression-testing monitoring

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Maintains evaluation harnesses and generates alerts. Does not modify external provider endpoints.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-continuous-eval-guardian/) Attributed definition available MIT
 Compare Undominated · Continuous Eval Guardian Add

Evidence review · Undominated.ai

### [Undominated · Crawl auditor](/agents/undominated-crawl-auditor/)

Review a sitemap or llms.txt before publication, so an English-only path is not locale-prefixed and a markdown link names a file that was written.

 seo crawl locale

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants. It does not fetch the live site to paper over a missing local file.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-crawl-auditor/) Attributed definition available MIT
 Compare Undominated · Crawl auditor Add

Evidence review · Undominated.ai

### [Undominated · Delivery-class reviewer](/agents/undominated-delivery-class-reviewer/)

Review a dominance sentence before it treats batch delivery, or a model's own other delivery, as a like-for-like beater.

 delivery batch dominance

**Why we selected it**The profile separates delivery class from price and capability, and it forbids a dominated sentence when the challenger is the same seller and the same weights on another delivery.

**Weigh up**The profile does not compute a price, a score, or a rank, and it does not admit a rate.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-delivery-class-reviewer/) Attributed definition available MIT
 Compare Undominated · Delivery-class reviewer Add

Evidence review · Undominated.ai

### [Undominated · Disaggregated Serving Architect](/agents/undominated-disaggregated-serving-architect/)

Designs separate prefill and decode GPU clusters connected via RDMA to eliminate TTFT and ITL scheduling interference.

 disaggregation prefill-decode cluster-architecture

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs cluster topology and network routing. Does not administer physical switches.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-disaggregated-serving-architect/) Attributed definition available MIT
 Compare Undominated · Disaggregated Serving Architect Add

Evidence review · Undominated.ai

### [Undominated · Distributed Context Engineer](/agents/undominated-distributed-context-engineer/)

Architects sequence-parallel, RingAttention, and context-parallel clusters for million-token inference pipelines.

 ring-attention sequence-parallel long-context

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs distributed attention topologies. Does not manage Kubernetes cluster provisioning.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-distributed-context-engineer/) Attributed definition available MIT
 Compare Undominated · Distributed Context Engineer Add

Evidence review · Undominated.ai

### [Undominated · Draft Model Calibrator](/agents/undominated-draft-model-calibrator/)

Aligns draft model tokenizer, temperature, and logit distributions with the verifier model to maximize acceptance rates.

 draft-model calibration acceptance-rate

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Calibrates sampling parameters and evaluates alignment. Does not retrain base models.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-draft-model-calibrator/) Attributed definition available MIT
 Compare Undominated · Draft Model Calibrator Add

Evidence review · Undominated.ai

### [Undominated · Draft verification auditor](/agents/undominated-draft-verification-auditor/)

Profiles draft verification kernels to prevent compute overhead from outpacing verification gains.

 serving speculative-decoding verification

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Profiles kernel execution times and memory bandwidth; does not alter kernel code directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-draft-verification-auditor/) Attributed definition available MIT
 Compare Undominated · Draft verification auditor Add

Evidence review · Undominated.ai

### [Undominated · Dynamic Routing Economist](/agents/undominated-dynamic-routing-economist/)

Architects real-time cost-and-latency aware multi-provider routing proxies that arbitrage spot price shifts.

 dynamic-routing arbitrage multi-provider

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs routing algorithms and fallback logic.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-dynamic-routing-economist/) Attributed definition available MIT
 Compare Undominated · Dynamic Routing Economist Add

Evidence review · Undominated.ai

### [Undominated · Edge AI deployment architect](/agents/undominated-edge-ai-deployment-architect/)

Sizes models for edge hardware (Apple Silicon, mobile NPUs, local workstations) to eliminate cloud API spend.

 serving edge-ai on-device

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Formulates hardware sizing blueprints; does not compile binary firmware directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-edge-ai-deployment-architect/) Attributed definition available MIT
 Compare Undominated · Edge AI deployment architect Add

Evidence review · Undominated.ai

### [Undominated · Enterprise Compliance Guardian](/agents/undominated-enterprise-compliance-guardian/)

Audits Zero Data Retention (ZDR), HIPAA, SOC2, and sovereign data boundary commitments across commercial AI providers.

 compliance zdr hipaa

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits technical and contractual provider commitments. Does not provide legal counsel.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-enterprise-compliance-guardian/) Attributed definition available MIT
 Compare Undominated · Enterprise Compliance Guardian Add

Evidence review · Undominated.ai

### [Undominated · Enterprise compliance officer](/agents/undominated-enterprise-compliance-officer/)

Enterprise compliance and regulatory risk auditor evaluating AI inference pipelines against GDPR data sovereignty, EU AI Act risk classifications, HIPAA BAA requirements, and SOC 2 Type II controls.

 compliance gdpr hipaa

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Provides technical guidance; does not replace legal counsel.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-enterprise-compliance-officer/) Attributed definition available MIT
 Compare Undominated · Enterprise compliance officer Add

Evidence review · Undominated.ai

### [Undominated · Eval harness auditor](/agents/undominated-eval-harness-auditor/)

Audit LLM evaluation harnesses, judge prompt rubrics, scoring determinism, and benchmark data hygiene to eliminate evaluation leaks and spurious rankings.

 evals harness judges

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-eval-harness-auditor/) Attributed definition available MIT
 Compare Undominated · Eval harness auditor Add

Evidence review · Undominated.ai

### [Undominated · Evidence reviewer](/agents/undominated-evidence-reviewer/)

Independently challenge numerical claims using source identity, denominator reconstruction and repeatable calculations.

 evidence audit pricing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-evidence-reviewer/) Install command in review MIT
 Compare Undominated · Evidence reviewer Add

Evidence review · Undominated.ai

### [Undominated · Expert Load Balancer Auditor](/agents/undominated-expert-load-balancer-auditor/)

Monitors router entropy, expert skew, and load balancing auxiliary loss regularization in production MoE models.

 moe load-balancing router-skew

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits routing frequencies and logit entropy. Does not retrain router gating weights.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-expert-load-balancer-auditor/) Attributed definition available MIT
 Compare Undominated · Expert Load Balancer Auditor Add

Evidence review · Undominated.ai

### [Undominated · Failover router architect](/agents/undominated-failover-router-architect/)

Systems resilience architect designing active-active multi-provider inference topologies with zero-loss retries, automated circuit breaking, and cross-region failover.

 failover routing resilience

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Provisions no cloud infrastructure directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-failover-router-architect/) Attributed definition available MIT
 Compare Undominated · Failover router architect Add

Evidence review · Undominated.ai

### [Undominated · GPU Footprint & Sharding Architect](/agents/undominated-gpu-footprint-calculator/)

Calculates required GPU VRAM, tensor parallelism sharding (TP=2, 4, 8), and minimum cluster configurations for hosting open-weight models.

 gpu vram sharding

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Estimates exclude framework runtime overheads (CUDA context, PyTorch activation memory). Always add 15-20% headroom.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-gpu-footprint-calculator/) Attributed definition available MIT
 Compare Undominated · GPU Footprint & Sharding Architect Add

Evidence review · Undominated.ai

### [Undominated · GPU Utilization Optimizer](/agents/undominated-gpu-utilization-optimizer/)

Implements autoscaling, sleep modes, and batch backfilling to maximize hardware utilization and eliminate idle power waste.

 utilization autoscaling batch-backfill

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Implements scheduling and autoscaling strategies.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-gpu-utilization-optimizer/) Attributed definition available MIT
 Compare Undominated · GPU Utilization Optimizer Add

Evidence review · Undominated.ai

### [Undominated · Graph RAG Cost Optimizer](/agents/undominated-graph-rag-cost-optimizer/)

Tunes entity extraction prompts and graph traversal depths to balance retrieval precision and token spend.

 graph-rag cost-optimizer retrieval

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Optimizes extraction templates and traversal parameters.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-graph-rag-cost-optimizer/) Attributed definition available MIT
 Compare Undominated · Graph RAG Cost Optimizer Add

Evidence review · Undominated.ai

### [Undominated · Guardrail Overhead & Latency Analyst](/agents/undominated-guardrail-overhead-analyst/)

Analyzes the throughput, latency, and financial token overhead of enterprise AI safety and moderation layers.

 guardrails safety latency

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Reviews operational telemetry and token logs. Does not establish legal compliance guarantees.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-guardrail-overhead-analyst/) Attributed definition available MIT
 Compare Undominated · Guardrail Overhead & Latency Analyst Add

Evidence review · Undominated.ai

### [Undominated · Hardware Infrastructure Planner](/agents/undominated-hardware-infrastructure-planner/)

Sizes on-premise GPU clusters based on enterprise peak and off-peak token demand profiles and CapEx payback models.

 infrastructure-planning gpu-cluster capex

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Models capacity, power, and amortization economics.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-hardware-infrastructure-planner/) Attributed definition available MIT
 Compare Undominated · Hardware Infrastructure Planner Add

Evidence review · Undominated.ai

### [Undominated · Hierarchical Memory Architect](/agents/undominated-hierarchical-memory-architect/)

Designs multi-tiered memory architectures combining working memory, episodic summaries, and graph knowledge.

 agent-memory hierarchical-memory architecture

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs memory schemas and compaction pipelines.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-hierarchical-memory-architect/) Attributed definition available MIT
 Compare Undominated · Hierarchical Memory Architect Add

Evidence review · Undominated.ai

### [Undominated · Hybrid SSM serving architect](/agents/undominated-hybrid-ssm-serving-architect/)

Architects hybrid Transformer-Mamba/SSM inference pipelines for extreme token throughput.

 serving hybrid mamba

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Configures hybrid serving parameters; does not modify model checkpoint weights.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-hybrid-ssm-serving-architect/) Attributed definition available MIT
 Compare Undominated · Hybrid SSM serving architect Add

Evidence review · Undominated.ai

### [Undominated · In-Context Example Pruner](/agents/undominated-in-context-example-pruner/)

Audits the marginal accuracy contribution of few-shot exemplars and prunes low-ROI examples to trim token costs.

 few-shot exemplars pruning

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates exemplar ablation datasets.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-in-context-example-pruner/) Attributed definition available MIT
 Compare Undominated · In-Context Example Pruner Add

Evidence review · Undominated.ai

### [Undominated · Indirect Injection Defender](/agents/undominated-indirect-injection-defender/)

Designs untrusted data isolation boundaries and document sanitization filters to prevent indirect prompt injection.

 indirect-injection data-sanitization isolation

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs data isolation architectures and filtering rules.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-indirect-injection-defender/) Attributed definition available MIT
 Compare Undominated · Indirect Injection Defender Add

Evidence review · Undominated.ai

### [Undominated · Inference CI/CD Architect](/agents/undominated-inference-cicd-architect/)

Integrates model quality, latency, and cost regression gates into continuous integration and automated deployment pipelines.

 cicd continuous-integration deployment-gates

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs CI/CD pipelines and quality gates.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-inference-cicd-architect/) Attributed definition available MIT
 Compare Undominated · Inference CI/CD Architect Add

Evidence review · Undominated.ai

### [Undominated · Inference Firewall Engineer](/agents/undominated-inference-firewall-engineer/)

Architects low-latency security firewalls, prompt injection classifiers, and rate limiters at the API gateway layer.

 firewall prompt-injection gateway

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Architects gateway security rules. Does not patch underlying model base weights.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-inference-firewall-engineer/) Attributed definition available MIT
 Compare Undominated · Inference Firewall Engineer Add

Evidence review · Undominated.ai

### [Undominated · Inference Scaling Strategist](/agents/undominated-inference-scaling-strategist/)

Analyzes test-time compute scaling laws, verifier passes, and search budgets to optimize accuracy per dollar spend.

 test-time-compute scaling-laws reasoning

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Focuses on cost-per-accuracy optimization. Does not train verifier reward models.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-inference-scaling-strategist/) Attributed definition available MIT
 Compare Undominated · Inference Scaling Strategist Add

Evidence review · Undominated.ai

### [Undominated · Inference SLO Gate Architect](/agents/undominated-slo-gate-architect/)

Defines and enforces strict latency, availability, and error budget SLO gates for production AI gateways.

 slo sli reliability

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**SLOs require observable telemetry data. Cannot guarantee performance on uninstrumented endpoints.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-slo-gate-architect/) Attributed definition available MIT
 Compare Undominated · Inference SLO Gate Architect Add

Evidence review · Undominated.ai

### [Undominated · Inference SRE architect](/agents/undominated-inference-sre-architect/)

Designs production observability, SLO alert thresholds, and automated traffic shedding for inference platforms.

 serving sre observability

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs observability architecture and alerting thresholds; does not configure live monitoring daemons.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-inference-sre-architect/) Attributed definition available MIT
 Compare Undominated · Inference SRE architect Add

Evidence review · Undominated.ai

### [Undominated · Judge Model Calibrator](/agents/undominated-judge-model-calibrator/)

Calibrates LLM judge prompts with few-shot calibration anchors to eliminate position bias and rating drift.

 judge-calibration llm-judge bias-elimination

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Calibrates judge prompts and scoring guidelines.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-judge-model-calibrator/) Attributed definition available MIT
 Compare Undominated · Judge Model Calibrator Add

Evidence review · Undominated.ai

### [Undominated · KV eviction policy architect](/agents/undominated-kv-eviction-policy-architect/)

Architects dynamic KV cache pruning and eviction policies under strict hardware VRAM limits.

 serving kv-cache eviction

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs cache eviction heuristics; does not alter hardware memory controllers.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-kv-eviction-policy-architect/) Attributed definition available MIT
 Compare Undominated · KV eviction policy architect Add

Evidence review · Undominated.ai

### [Undominated · Library intake editor](/agents/undominated-library-intake-editor/)

Decide whether a skill, agent profile, or MCP server belongs in the public install set, using pinned identity, a licence, and a real checker or an explicit reason it has none.

 resources licence install

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**A portable role profile. It does not register a native subagent or certify third-party runtime behaviour.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-library-intake-editor/) Attributed definition available MIT
 Compare Undominated · Library intake editor Add

Evidence review · Undominated.ai

### [Undominated · Licence derivation auditor](/agents/undominated-licence-derivation-auditor/)

Open-source legal and IP compliance specialist auditing fine-tuning data lineage, synthetic data derivation rights, model weight inheritance, and commercial redistribution boundaries.

 licensing lineage derivation

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Provides technical IP audit guidance.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-licence-derivation-auditor/) Attributed definition available MIT
 Compare Undominated · Licence derivation auditor Add

Evidence review · Undominated.ai

### [Undominated · LLM security red teamer](/agents/undominated-llm-security-red-teamer/)

Designs adversarial jailbreak probes and evaluates model alignment under automated attacks.

 evaluation security jailbreak

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Develops adversarial evaluation benchmarks; does not perform illegal cyber operations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-llm-security-red-teamer/) Attributed definition available MIT
 Compare Undominated · LLM security red teamer Add

Evidence review · Undominated.ai

### [Undominated · Long context bandwidth auditor](/agents/undominated-long-context-bandwidth-auditor/)

Audits inter-node network requirements to guarantee communication is fully masked by attention compute.

 serving bandwidth interconnect

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Verifies network saturation limits against compute execution times; does not capture live packets.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-long-context-bandwidth-auditor/) Attributed definition available MIT
 Compare Undominated · Long context bandwidth auditor Add

Evidence review · Undominated.ai

### [Undominated · Low-bit fidelity auditor](/agents/undominated-low-bit-fidelity-auditor/)

Audits mathematical reasoning and coding benchmarks under aggressive sub-4-bit quantization.

 evaluation quantization fidelity

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates benchmark regression matrices; does not perform weight quantization.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-low-bit-fidelity-auditor/) Attributed definition available MIT
 Compare Undominated · Low-bit fidelity auditor Add

Evidence review · Undominated.ai

### [Undominated · Merged capability auditor](/agents/undominated-merged-capability-auditor/)

Audits merged model checkpoints for catastrophic forgetting and multi-task capability collisions.

 evaluation model-merging benchmarks

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates benchmark score matrices; does not perform model inference directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-merged-capability-auditor/) Attributed definition available MIT
 Compare Undominated · Merged capability auditor Add

Evidence review · Undominated.ai

### [Undominated · Mixed Precision Architect](/agents/undominated-mixed-precision-architect/)

Designs layer-wise quantization profiles balancing perplexity retention against memory savings across FP4, FP8, and INT4.

 mixed-precision quantization layer-allocation

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs layer quantization strategies. Does not train quantization scales.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-mixed-precision-architect/) Attributed definition available MIT
 Compare Undominated · Mixed Precision Architect Add

Evidence review · Undominated.ai

### [Undominated · Model Cascade Architect](/agents/undominated-model-cascade-architect/)

Architects multi-tier model cascading pipelines with confidence-gated fallback routing to optimize cost-per-task.

 cascade architecture routing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Requires access to historical query distributions and labeled validation datasets.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-model-cascade-architect/) Attributed definition available MIT
 Compare Undominated · Model Cascade Architect Add

Evidence review · Undominated.ai

### [Undominated · Model merging architect](/agents/undominated-model-merging-architect/)

Architects zero-training model merges using TIES, DARE, and SLERP to combine specialized domain models.

 evaluation model-merging ties

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Formulates weight blending equations and pruning parameters; does not modify PyTorch tensors directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-model-merging-architect/) Attributed definition available MIT
 Compare Undominated · Model merging architect Add

Evidence review · Undominated.ai

### [Undominated · Model Merging Evaluator](/agents/undominated-model-merging-evaluator/)

Evaluates merged model weights across benchmark suites to prevent catastrophic interference and capability loss.

 model-merging slerp interference-testing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits weight cosine similarity and downstream benchmark evaluations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-model-merging-evaluator/) Attributed definition available MIT
 Compare Undominated · Model Merging Evaluator Add

Evidence review · Undominated.ai

### [Undominated · Model migration planner](/agents/undominated-migration-planner/)

Plan workload-specific model migrations while preserving required capabilities and defining observable rollback criteria.

 migration evaluation models

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-migration-planner/) Install command in review MIT
 Compare Undominated · Model migration planner Add

Evidence review · Undominated.ai

### [Undominated · Model Provenance Investigator](/agents/undominated-model-provenance-investigator/)

Investigates training data lineage, open-weights licensing boundaries, and attribution requirements across model releases.

 provenance license-boundary attribution

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Investigates public training disclosures and license documentation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-model-provenance-investigator/) Attributed definition available MIT
 Compare Undominated · Model Provenance Investigator Add

Evidence review · Undominated.ai

### [Undominated · MoE Serving Architect](/agents/undominated-moe-serving-architect/)

Specializes in Expert Parallelism (EP), Tensor Parallelism (TP), and expert capacity factor calibration for large MoE clusters.

 moe expert-parallelism cluster-sizing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs distributed topology and capacity factors. Does not write CUDA kernels.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-moe-serving-architect/) Attributed definition available MIT
 Compare Undominated · MoE Serving Architect Add

Evidence review · Undominated.ai

### [Undominated · Multi-agent systems economist](/agents/undominated-multi-agent-systems-economist/)

Designs multi-agent workflows to minimize redundant inter-agent chatter and prevent runaway token loops.

 pricing multi-agent economics

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs governance policies and token budgets; does not execute multi-agent swarms.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-multi-agent-systems-economist/) Attributed definition available MIT
 Compare Undominated · Multi-agent systems economist Add

Evidence review · Undominated.ai

### [Undominated · Multi-LoRA Serving Specialist](/agents/undominated-multi-lora-serving-specialist/)

Configures multi-adapter serving clusters serving hundreds of fine-tuned LoRA adapters concurrently on a single base model.

 s-lora multi-tenant adapters

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Configures S-LoRA/Punica serving frameworks. Does not train LoRA weights.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-multi-lora-serving-specialist/) Attributed definition available MIT
 Compare Undominated · Multi-LoRA Serving Specialist Add

Evidence review · Undominated.ai

### [Undominated · Multi-Needle Retrieval Validator](/agents/undominated-retrieval-needle-validator/)

Generates and evaluates multi-needle retrieval benchmarks to expose lost-in-the-middle context blindness in long-context models.

 needle-in-a-haystack long-context eval

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluations use synthetic text corpora and require substantial inference tokens to complete comprehensive sweeps.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-retrieval-needle-validator/) Attributed definition available MIT
 Compare Undominated · Multi-Needle Retrieval Validator Add

Evidence review · Undominated.ai

### [Undominated · Multimodal streaming architect](/agents/undominated-multimodal-streaming-architect/)

Architects real-time streaming audio and video inference pipelines with bounded lookahead latency.

 serving multimodal streaming

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs chunking topologies and latency budgets; does not stream live media.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-multimodal-streaming-architect/) Attributed definition available MIT
 Compare Undominated · Multimodal streaming architect Add

Evidence review · Undominated.ai

### [Undominated · NCCL topology auditor](/agents/undominated-nccl-topology-auditor/)

Audits NVLink, NVSwitch, and InfiniBand rail-optimized communication topologies for distributed serving.

 serving nccl nvswitch

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Analyzes NCCL topology graph dumps and bus profiles; does not reconfigure hardware switches.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-nccl-topology-auditor/) Attributed definition available MIT
 Compare Undominated · NCCL topology auditor Add

Evidence review · Undominated.ai

### [Undominated · On-device performance auditor](/agents/undominated-on-device-performance-auditor/)

Audits thermal throttling, unified memory pressure, and battery consumption on consumer edge devices.

 serving edge thermal-throttling

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates recorded thermal and memory telemetry; does not read hardware sensors in real time.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-on-device-performance-auditor/) Attributed definition available MIT
 Compare Undominated · On-device performance auditor Add

Evidence review · Undominated.ai

### [Undominated · Population reviewer](/agents/undominated-population-reviewer/)

Review a count, rank or correlation before publication, so the computed rows are the population the sentence names.

 population denominators ranking

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-population-reviewer/) Attributed definition available MIT
 Compare Undominated · Population reviewer Add

Evidence review · Undominated.ai

### [Undominated · Preference alignment auditor](/agents/undominated-preference-alignment-auditor/)

Audits reward models and preference datasets for length bias, sycophancy, and mode collapse.

 evaluation alignment dpo

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Analyzes preference dataset distributions and response characteristics; does not execute training loops.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-preference-alignment-auditor/) Attributed definition available MIT
 Compare Undominated · Preference alignment auditor Add

Evidence review · Undominated.ai

### [Undominated · Pricing source reviewer](/agents/undominated-pricing-source-reviewer/)

Review a provider price feed before any rate is admitted, including units, currency, tiers and prose quotes that are not USD.

 pricing providers provenance

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/undominated-pricing-source-reviewer/) Install command in review MIT
 Compare Undominated · Pricing source reviewer Add

Evidence review · Undominated.ai

### [Undominated · Prompt Compression Economist](/agents/undominated-prompt-compression-economist/)

Audits client-side prompt compression pipelines to minimize billed input token volume without losing semantic fidelity.

 prompt-compression token-economics cost-slashing

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs compression and pruning policies. Does not modify upstream model weights.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-prompt-compression-economist/) Attributed definition available MIT
 Compare Undominated · Prompt Compression Economist Add

Evidence review · Undominated.ai

### [Undominated · Prompt firewall architect](/agents/undominated-prompt-firewall-architect/)

Constructs low-latency pre-inference guard firewalls to intercept injection and extraction attacks.

 serving security prompt-firewall

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs firewall filter rules and routing architecture; does not run network proxies.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-prompt-firewall-architect/) Attributed definition available MIT
 Compare Undominated · Prompt firewall architect Add

Evidence review · Undominated.ai

### [Undominated · Provider Resilience Architect](/agents/undominated-provider-resilience-architect/)

Designs automatic failover, circuit breaking, and idempotency guarantees across redundant inference providers.

 resilience failover circuit-breaker

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs gateway resilience architectures.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-provider-resilience-architect/) Attributed definition available MIT
 Compare Undominated · Provider Resilience Architect Add

Evidence review · Undominated.ai

### [Undominated · Quantization Evaluation Reviewer](/agents/undominated-quantization-eval-reviewer/)

Audits LLM evaluation protocols to verify whether published benchmark scores match the model's serving quantization or upstream unquantized weights.

 quantization eval benchmarks

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Review is strictly factual and evidence-bound. Missing quantization disclosures are flagged as unverified.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-quantization-eval-reviewer/) Attributed definition available MIT
 Compare Undominated · Quantization Evaluation Reviewer Add

Evidence review · Undominated.ai

### [Undominated · Quantized KV Cache Calibrator](/agents/undominated-quantized-kv-cache-calibrator/)

Calibrates per-channel and per-group scale factors for sub-8-bit KV caches to prevent long-context reasoning drift.

 kv-cache int4 fp8

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Calibrates scaling parameters and clipping thresholds.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-quantized-kv-cache-calibrator/) Attributed definition available MIT
 Compare Undominated · Quantized KV Cache Calibrator Add

Evidence review · Undominated.ai

### [Undominated · Quote identity reviewer](/agents/undominated-quote-identity-reviewer/)

Review a proposed join between a vendor quote and a catalogue model, and refuse any match that is not exact.

 identity pricing join

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-quote-identity-reviewer/) Attributed definition available MIT
 Compare Undominated · Quote identity reviewer Add

Evidence review · Undominated.ai

### [Undominated · RAG Context Economist](/agents/undominated-rag-context-economist/)

Optimizes context window packing, chunk overlap boundaries, and token budgets for enterprise RAG systems.

 rag context-budget embeddings

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Relies on documented retrieval metrics and rate cards. Does not alter upstream vector database schemas.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-rag-context-economist/) Attributed definition available MIT
 Compare Undominated · RAG Context Economist Add

Evidence review · Undominated.ai

### [Undominated · Reasoning budget planner](/agents/undominated-reasoning-budget-planner/)

Architect agent that models reasoning token expenditure, dynamically calibrates thinking budgets across prompt difficulty classes, and prevents runaway cost expansion.

 reasoning budget tokens

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-reasoning-budget-planner/) Attributed definition available MIT
 Compare Undominated · Reasoning budget planner Add

Evidence review · Undominated.ai

### [Undominated · Reasoning Trace Compressor](/agents/undominated-reasoning-trace-compressor/)

Audits chain-of-thought reasoning traces to detect circular deliberation loops, repetitive tokens, and distillation opportunities.

 cot reasoning compression

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits reasoning trace structure and redundancy. Does not rewrite private model weight internal activations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-reasoning-trace-compressor/) Attributed definition available MIT
 Compare Undominated · Reasoning Trace Compressor Add

Evidence review · Undominated.ai

### [Undominated · Reasoning verifier auditor](/agents/undominated-reasoning-verifier-auditor/)

Audits process reward model verifiers for false-positive validation passes and search path collapse.

 evaluation prm reasoning

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates verification agreement and error distributions; does not execute reward models.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-reasoning-verifier-auditor/) Attributed definition available MIT
 Compare Undominated · Reasoning verifier auditor Add

Evidence review · Undominated.ai

### [Undominated · Recurrent state auditor](/agents/undominated-recurrent-state-auditor/)

Audits recurrent hidden state numerical drift and precision degradation during continuous streaming.

 serving recurrent drift

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Monitors state norm stability and accumulation variance; does not generate token predictions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-recurrent-state-auditor/) Attributed definition available MIT
 Compare Undominated · Recurrent state auditor Add

Evidence review · Undominated.ai

### [Undominated · Regulatory Compliance Officer](/agents/undominated-regulatory-compliance-officer/)

Audits AI deployments for EU AI Act, US Executive Order, and ISO 42001 governance and transparency frameworks.

 compliance eu-ai-act governance

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits technical compliance requirements. Does not provide formal legal counsel.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-regulatory-compliance-officer/) Attributed definition available MIT
 Compare Undominated · Regulatory Compliance Officer Add

Evidence review · Undominated.ai

### [Undominated · Resource release verifier](/agents/undominated-release-verifier/)

Independently verify packaged resources, clean installation and meaningful public availability after a release.

 releases verification packages

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-release-verifier/) Install command in review MIT
 Compare Undominated · Resource release verifier Add

Evidence review · Undominated.ai

### [Undominated · Router Threshold Calibrator](/agents/undominated-router-threshold-calibrator/)

Calibrates draft model confidence thresholds to balance API cost savings against quality degradation.

 thresholds calibration quality-gate

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Calibration relies on empirical validation curves. Thresholds must be re-calibrated upon model updates.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-router-threshold-calibrator/) Attributed definition available MIT
 Compare Undominated · Router Threshold Calibrator Add

Evidence review · Undominated.ai

### [Undominated · Safety Refusal Calibrator](/agents/undominated-safety-refusal-calibrator/)

Calibrates safety classifier thresholds to minimize benign query refusals while maintaining strict compliance boundaries.

 safety refusal calibration

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Does not loosen boundaries on core safety violations (CSAM, CBRN, self-harm). Calibrates benign edge cases.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-safety-refusal-calibrator/) Attributed definition available MIT
 Compare Undominated · Safety Refusal Calibrator Add

Evidence review · Undominated.ai

### [Undominated · Schema Contract Verifier](/agents/undominated-schema-contract-verifier/)

Verifies tool schemas, argument enums, and parameter constraints to prevent runtime validation failures.

 schema-verification contract-testing tools

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits JSON schema specifications and validation logic.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-schema-contract-verifier/) Attributed definition available MIT
 Compare Undominated · Schema Contract Verifier Add

Evidence review · Undominated.ai

### [Undominated · Serving Engine Tuner](/agents/undominated-serving-engine-tuner/)

Specializes in tuning vLLM, SGLang, and TensorRT-LLM parameters including chunked prefill, radix trees, and batching scheduling.

 serving vllm sglang

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Focuses on runtime parameters and flags. Does not rewrite model CUDA kernels.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-serving-engine-tuner/) Attributed definition available MIT
 Compare Undominated · Serving Engine Tuner Add

Evidence review · Undominated.ai

### [Undominated · Sovereign AI TCO auditor](/agents/undominated-sovereign-ai-tco-auditor/)

Models national sovereign AI cluster CapEx/OpEx, power grid contracts, and 5-year hardware lifecycle TCO.

 pricing sovereign-ai tco

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Models multi-year financial statements and depreciation schedules; does not issue procurement tenders.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-sovereign-ai-tco-auditor/) Attributed definition available MIT
 Compare Undominated · Sovereign AI TCO auditor Add

Evidence review · Undominated.ai

### [Undominated · Sparse Attention Evaluator](/agents/undominated-sparse-attention-evaluator/)

Audits accuracy retention and memory bandwidth reduction across Native Sparse Attention (NSA) and block-sparse mechanisms.

 sparse-attention nsa accuracy-retention

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Evaluates benchmark accuracy retention and hardware bandwidth savings.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-sparse-attention-evaluator/) Attributed definition available MIT
 Compare Undominated · Sparse Attention Evaluator Add

Evidence review · Undominated.ai

### [Undominated · Speculative Architecture Engineer](/agents/undominated-speculative-architecture-engineer/)

Architects speculative decoding topologies including Multi-Token Prediction (MTP), Medusa heads, and Eagle tree verifiers.

 speculative-decoding mtp medusa

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs draft-verifier architectures and tuning parameters.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-speculative-architecture-engineer/) Attributed definition available MIT
 Compare Undominated · Speculative Architecture Engineer Add

Evidence review · Undominated.ai

### [Undominated · Speculative tree architect](/agents/undominated-speculative-tree-architect/)

Designs multi-candidate speculative draft trees to maximize generation speed on constrained GPUs.

 serving speculative-decoding tree-search

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs tree topologies and candidate selection masks; does not compute forward passes.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-speculative-tree-architect/) Attributed definition available MIT
 Compare Undominated · Speculative tree architect Add

Evidence review · Undominated.ai

### [Undominated · Stack cost optimizer](/agents/undominated-stack-cost-optimizer/)

Full-stack AI system cost optimization specializing in multi-tier cascading, retrieval pruning, speculative drafting, and prompt caching to slash API spend while preserving benchmark quality.

 optimization cascading cost

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-stack-cost-optimizer/) Attributed definition available MIT
 Compare Undominated · Stack cost optimizer Add

Evidence review · Undominated.ai

### [Undominated · Streaming Reliability Engineer](/agents/undominated-streaming-reliability-engineer/)

Specializes in Server-Sent Events (SSE) connection health, keep-alive heartbeat spacing, and client reconnection handling.

 streaming sse heartbeat

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Operates over observed network traces and server configuration. Does not execute intrusive network attacks.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-streaming-reliability-engineer/) Attributed definition available MIT
 Compare Undominated · Streaming Reliability Engineer Add

Evidence review · Undominated.ai

### [Undominated · Sustainable inference architect](/agents/undominated-sustainable-inference-architect/)

Optimizes AI workload scheduling for renewable power availability and lowest carbon footprint.

 pricing datacenter sustainability

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs carbon-aware scheduling models; does not interact with electrical power grids directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-sustainable-inference-architect/) Attributed definition available MIT
 Compare Undominated · Sustainable inference architect Add

Evidence review · Undominated.ai

### [Undominated · Synthetic curation architect](/agents/undominated-synthetic-curation-architect/)

Architects synthetic training dataset filtering pipelines to eliminate contamination and redundancy.

 evaluation synthetic-data filtering

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs filtering criteria and similarity thresholds; does not store external training corpora.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-synthetic-curation-architect/) Attributed definition available MIT
 Compare Undominated · Synthetic curation architect Add

Evidence review · Undominated.ai

### [Undominated · Synthetic judge calibrator](/agents/undominated-synthetic-judge-calibrator/)

Evaluation scientist specializing in LLM-as-a-judge alignment, position bias mitigation, length normalization, and inter-rater agreement calibration against human experts.

 llm-judge calibration agreement

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Executes no judge calls directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-synthetic-judge-calibrator/) Attributed definition available MIT
 Compare Undominated · Synthetic judge calibrator Add

Evidence review · Undominated.ai

### [Undominated · Tail latency auditor](/agents/undominated-tail-latency-auditor/)

Profiles p99.9 tail latencies to eliminate micro-stalls caused by garbage collection and multi-tenant contention.

 serving tail-latency p99

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Analyzes latency distribution traces; does not modify kernel scheduling priorities.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-tail-latency-auditor/) Attributed definition available MIT
 Compare Undominated · Tail latency auditor Add

Evidence review · Undominated.ai

### [Undominated · Tail latency SLA auditor](/agents/undominated-tail-latency-sla-auditor/)

Production observability auditor comparing provider Service Level Agreements against measured p95/p99 tail latency, serverless cold starts, and outage windows.

 latency sla observability

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Portable profile; manually load or adapt to a native agent format. Executes no billing disputes directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-tail-latency-sla-auditor/) Attributed definition available MIT
 Compare Undominated · Tail latency SLA auditor Add

Evidence review · Undominated.ai

### [Undominated · Ternary inference architect](/agents/undominated-ternary-inference-architect/)

Architects native ternary and low-bit compute pipelines for low-energy edge and cloud inference.

 serving bitnet ternary

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs compute pipelines and memory layouts; does not fabricate custom silicon.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-ternary-inference-architect/) Attributed definition available MIT
 Compare Undominated · Ternary inference architect Add

Evidence review · Undominated.ai

### [Undominated · Test-time compute economist](/agents/undominated-test-time-compute-economist/)

Optimizes test-time compute allocation across search width and reasoning depth to balance accuracy and cost.

 pricing reasoning test-time-compute

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Models cost-accuracy curves and search allocation policies; does not generate reasoning traces.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-test-time-compute-economist/) Attributed definition available MIT
 Compare Undominated · Test-time compute economist Add

Evidence review · Undominated.ai

### [Undominated · Tool Registry Architect](/agents/undominated-tool-registry-architect/)

Designs dynamic tool indexing and semantic retrieval to keep system prompt tokens minimal across large API catalogs.

 tool-registry dynamic-tools function-calling

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Designs tool registry indexing and selection mechanisms.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-tool-registry-architect/) Attributed definition available MIT
 Compare Undominated · Tool Registry Architect Add

Evidence review · Undominated.ai

### [Undominated · Vision token economist](/agents/undominated-vision-token-economist/)

Optimizes vision patch resolution and temporal subsampling to minimize multi-modal token billing.

 pricing vision multimodal

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Calculates patch token billing models; does not run image computer vision models.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-vision-token-economist/) Attributed definition available MIT
 Compare Undominated · Vision token economist Add

Evidence review · Undominated.ai

### [Undominated · VRAM Fragmentation Analyst](/agents/undominated-vram-fragmentation-analyst/)

Analyzes PagedAttention block size allocation, CUDA graph memory pools, and virtual memory fragmentation to prevent GPU OOMs.

 vram fragmentation paged-attention

**Why we selected it**Defines a specialist role, required evidence, handoff contract and explicit limits on external actions.

**Weigh up**Audits memory allocation patterns. Does not debug hardware PCIe bus faults.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/undominated-vram-fragmentation-analyst/) Attributed definition available MIT
 Compare Undominated · VRAM Fragmentation Analyst Add

Creative tooling · Agency Agents community

### [Unity editor tooling developer](/agents/agency-unity-editor-tool-developer/)

A Unity profile for editor extensions, asset-import checks and build-blocking validation.

 unity editor-tools asset-pipeline

**Why we selected it**Editor code is isolated through Editor folders, conditional guards and assembly definitions instead of leaking UnityEditor into player builds.

**Weigh up**Example code and adoption/time-saved claims were not executed or measured; the profile does not provide a Unity licence or CI runner.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-unity-editor-tool-developer/) Attributed definition available MIT
 Compare Unity editor tooling developer Add

Game development · Seth Hobson

### [Unity gameplay and performance engineer](/agents/wshobson-unity-developer/)

Plans Unity gameplay and asset/rendering work using project-specific pipelines and target-hardware profiling.

 Unity profiling assets

**Why we selected it**The profile connects Profiler/Frame Debugger evidence to CPU/GPU/memory work and includes Addressables asset-lifecycle concerns.

**Weigh up**The broad capability inventory is not proof of version compatibility; some service names are legacy and require current official documentation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/wshobson-unity-developer/) Attributed definition available MIT
 Compare Unity gameplay and performance engineer Add

Game development · Agency Agents community

### [Unreal world-streaming planner](/agents/agency-unreal-world-builder/)

An Unreal environment profile for world partition, HLOD and procedural population planning.

 unreal world-partition hlod

**Why we selected it**It calls for configuring streaming structure before population and reviewing distant HLOD visually.

**Weigh up**Fixed cell sizes, distances, layer limits and numeric performance targets are author heuristics, not measured limits for your project; examples need engine-version validation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-unreal-world-builder/) Upstream setup linked MIT
 Compare Unreal world-streaming planner Add

Changelog editing · Astral Software Inc.

### [uv changelog editorial](/agents/astral-uv-changelog-editorial/)

Rewrites only the newest uv changelog section, and keeps the version, date, pull-request numbers, and URLs as they are.

 uv changelog release

**Why we selected it**The prompt edits nothing and uses no network; it returns only the newest release section.

**Weigh up**This Markdown file has no frontmatter and is not a native subagent registration.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/astral-uv-changelog-editorial/) Upstream setup linked MIT
 Compare uv changelog editorial Add

Pull-request labels · Astral Software Inc.

### [uv pull-request labels](/agents/astral-uv-pull-request-labels/)

Chooses at most the semantic labels for one uv pull request, and leaves the list empty when the diff does not support one.

 uv labels pull-request

**Why we selected it**Labels have to come from .pull-request-labels.json. An unclear case is an empty array. The prompt says not to recommend labels already on the pull request and not to suggest removals.

**Weigh up**The prompt forbids file/GitHub changes and PR-code execution; the reviewed read-only profile permits only api.github.com and github.com.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/astral-uv-pull-request-labels/) Upstream setup linked MIT
 Compare uv pull-request labels Add

Bug reproduction · Astral Software Inc.

### [uv reproduce-bug](/agents/astral-uv-reproduce-bug/)

Decides whether a reported uv behavior can be reproduced, and refuses to treat source inspection as a reproduction.

 uv reproduction triage

**Why we selected it**The outcome is one of reproducible, not_reproducible, or needs_more_information. A reproduced behavior is not treated as proof the behavior is wrong.

**Weigh up**The prompt is tied to astral-sh/uv issue context and test paths. Its workflow prepares temporary state from uv-dev; copying the prompt does not create that state.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/astral-uv-reproduce-bug/) Upstream setup linked MIT
 Compare uv reproduce-bug Add

CI diagnosis · Astral Software Inc.

### [uv workflow-failure](/agents/astral-uv-workflow-failure/)

Classifies one failed uv workflow as flaky or deterministic, and as create, duplicate, or ignore.

 uv ci triage

**Why we selected it**flaky is allowed only when every independent root cause is transient. One deterministic failure makes the run deterministic. Dependent cancellations are not independent root causes.

**Weigh up**The prompt assumes astral-sh/uv and uv-dev issue searches and repository labels. Another project must adapt those names, the input collector and reporting destinations.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/agents/astral-uv-workflow-failure/) Upstream setup linked MIT
 Compare uv workflow-failure Add

Data and retrieval · wshobson

### [Vector Database Engineer](/agents/wshobson-vector-database-engineer/)

Plans and implements semantic retrieval systems through corpus analysis, embeddings, chunking, index selection, hybrid search, reranking and monitoring.

 vector-db embeddings hybrid-search

**Why we selected it**Workflow is requirement→embedding→chunk→store→index→hybrid→rerank→monitor, which is a real RAG build path.

**Weigh up**The broad implementation role declares no tool allowlist; access to databases, credentials and file changes comes from the host.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/wshobson-vector-database-engineer/) Attributed definition available MIT
 Compare Vector Database Engineer Add

Infrastructure and delivery · Vercel

### [Vercel deployment expert](/agents/vercel-deployment-expert/)

Diagnoses failed Vercel builds, function timeouts, environment variables and domains, and stages production builds before promoting them.

 deployments rollback ci/cd

**Why we selected it**It says to promote a staged production deployment, not a preview, because promoting a preview rebuilds it with production variables and the tested build is not the one released.

**Weigh up**One build branch says to delete the lockfile, reinstall and commit a fresh one on a lockfile mismatch. That re-resolves every dependency; prefer fixing the mismatch.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/vercel-deployment-expert/) Install command in review Apache-2.0
 Compare Vercel deployment expert Add

Browser and performance · Vercel

### [Vercel performance optimizer](/agents/vercel-performance-optimizer/)

Walks LCP, INP and CLS decision trees for a Vercel or Next.js app, measuring first and reading the installed Next.js docs before recommending a change.

 core web vitals next.js performance

**Why we selected it**The audit checklist starts by measuring real-user Core Web Vitals in Speed Insights and identifying the LCP element before any change.

**Weigh up**Each finding includes an Expected Improvement target metric. The file gives no method for that estimate; treat it as a hypothesis to re-measure.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/agents/vercel-performance-optimizer/) Install command in review Apache-2.0
 Compare Vercel performance optimizer Add

Modernization and specifications · anthropics

### [Version Delta Analyst](/agents/anthropic-version-delta-analyst/)

Maps an exact same-stack version pair to the APIs and behaviors a particular tree uses, returning delta cards and explicitly lost tool coverage to the migration owner.

 version-uplift breaking-changes delta-catalog

**Why we selected it**Requires file:line evidence for the intersection of version changes and actual code usage, excluding removed APIs the code never calls.

**Weigh up**Read-only wording conflicts with the instruction to create an rsync scratch copy and run tools that write build output/download plugins. Bash is declared; the profile does not enforce a filesystem or network sandbox.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/agents/anthropic-version-delta-analyst/) Attributed definition available Apache-2.0
 Compare Version Delta Analyst Add

Testing and review · affaan-m

### [Vue Reviewer](/agents/ecc-vue-reviewer/)

Reviews Vue single-file components for reactivity correctness, v-html and URL-binding security, composable cleanup, Router and Pinia patterns, and SSR safety — reporting findings without rewriting code.

 vue code review composition api

**Why we selected it**Owns an explicit scope table that splits Vue-specific lanes (reactivity, v-html, composables, props/emits, Router, Pinia, SSR) from the generic TypeScript reviewer, so the two roles compose instead of duplicating.

**Weigh up**Full .vue coverage needs the sibling typescript-reviewer for generic type-safety lanes; this file reviews Vue-specific concerns only.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/ecc-vue-reviewer/) Attributed definition available MIT
 Compare Vue Reviewer Add

Systems performance · Agency Agents community

### [WebAssembly boundary and runtime planner](/agents/agency-engineering-webassembly-engineer/)

Evaluates Wasm adoption through measured workloads, explicit memory ownership and capability-scoped runtime design.

 WebAssembly WASI interop

**Why we selected it**The wasm-bindgen example explicitly performs bulk copies and disclaims a zero-copy ABI; ownership is part of the boundary design.

**Weigh up**The Wasmtime fragment only builds configuration/context and does not supply complete linking, store, limits or module execution code.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/agency-engineering-webassembly-engineer/) Upstream setup linked MIT
 Compare WebAssembly boundary and runtime planner Add

Infrastructure and delivery · VoltAgent

### [Webhook Engineer](/agents/voltagent-webhook-engineer/)

Builds webhook handlers and delivery paths that survive the real world: raw-body signature verification before parsing, durable enqueue before the 2xx, deduplication matched to the provider retry window, and dead-letter replay as a first-class operation.

 webhooks idempotency retries

**Why we selected it**Treats at-least-once delivery, duplicates and reordering as the default world and builds the checklist around them: constant-time signature checks with replay windows, event identifiers persisted before processing, a dedup store whose TTL matches the provider retry window, and database constraints as the final dedupe guarantee.

**Weigh up**The integration section names sibling agents (backend-developer, api-designer and others) for coordination; those are separate files and not needed for the core method.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/agents/voltagent-webhook-engineer/) Attributed definition available MIT
 Compare Webhook Engineer Add

Documentation · Microsoft Corporation

### [Wiki writer](/agents/microsoft-wiki-writer/)

Microsoft deep-wiki agent that writes VitePress markdown with dark-mode Mermaid diagrams and a citation for each claim, and that refuses to write before the git remote is resolved.

 wiki citations mermaid

**Why we selected it**The catalogue has the deep-wiki researcher skill and not this writer agent.

**Weigh up**This review did not execute the agent.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/microsoft-wiki-writer/) Install command in review MIT
 Compare Wiki writer Add

Build and packaging · GitHub community

### [Windows ARM64 wheel builder](/agents/github-windows-arm64-wheel-builder/)

Extends an existing Python wheel workflow with a native Windows ARM64 path, checking matrix filters, native dependencies and artifact names.

 Python Windows ARM64 GitHub Actions

**Why we selected it**It traces reusable workflows and composite actions before editing, and checks whether an ARM64 entry already exists to avoid duplicates.

**Weigh up**No tools list is declared, so host defaults can include editing and execution. Scope workflow edits and CI triggering explicitly.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/github-windows-arm64-wheel-builder/) Attributed definition available MIT
 Compare Windows ARM64 wheel builder Add

Infrastructure · VoltAgent

### [Windows infrastructure change planner](/agents/voltagent-windows-infra-admin/)

A Windows infrastructure profile organizing directory, DNS, DHCP and policy changes around inventories and rollback.

 windows-server dns dhcp

**Why we selected it**The checklist requires enumerating affected objects before modification and reviewing a WhatIf preview.

**Weigh up**WhatIf support depends on the actual command and does not guarantee rollback; Bash/Edit/Write can alter infrastructure through available credentials.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-windows-infra-admin/) Attributed definition available MIT
 Compare Windows infrastructure change planner Add

Persistent work coordination · GitHub community

### [Workshop coordinator](/agents/github-workshop-ta/)

Coordinates workstreams using shared artifacts, desk journals and structured escalation signals across independent sessions.

 journals handoffs coordination

**Why we selected it**It uses files and journals to carry state across sessions and treats peer findings as evidence to review.

**Weigh up**Requires workshop-create, desk-open, bench-read, desk-journal and signal-write; the optional signals dashboard is separately installed.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/agents/github-workshop-ta/) Upstream setup linked MIT
 Compare Workshop coordinator Add

API engineering · VoltAgent

### [X data integration contract engineer](/agents/voltagent-x-api-integration/)

An integration profile organizing X-data reads and writes around explicit provider contracts and reproducible fixtures.

 api-contracts pagination webhooks

**Why we selected it**It preserves partial results after late pagination failures and snapshots source version and request parameters for auditability.

**Weigh up**No API access or quota is included; the alternative provider mention is not independent validation of its provenance or terms. The example completed-tests sentence is a template, not evidence.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/agents/voltagent-x-api-integration/) Attributed definition available MIT
 Compare X data integration contract engineer Add

Security review · Trail of Bits

### [Zeroize MCP resolver](/agents/trailofbits-1-mcp-resolver/)

Pins the zeroize-audit agent that resolves symbols through Serena and stops the pass when activation fails or the query budget is spent.

 zeroize security symbols

**Why we selected it**The agents catalogue has no sourcePath for plugins/zeroize-audit/agents/1-mcp-resolver.md.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/agents/trailofbits-1-mcp-resolver/) Install command in review CC-BY-SA-4.0
 Compare Zeroize MCP resolver Add

Code review · Zoom

### [Zoom integration reviewer](/agents/zoom-integration-reviewer/)

Reviews a Zoom integration for architectural fit, token lifecycle, webhook verification and SDK or API misuse, findings first.

 zoom webhooks oauth

**Why we selected it**It names what to flag first: wrong product-surface choices, broken token lifecycle assumptions, webhook verification bugs and unsupported SDK or API assumptions.

**Weigh up**The file is a short prompt. It does not list Zoom API behaviour itself; correctness depends on the documentation and skills in the session.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/agents/zoom-integration-reviewer/) Attributed definition available MIT
 Compare Zoom integration reviewer Add

Security review · Zoom

### [Zoom OAuth scope auditor](/agents/zoom-oauth-scope-auditor/)

Reviews the Zoom scopes an app requests, configures and documents for least privilege, missing scopes and mixed product surfaces.

 oauth scopes least privilege

**Why we selected it**It is told not to invent scopes, to say what evidence is missing, and to prefer the narrowest documented scope set that supports the workflow.

**Weigh up**The file is a short prompt with no scope list of its own. Correctness depends on the Zoom documentation and skills available in the session.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/agents/zoom-oauth-scope-auditor/) Attributed definition available MIT
 Compare Zoom OAuth scope auditor Add

03 / BEHIND THE SELECTION

## The review is part of the product.

A useful recommendation tells you why it fits—and what still needs checking.

### What we inspect

We read the complete selected definition, identify its role, workflow, output expectations and verification instructions, and check the applicable licence. Review notes distinguish instructions from enforcement: a prompt saying “read only” does not itself restrict the host’s tools.

### What a selection means

Each resource has a concrete use case, original selection reasons, named limitations and a dated review record. We favour specific instructions, useful scope and inspectable setup. The list is curated; it is not a census of everything available or an independently benchmarked league table.

### Before using it

Read the complete review, check the upstream revision and match the resource to your own host and permissions. Review notes apply to the material named at the recorded date. Installation commands may retrieve a newer upstream version.

### Where we looked

 - [anthropics/claude-plugins-official ↗](https://github.com/anthropics/claude-plugins-official)
- [github/awesome-copilot ↗](https://github.com/github/awesome-copilot)
- [VoltAgent/awesome-claude-code-subagents ↗](https://github.com/VoltAgent/awesome-claude-code-subagents)
- [wshobson/agents ↗](https://github.com/wshobson/agents)
- [msitarzewski/agency-agents ↗](https://github.com/msitarzewski/agency-agents)
- [affaan-m/everything-claude-code ↗](https://github.com/affaan-m/everything-claude-code)
- [AWS Labs AI-DLC Workflows ↗](https://github.com/awslabs/aidlc-workflows) Reviewed authored personas and the documented framework projection; retained the advisory compliance role.
- [Trail of Bits Skills ↗](https://github.com/trailofbits/skills) Reviewed full worker definitions, output contracts, plugin dependencies and the CC-BY-SA licence.
- [Sentry Skills ↗](https://github.com/getsentry/skills) Screened agent originals; recorded frontmatter exclusions and selected the original Anthropic simplifier instead of a duplicate vendored copy.
- [Microsoft Skills ↗](https://github.com/microsoft/skills) Reviewed infrastructure and wiki agent definitions; excluded project-specific or overlapping roles.
- [VoltAgent/awesome-claude-code-subagents — expanded definition review ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/tree/82b73821baa7a911d5b14cfb6da238b7f0db6b42) Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.
- [affaan-m/everything-claude-code — expanded definition review ↗](https://github.com/affaan-m/everything-claude-code/tree/bf70150eb2df8070024e5bdf08e4aa08959e2735) Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.
- [anthropics/claude-plugins-official — expanded definition review ↗](https://github.com/anthropics/claude-plugins-official/tree/c447c3207a425bc4e2a0d068435f64b0477ae981) Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.
- [github/awesome-copilot — expanded definition review ↗](https://github.com/github/awesome-copilot/tree/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80) Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.
- [msitarzewski/agency-agents — expanded definition review ↗](https://github.com/msitarzewski/agency-agents/tree/87f8301cad3823a9a34d762036ae923a0eff306f) Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.
- [wshobson/agents — expanded definition review ↗](https://github.com/wshobson/agents/tree/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620) Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.
- [Svelte primary source ↗](https://github.com/sveltejs/ai-tools) Direct source screening; popularity was not treated as evidence of quality.
- [Terraform AWS provider ↗](https://github.com/hashicorp/terraform-provider-aws)
- [Anthropic Buffa agent definitions ↗](https://github.com/anthropics/buffa) Reviewed the Rust API ergonomics role and the Apache-2.0 licence. Repository-internal maintainer agents from other publishers were recorded as exclusions.
- [GitHub Agentic Workflows ↗](https://github.com/github/gh-aw)
- [OpenAI Codex rust review label ↗](https://github.com/openai/codex/tree/8f21b7fffbefe77529325fc86c95289371841c6c) Read the rust review label and the Apache-2.0 licence at this commit. The workflow that substitutes the event-path token was not opened.
- [Anthropic math-proof agents ↗](https://github.com/anthropics/claude-plugins-official/tree/b78ac49cdc6b3d7b61c4439470e311f4291265b1) Read the math-proof judge and worker, and the plugin Apache-2.0 licence. The siege skill that launches them was not opened.
- [GitHub AWF diagnosis agent ↗](https://github.com/github/gh-aw-firewall/tree/8c67001a25708115ca1d76faad99a73904a79d3a) Read the diagnosis playbook and the MIT licence. Sibling docs named by the playbook were not opened, and no probe was run.
- [astral-sh/uv ↗](https://github.com/astral-sh/uv) Four Codex prompts, config.toml, triage-issue.md, and LICENSE-MIT at the reviewed commit. Write-capable prompts were not selected.
- [github/docs ↗](https://github.com/github/docs) Read .github/agents/readability-editor.md, LICENSE-CODE, and README at b3ca4b7986534061037979e480c9d363fc95a909. The dependabot ecosystem agent at that commit was not selected.
- [anthropics/claude-plugins-official at f359d43b ↗](https://github.com/anthropics/claude-plugins-official/tree/f359d43b406057f1a8cdbc4ea93b827642c162e6) Listed every plugins/*/agents/*.md. Selected four new agents. plugin-validator still ends with session text and silent-failure-hunter still fails YAML parsing, so their earlier exclusions stand.
- [anthropics/financial-services at 574ed362 ↗](https://github.com/anthropics/financial-services/tree/574ed3624aebd0418c7e96cd101262f30210ab26) Formerly financial-services-plugins. Read five agent-plugin definitions, the README install section, two cookbook workers and the Apache-2.0 licence.
- [zoom/zoom-plugin-codex at 10936829 ↗](https://github.com/zoom/zoom-plugin-codex/tree/10936829584d5b232e8edd9e6a6cab48729d2c52) Read both reviewer agents, agents/openai.yaml, the README, the plugin manifest and the MIT licence.
- [vercel/vercel-plugin at b97d74d0 ↗](https://github.com/vercel/vercel-plugin/tree/b97d74d07702e9fe4bd7ac5ef308bc9f65abc826) Read the three agents, the README (install, agents, telemetry), the plugin manifest and the Apache-2.0 notice. The ai-architect agent was not selected.
- [openai/plugins at 0722921d ↗](https://github.com/openai/plugins/tree/0722921d5542fc593105c27bd52630babd8b8c2a) Listed plugin-level agents/ directories. Vercel and Zoom agents were pinned at their publishers' own repositories. The Figma agents are under the Figma Developer Terms.
- [openai/codex built-in agent roles at 21c16161 ↗](https://github.com/openai/codex/tree/21c16161191ff965031d1ac41fe9046011610743/codex-rs/core/assets/agent/builtins) Read awaiter.toml and explorer.toml. Neither was selected.
- [aws/agent-toolkit-for-aws at c34fbdfd ↗](https://github.com/aws/agent-toolkit-for-aws/tree/c34fbdfde6779593f651f2c85629a85d27231498/plugins/aws-startup-advisor/agents) Read the seven aws-startup-advisor agents and the Apache-2.0 licence. None was selected.
- [stripe/ai at deae744b ↗](https://github.com/stripe/ai/tree/deae744bc0cbf6034b4b6f22f51c690b71a4e779/providers/claude/plugin/agents) Read the company-researcher agent. Not selected.
- [getsentry/sentry-for-ai at c2313d3a ↗](https://github.com/getsentry/sentry-for-ai/tree/c2313d3a826d56249e70623313bdc27ce5fca8b6/.github/agents) Read the descriptions of the skill-creator and skill-updater agents. Not selected.
- [google-gemini/gemini-cli at 29315e53 ↗](https://github.com/google-gemini/gemini-cli/tree/29315e53d0c2e9b78f301f3c24db235b0f3fa597) Listed the tree. The only .gemini/agents file is tools/gemini-cli-bot/.gemini/agents/WORKER.md, inside the repository's own bot tooling. It was not opened, and no other agent definition was found.
- [github/awesome-copilot at 156736fb ↗](https://github.com/github/awesome-copilot/tree/156736fb63e965b2f547a1460f3b5972c46e6b24) Compared agents/*.agent.md with the library and its exclusions, read the partners plugin manifest and README, and read each candidate definition named in a record or an exclusion.
- [GitHub community agent workflow review ↗](https://github.com/github/awesome-copilot/tree/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8) Reviewed complete definitions, MIT notice and current host boundaries. Selected six concrete workflows; four standalone originals include licensed downloads. No task execution or security certification.
 [Download this index as JSON ↗](/data/resources/agents.json)

 Selections we withheld (118)

These are documented decisions from this review, not a blacklist of the wider ecosystem.

 - **anthropic-silent-failure-hunter:** The full upstream file fails YAML parsing: the unquoted description contains embedded example text with colon-space syntax. Excluded from screened native-agent downloads; additional project-specific logging assumptions would also need adaptation. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/silent-failure-hunter.md)
- **anthropic-plugin-validator:** The definition ends with unrelated generation-session chatter, refers to sibling validation utilities not included in a standalone download, and encodes host schema assumptions that need current validation. Kept as reviewed evidence, excluded from selected downloads. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/plugin-dev/agents/plugin-validator.md)
- **github-api-architect:** The role depends on a Code Interpreter environment that is not declared in its host tool configuration, and tightly couples its generation workflow to a particular service/manager architecture. Excluded in favor of more portable, source-aware architecture definitions. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/api-architect.agent.md)
- **github-scientific-paper-research:** Primarily a wrapper around a specific remote BGPT MCP service, whose access terms, host configuration and evidence-quality output were not verified here. Too little standalone research methodology for the selected definition downloads. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/scientific-paper-research.agent.md)
- **github-search-ai-optimization-expert:** The broad SEO/GEO checklist mixes implementation and optimization claims without a concrete evidence or audit-output contract. Named commercial analysis tools are not bundled or configured; stronger bounded research and technical roles were selected. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/search-ai-optimization-expert.agent.md)
- **voltagent-docs-drift-editor:** The otherwise narrow editing workflow incorrectly says an HTML comment preserves an old fragment anchor. It also permits a TODO mutation while describing the page as skipped. Do not promote the unchanged definition until these instructions are corrected. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/06-developer-experience/docs-drift-editor.md)
- **voltagent-dependency-manager:** Broad checklist persona includes fixed, apparently completed vulnerability, package and performance results as a delivery notification, without a sufficiently specific evidence/output contract. A narrower verified workflow is preferable. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/06-developer-experience/dependency-manager.md)
- **voltagent-incident-responder:** Includes operationally destructive containment actions and an unrestricted Bash/write tool set without an explicit action-authority gate; fixed successful incident metrics also appear in the delivery template. Not selected as a ready reusable response role. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/03-infrastructure/incident-responder.md)
- **voltagent-data-engineer:** Generic broad implementation checklist asserts zero-data-loss guarantees and supplies fixed successful delivery metrics. Insufficient grounding and role-specific output constraints for this curated selection. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/05-data-ai/data-engineer.md)
- **voltagent-assumption-mapping:** The full upstream role has invalid YAML frontmatter: its unquoted description contains a colon followed by a space. Excluded from screened downloads rather than requiring users to repair a known-broken native definition. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/08-business-product/assumption-mapping.md)
- **voltagent-ab-test-analysis:** The full upstream file fails YAML parsing because its description contains unquoted colon-space syntax. Its fixed-threshold decision framework also conflates minimum detectable effect with a shipping threshold and lacks a specified sequential design for extending tests. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/10-research-analysis/ab-test-analysis.md)
- **voltagent-scientific-literature-researcher:** Relies on a BGPT service and an unspecified context-manager integration, includes example completed research metrics, and repeats vendor evidence-quality claims without independent validation. The selected Research Synthesist provides a clearer source-assessment method without that dependency. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/10-research-analysis/scientific-literature-researcher.md)
- **agency-design-ux-researcher:** Includes fixed adoption and satisfaction targets while deferring important methodological detail to the model’s training. Research recruitment, consent, analysis and output verification are insufficiently specified for this screened collection. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/design/design-ux-researcher.md)
- **agency-design-brand-guardian:** Broad brand and trademark strategy persona with unmeasured consistency/equity targets and methodology deferred to core training. Insufficiently bounded deliverables and validation for the selected collection. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/design/design-brand-guardian.md)
- **agency-product-sprint-prioritizer:** Supplies fixed velocity, timeline and feature-success targets without an evidence workflow or configured planning integration. Excluded rather than present the persona’s targets as demonstrated planning performance. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/product/product-sprint-prioritizer.md)
- **agency-testing-reality-checker:** Predetermines a negative assessment and grade range, treats any zero-issue report as an automatic failure, and assumes a particular local capture script and app layout. That is not a neutral evidence gate. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/testing/testing-reality-checker.md)
- **agency-project-management-experiment-tracker:** Treats reaching statistical significance for nearly every experiment as a success target and supplies an illustrative revenue claim without a measurement procedure. Excluded because that framing can bias experimental interpretation. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/project-management/project-management-experiment-tracker.md)
- **wshobson-observability-engineer:** An extensive prospective capability list spanning telemetry, cloud cost, compliance and chaos engineering, with little bounded output or operational authority protocol. Excluded in favor of more focused definitions. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/observability-monitoring/agents/observability-engineer.md)
- **wshobson-context-manager:** Broad context-engineering capability lists do not provide a sufficiently concrete handoff schema or standalone memory implementation. Excluded to favor narrowly actionable roles and avoid implying that a prompt installs persistent memory. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/context-management/agents/context-manager.md)
- **ecc-build-error-resolver:** Its quick-recovery section deletes the dependency lockfile and reinstalls packages, conflicting with a minimal, reproducible repair role. Excluded from the unchanged downloadable selection. [Source ↗](https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/build-error-resolver.md)
- **ecc-e2e-runner:** Contains misleading Playwright guidance that raw page.click lacks auto-waiting, recommends networkidle for animation timing, and offers test quarantine plus artifact upload without enough workflow boundaries. A corrected definition would be preferable. [Source ↗](https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/e2e-runner.md)
- **ecc-doc-updater:** Assumes companion code-map generation scripts and tooling that are not included in the standalone file. It overlaps the selected documentation roles, whose repository inspection and output contracts are more reusable. [Source ↗](https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/doc-updater.md)
- **voltagent-content-quality-editor:** Delegates its central editing step to a globally installed external unslop package that was not independently reviewed, while using fixed readability targets as a quality gate. The standalone definition is not a self-contained substantive editing method. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/08-business-product/content-quality-editor.md)
- **voltagent-ai-writing-auditor:** The role treats unsupported stylometric frequency thresholds and blanket punctuation/hedging rules as an audit method, then rewrites the entire text. It also incorporates named external writing systems whose applicable upstream permissions were not independently verified in this pass. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/04-quality-security/ai-writing-auditor.md)
- **github-refine-issue:** A short generic issue-refinement checklist requests delete_issue alongside update tools without explaining or gating that unrelated destructive capability. It lacks a concrete change-review contract and was not selected. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/refine-issue.agent.md)
- **github-agent-governance-reviewer:** The broad governance role prescribes a Python-style policy decorator and speculative trust scoring across multiple frameworks without a concrete output contract, verification protocol or referenced implementation. It overlaps better-bounded security and threat-modeling roles and was excluded rather than presented as an implemented enforcement layer. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/agent-governance-reviewer.agent.md)
- **github-task-researcher:** Requires deleting non-selected alternatives from the final research record and assumes a large host-specific tool collection. It substantially overlaps the selected technical-spike researcher while preserving less of the decision trail. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/task-researcher.agent.md)
- **sentry-senpai:** The full original fails strict YAML parsing: an unquoted description contains colon-space syntax at Examples:. Excluded from unchanged native-agent downloads. [Source ↗](https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/agents/senpai.md)
- **sentry-code-simplifier:** This vendored copy puts an attribution comment before its YAML block and duplicates the Anthropic role. Selected the valid original Anthropic definition with its applicable licence instead. [Source ↗](https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/agents/code-simplifier.md)
- **awslabs-aidlc-aws-platform:** The persona covers live provisioning, drift remediation and teardown through inherited shell tools. The single file supplies neither an action-specific approval contract nor a fixed output schema; framework controls would need separate operational verification. Not selected for this reusable-definition expansion. [Source ↗](https://github.com/awslabs/aidlc-workflows/blob/3e614b6e55963a2d2390c4d8b0877c5a8a33bb2f/core/agents/aidlc-aws-platform-agent.md)
- **awslabs-aidlc-operations:** Includes production chaos experiments and restart, failover and scaling runbooks without defining action-specific authorization, abort conditions or a bounded response artifact in the persona. Prefer a separately reviewed operational workflow over promoting the unchanged role as a general-purpose download. [Source ↗](https://github.com/awslabs/aidlc-workflows/blob/3e614b6e55963a2d2390c4d8b0877c5a8a33bb2f/core/agents/aidlc-operations-agent.md)
- **trailofbits-dimension-validator:** The definition assigns severity from mismatch type and broadly excludes commented conversions, test/mock code and documented edge cases from findings without requiring the same path-level verification. It also depends on prior unit annotations and host-specific task tools. The narrower evidence-driven workers were selected instead. [Source ↗](https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/dimensional-analysis/agents/dimension-validator.md)
- **microsoft-coreai-infrastructure:** This is a CoreAI DIY project runbook with fixed repository paths, Bicep modules and Azure deployment/teardown commands. It is not a portable infrastructure definition, and the unchanged file cannot supply another project’s deployment boundaries. [Source ↗](https://github.com/microsoft/skills/blob/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/agents/infrastructure.agent.md)
- **microsoft-wiki-researcher:** Substantially overlaps the selected code exploration and research roles. It depends on a resolved repository/citation context and has no tools allowlist; the expansion favors more bounded workers with explicit analysis outputs. [Source ↗](https://github.com/microsoft/skills/blob/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/deep-wiki/agents/wiki-researcher.md)
- **AWS Incident Triage:** Withheld after inspecting its required aws-cloudwatch-investigation companion: the throttling example treats every API Gateway 4XXError as a throttling event, and the previous-week comparison duplicates the same metric inside one request without shifting its time window. Current AWS API documentation does not support these interpretations. The investigation outline is useful, but the unchanged dependency can produce misleading incident evidence. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/aws-incident-triage.agent.md)
- **aws-principal-architect:** Broad AWS expertise inventory lacks a concrete required deliverable or verification contract. The selected serverless architect gives a more specific design output and fills the AWS architecture gap without another overlapping generalist. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/aws-principal-architect.agent.md)
- **aws-serverless-architect:** Withheld in favour of more specific, verifiable definitions. Its advice mixes an HTTP API preference with REST-only API Gateway features without explaining the boundary, asks for rough monthly costs without a pricing-source or calculator requirement, and requests working infrastructure examples without a verification gate. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/aws-serverless-architect.agent.md)
- **react19-test-guardian:** Contains a false React 19 Strict Mode claim and tells the agent to change spy assertions to observed call counts. Current React documentation still describes extra development effect cycles. Its passWithNoTests/forceExit-driven completion loop can also obscure missing coverage or unresolved handles. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/react19-test-guardian.agent.md)
- **arm-migration-agent:** Directs automatic architecture and dependency changes while treating builds and integration validation as optional. It also requires learning_path_server, which is absent from the declared MCP tools. The unchanged workflow lacks a sufficiently reliable validation contract for architecture-specific changes. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/arm-migration.agent.md)
- **Oracle-to-PostgreSQL Migration Expert:** Withheld after inspecting required companion skills: migrating-oracle-to-postgres-data-access-code instructs retaining CommandType.StoredProcedure for function calls, contrary to the default behaviour documented for Npgsql 7 and later. Its risk-review skill also needs a separate references tree. The phase structure is useful, but the unchanged workflow includes a material migration error. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/oracle-to-postgres-migration-expert.agent.md)
- **OpenAPI to Application Generator:** Withheld because the procedure asks for a complete deployable application but does not define concrete OpenAPI validation, unresolved-reference handling, architecture decisions or executed acceptance checks; it largely repeats the existing scaffolding role. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/openapi-to-application.agent.md)
- **backend-development-performance-engineer:** Assigns generic latency severity thresholds and asks for expected improvement estimates without a concrete measurement protocol. The selected database and browser performance roles make stronger distinctions between observed measurements and recommendations. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/performance-engineer.md)
- **backend-development-test-automator:** Substantially overlaps the selected Test Engineer and the expanded QA and Playwright roles. Its general capability list and test-file organization add less distinctive method than the bounded alternatives. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/test-automator.md)
- **backend-development-graphql-architect:** Mostly a broad catalogue of GraphQL capabilities and technologies, with no specific output schema, evidence contract or failure handling. Not selected solely to fill an API-design label. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/graphql-architect.md)
- **monorepo-architect:** A compact setup checklist with no concrete validation, migration boundaries or deliverable contract. The architecture and build-related roles already cover its general planning advice. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/developer-essentials/agents/monorepo-architect.md)
- **eval-orchestrator:** Combines static checks and model-supplied rubric/F1 scores into badges such as production ready without a defensible runtime validation contract. The workflow depends on a CLI and judge absent from the standalone definition and overstates what the composite can establish. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/plugin-eval/agents/eval-orchestrator.md)
- **framework-migration-legacy-modernizer:** A short general migration checklist substantially overlaps the existing modernization roles. The selected Uplift Migrator adds a more concrete pilot-playbook gate, unit ownership and executed-build reporting contract. [Source ↗](https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/framework-migration/agents/legacy-modernizer.md)
- **api-designer:** The delivery template contains fixed successful endpoint and SDK counts, while the role assumes an unspecified context-manager protocol. The extensive topic lists do not establish an evidence-backed validation or completion contract. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/01-core-development/api-designer.md)
- **a11y-architect:** Misidentifies WCAG 2.2 criterion 2.4.11 as focus contrast and blends target-size/spacing advice into purported universal requirements. Current W3C documentation defines 2.4.11 as Focus Not Obscured (Minimum). The unchanged reference should be corrected before recommendation. [Source ↗](https://github.com/affaan-m/everything-claude-code/blob/bf70150eb2df8070024e5bdf08e4aa08959e2735/agents/a11y-architect.md)
- **Software Architect:** The bounded-context and architecture-pattern guidance is useful, but overlaps the selected Code Architect, Architecture Critic and ADR roles. This expansion prioritizes missing methods rather than another general system-design persona. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/engineering/engineering-software-architect.md)
- **Test Automation Engineer:** The CI example relies on an unconfigured PLAYWRIGHT_TRACE environment variable for tracing and its worker fixture is not safe across concurrent shard jobs sharing a backend. The role also prescribes fixed reliability targets and automatic test quarantine. Prefer the narrower exploration-first test role. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/testing/testing-test-automation-engineer.md)
- **Spatial Data Scientist:** Overstates that non-spatial models on spatial data necessarily produce invalid inference, and lists many spatial methods without a precise data/validation contract. The selected statistician provides clearer design and assumption boundaries without that blanket claim. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/gis/gis-spatial-data-scientist.md)
- **Language Translator:** A Spanish-English travel and conversation persona rather than a software-localization workflow. Broad cultural and emergency guidance and phonetic approximations would need specialist verification; this pass does not promote it as a general translation or localisation solution. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/specialized/language-translator.md)
- **Lingo.dev Internationalization:** Delegates the entire procedure to a remote i18n_checklist tool whose current workflow and service requirements were not independently reviewed. The file supplies no substantive standalone localization method beyond obeying that service. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/lingodotdev-i18n.agent.md)
- **GitHub Community Elasticsearch Observability Agent:** Withheld at this revision: the embedded MCP configuration combines a remote type with local command/args and no remote URL field. It needs a host-specific configuration correction before the advertised Elastic tools can be treated as an installable integration. [Source ↗](https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/agents/elasticsearch-observability.agent.md)
- **Agency Experiment Tracker:** Withheld for experiment analysis: its success criteria reward most experiments reaching statistical significance. That is not a sound generic measure of experiment quality and can bias interpretation away from valid null results. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/project-management/project-management-experiment-tracker.md)
- **SAST and SCA analyzer:** The pinned profile assigns an overall compliance PASS when no Critical or High findings are found. A bounded SAST/SCA scan cannot establish compliance with the named frameworks, and the self-assessed quality score supplies no independent validation. [Source ↗](https://github.com/github/awesome-copilot/blob/3a685010a7afdc0dbd4c83b7fbda6c316aa516e5/agents/sast-sca-security-analyzer.agent.md)
- **ARM Cortex expert:** The pinned profile both recommends static mut DMA buffers and later calls all static mut undefined behavior. Its critical-section example unconditionally enables interrupts after disabling them, failing to preserve a previously disabled state. Hardware-specific code needs correction and device-bound verification. [Source ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/arm-cortex-microcontrollers/agents/arm-cortex-expert.md)
- **Healthcare reviewer:** The profile emits SAFE TO DEPLOY for clinical software from an LLM code review without a validated clinical-safety acceptance contract or qualified sign-off. That verdict exceeds this source-review evidence; retain as a private candidate pending a bounded contract. [Source ↗](https://github.com/affaan-m/ECC/blob/ef648e01899ba3e8dc6371642deaaf64b4477775/agents/healthcare-reviewer.md)
- **SE Security Reviewer at the reviewed revision:** Withheld: its prompt-injection example labels a simple input-sanitization approach secure, which overstates the protection offered by string filtering. [Source ↗](https://github.com/github/awesome-copilot/blob/3a685010a7afdc0dbd4c83b7fbda6c316aa516e5/agents/se-security-reviewer.agent.md)
- **Technical Content Evaluator at the reviewed revision:** Withheld: the instructions depend on an undefined /ultra-think invocation and mandate numerical content scores without a validated measurement procedure. [Source ↗](https://github.com/github/awesome-copilot/blob/3a685010a7afdc0dbd4c83b7fbda6c316aa516e5/agents/technical-content-evaluator.agent.md)
- **replay-minimizer:** The opened definition is bound to microsoft/TypeScript’s Go TestReplay harness, flags and replay-file format. It is a compiler-repo procedure, not a portable crash minimizer. [Source ↗](https://github.com/microsoft/TypeScript/blob/d61a7d235906e78be9b111de0ba060e28e67ecfa/.github/agents/replay-minimizer.md)
- **Demonstrate:** The opened Copilot agent demonstrates a microsoft/vscode pull request through vscode-playwright-mcp and can edit settings. It is not a portable UI check and it does not produce a pass or fail result. [Source ↗](https://github.com/microsoft/vscode/blob/35c48f9946eecf40beed751940607f184a03b6de/.github/agents/demonstrate.md)
- **go-sdk-tool-migrator:** The opened definition migrates one toolset in github/github-mcp-server from mark3labs/mcp-go to modelcontextprotocol/go-sdk. It is not a general Go or MCP migration guide. [Source ↗](https://github.com/github/github-mcp-server/blob/55edd58d5e1127fe7ea3c036bc14dca66f7e41c4/.github/agents/go-sdk-tool-migrator.md)
- **.NET Notebook Migration Agent:** The opened definition converts notebooks in microsoft/ai-agents-for-beginners and allows runCommands while the body says not to execute code. It is a course-repo transform, not a general agent. [Source ↗](https://github.com/microsoft/ai-agents-for-beginners/blob/25b7985f3b2dc37a84f4a7387ccd3c9f0e5b1595/.github/agents/dotnet-notebook-migration.agent.md)
- **Claude Security plugin agents:** plugins/claude-security/LICENSE at this commit defines the Plugin as "This software, including its prompts, agent and skill definitions, workflows, server code, and documentation" and says "you may not: (a) distribute, publish, sublicense, sell, or otherwise make the Plugin or any modified version of it available to any third party". Its agents patch-verifier and scan-verifier are therefore not listed, not even with a short description quote. The licence is byte-identical at c447c3207a425bc4e2a0d068435f64b0477ae981. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/claude-security/LICENSE)
- **anthropic-pr-review-code-reviewer:** Same review responsibilities and confidence threshold as the selected feature-dev code reviewer, but this copy declares no tools, so in Claude Code it inherits every subagent tool, including Write and Bash. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/f359d43b406057f1a8cdbc4ea93b827642c162e6/plugins/pr-review-toolkit/agents/code-reviewer.md)
- **anthropic-pr-review-code-simplifier:** The body after the frontmatter is byte-identical to plugins/code-simplifier/agents/code-simplifier.md, already listed as anthropic-code-simplifier. Only the description differs. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/f359d43b406057f1a8cdbc4ea93b827642c162e6/plugins/pr-review-toolkit/agents/code-simplifier.md)
- **anthropic-math-proof-worker-deep:** The higher-effort variant of the listed math-proof worker. Its description says it is launched only by the math-proof plugin's siege skill, from the escalation round on. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/f359d43b406057f1a8cdbc4ea93b827642c162e6/plugins/math-proof/agents/math-proof-worker-deep.md)
- **anthropic-skill-eval-comparator:** Assigns 1 to 5 rubric scores and a 1 to 10 overall score, and is told to be decisive because ties should be rare. The pass-or-fail grader from the same skill is listed instead. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/f359d43b406057f1a8cdbc4ea93b827642c162e6/plugins/skill-creator/skills/skill-creator/agents/comparator.md)
- **anthropic-skill-eval-analyzer:** Reads the blind comparator's winner and scores to explain why the winner won, so it depends on the comparator excluded above. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/f359d43b406057f1a8cdbc4ea93b827642c162e6/plugins/skill-creator/skills/skill-creator/agents/analyzer.md)
- **anthropic-valuation-reviewer:** The agent computes fund NAV, carried interest and LP allocations itself, with no cite-every-number rule and no independent re-verification step of the kind the GL reconciler has. [Source ↗](https://github.com/anthropics/financial-services/blob/574ed3624aebd0418c7e96cd101262f30210ab26/plugins/agent-plugins/valuation-reviewer/agents/valuation-reviewer.md)
- **vercel-ai-architect:** Its model-selection tree names fixed models for lowest latency and for speed with low cost, and a fallback order, with no measurement, source or date behind those comparisons. [Source ↗](https://github.com/vercel/vercel-plugin/blob/b97d74d07702e9fe4bd7ac5ef308bc9f65abc826/agents/ai-architect.md)
- **openai-codex-awaiter:** A built-in Codex helper role that polls a command until it finishes. It is compiled into Codex, not a definition users load, and it reviews nothing. [Source ↗](https://github.com/openai/codex/blob/21c16161191ff965031d1ac41fe9046011610743/codex-rs/core/assets/agent/builtins/awaiter.toml)
- **openai-codex-explorer:** The built-in explorer.toml is an empty file (0 bytes) at this commit. [Source ↗](https://github.com/openai/codex/blob/21c16161191ff965031d1ac41fe9046011610743/codex-rs/core/assets/agent/builtins/explorer.toml)
- **figma-design-parity-review-agent:** The Figma plugin's agents are governed by plugins/figma/LICENSE.txt, which points to the Figma Developer Terms and says the beta materials may be modified or discontinued at any time. Those terms were not reviewed. The design-system-rules agent in the same folder was excluded for the same reason. [Source ↗](https://github.com/openai/plugins/blob/0722921d5542fc593105c27bd52630babd8b8c2a/plugins/figma/agents/design-parity-review-agent.md)
- **aws-llm2bedrock-agents:** The five llm2bedrock agents (code-analyzer, log-ingestor, prompt-evaluator, code-rewriter, report-generator) are phases of AWS Startup Migrate Track 2 and consume each other's results. The report generator prices source models from a static table to be updated periodically, and estimates a missing model from the closest listed one. [Source ↗](https://github.com/aws/agent-toolkit-for-aws/blob/c34fbdfde6779593f651f2c85629a85d27231498/plugins/aws-startup-advisor/agents/llm2bedrock-report-generator.md)
- **aws-generic-phase-workers:** generic-phase-worker-rw and -rwx are dispatched only by the plugin's DSL interpreter. Their descriptions say not to dispatch them directly for user conversation. [Source ↗](https://github.com/aws/agent-toolkit-for-aws/blob/c34fbdfde6779593f651f2c85629a85d27231498/plugins/aws-startup-advisor/agents/generic-phase-worker-rw.md)
- **stripe-company-researcher:** Researches a third-party company's website to pre-fill Stripe Connect discovery answers. Not a code, security, testing or evaluation role, and its confidence levels are inferred by the model. [Source ↗](https://github.com/stripe/ai/blob/deae744bc0cbf6034b4b6f22f51c690b71a4e779/providers/claude/plugin/agents/company-researcher.md)
- **sentry-for-ai skill-creator and skill-updater:** Maintainer agents that create or update Sentry SDK skill bundles in this repository and open a pull request. [Source ↗](https://github.com/getsentry/sentry-for-ai/blob/c2313d3a826d56249e70623313bdc27ce5fca8b6/.github/agents/skill-creator.agent.md)
- **github-dynatrace-expert:** The embedded MCP server URL is a specific dynatracelabs.com development host (pia1134d.dev.apps.dynatracelabs.com) and sends the user's Dynatrace token to it as a bearer header. Loaded unchanged, the agent would route credentials to that host. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/dynatrace-expert.agent.md)
- **github-amplitude-experiment-implementation:** Creates a live experiment in the user's Amplitude project with create_experiment and wraps the feature in it, with no approval step before the remote write. No tools or MCP server are declared in the file. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/amplitude-experiment-implementation.agent.md)
- **github-postgresql-dba:** A broad DBA persona with pgsql_modifyDatabase, bulk-load and runCommands tools, listing backups and restores among its tasks, with no confirmation gate or output contract. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/postgresql-dba.agent.md)
- **github-ms-sql-dba:** A broad DBA persona with runCommands and query tools covering backups, restores, upgrades and security changes, with no confirmation gate or output contract. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/ms-sql-dba.agent.md)
- **github-se-system-architecture-reviewer:** Chooses architectures from fixed user-count and monthly hosting-budget bands (for example under $100 a month means serverless) with no source, and creates an ADR file for every decision. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/se-system-architecture-reviewer.agent.md)
- **github-quality-playbook:** Its description claims it finds the 35% of real defects that structural review cannot catch, and the body says iterations typically add 40-60% more confirmed bugs. Neither figure is sourced in the file. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/quality-playbook.agent.md)
- **github-gem-reviewer:** A hidden subagent (user-invocable false) that needs the gem-team orchestrator's plan_id and handoff fields, and returns a model-supplied confidence number such as 0.95. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/gem-reviewer.agent.md)
- **github-insiders-a11y-tracker:** Tracks accessibility issues released to VS Code Insiders in microsoft/vscode only. It does not review the user's own code. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/insiders-a11y-tracker.agent.md)
- **github-defender-scout-kql:** Tells the agent to always filter on Timestamp, yet lists DeviceTvmSoftwareVulnerabilities among its tables. Microsoft's schema page for that table (learn.microsoft.com/en-us/defender-xdr/advanced-hunting-devicetvmsoftwarevulnerabilities-table, checked 2026-10-13) has no Timestamp column, so the rule produces failing queries. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/defender-scout-kql.agent.md)
- **github-wg-code-sentinel:** A security persona with a broad edit and runCommands tool set and no evidence or output contract beyond a severity label. Much of the file is a speaking style. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/wg-code-sentinel.agent.md)
- **github-tech-debt-remediation-plan:** Says analysis only, no code modifications, but declares editFiles, runCommands, runTests and github tools, and asks it to create issues from a template. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/tech-debt-remediation-plan.agent.md)
- **github-critical-thinking:** A questioning mode that overlaps the listed devils-advocate agent and produces no artefact to review. [Source ↗](https://github.com/github/awesome-copilot/blob/156736fb63e965b2f547a1460f3b5972c46e6b24/agents/critical-thinking.agent.md)
- **github-se-system-architecture-reviewer:** Generic user-count/budget thresholds and one-line architecture decision trees are unsupported heuristics; overlap with existing architecture reviewers. [Source ↗](https://github.com/github/awesome-copilot/blob/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8/agents/se-system-architecture-reviewer.agent.md)
- **voltagent-cohort-analysis:** Unquoted description contains Triggers on: and fails YAML parsing; not distributed as a working native definition. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/408d3c9eee2d0c75c12a3abb5de29e53c2ca6b9e/categories/10-research-analysis/cohort-analysis.md)
- **voltagent-backlog-grooming:** Unquoted description contains Triggers on: and fails YAML parsing; not distributed as a working native definition. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/408d3c9eee2d0c75c12a3abb5de29e53c2ca6b9e/categories/08-business-product/backlog-grooming.md)
- **voltagent-first-principles-thinking:** Unquoted description contains Triggers on: and fails YAML parsing; not distributed as a working native definition. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/408d3c9eee2d0c75c12a3abb5de29e53c2ca6b9e/categories/10-research-analysis/first-principles-thinking.md)
- **ecc-django-build-resolver:** Troubleshooting commands can print database credentials, kill unrelated port owners and fake/reset migrations. Not admitted as a general build helper. [Source ↗](https://github.com/affaan-m/everything-claude-code/blob/b92f181b3b748d1abbc2afd94af6aa7d8c8fca29/agents/django-build-resolver.md)
- **github-technical-content-evaluator:** Conflicting grade ceilings, absent /ultra-think dependency and simulated learner-success estimates weaken the claimed evaluation contract. [Source ↗](https://github.com/github/awesome-copilot/blob/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8/agents/technical-content-evaluator.agent.md)
- **voltagent-license-engineer:** Pseudo-legal engineering terminology and example 100% clearance claims do not establish usable legal review or licence clearance. [Source ↗](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/408d3c9eee2d0c75c12a3abb5de29e53c2ca6b9e/categories/08-business-product/license-engineer.md)
- **wshobson-payment-integration:** Instructs acknowledging webhooks before database writes/durable acceptance and groups PayPal under generic HMAC handling; insufficient payment correctness. [Source ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/payment-processing/agents/payment-integration.md)
- **wshobson-c4-container:** Conflates C4 containers with environment deployment topology and mandates OpenAPI across non-HTTP interfaces. Official C4 documentation separates deployment diagrams. [Source ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/c4-architecture/agents/c4-container.md)
- **github-electron-angular-native:** Names ipcMain.handleSync, absent from the inspected official ipcMain API, and includes older project-specific assumptions. Replaced with a clearer role. [Source ↗](https://github.com/github/awesome-copilot/blob/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8/agents/electron-angular-native.agent.md)
- **github-winforms-expert:** Partial candidate review found conflicting never-dock versus Dock=Fill directions and questionable floating-range guidance. Full technical validation not completed; not admitted. [Source ↗](https://github.com/github/awesome-copilot/blob/f25421d3f1b8b3bb217f78a7c0567cf7ec117cd8/agents/WinFormsExpert.agent.md)
- **agency-engineering-privacy-engineer:** Overbroad special-category and legal-basis statements plus unqualified anonymization claims make the profile unsuitable for a general technical privacy recommendation. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/engineering/engineering-privacy-engineer.md)
- **agency-engineering-search-relevance-engineer:** Says search-time-only synonyms break matching, then recommends exactly that in its example; official synonym_graph documentation explicitly supports search-only use. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/engineering/engineering-search-relevance-engineer.md)
- **agency-engineering-mobile-release-engineer:** Android lane calls the iOS dSYM upload_symbols_to_crashlytics action as though it uploads mapping.txt. Current official action docs list iOS support. [Source ↗](https://github.com/msitarzewski/agency-agents/blob/bd956db032d907387e6b9ddebff3e18f1de8c679/engineering/engineering-mobile-release-engineer.md)
- **Zeroize preflight:** The same file says the orchestrator inputs are a closed table that includes languages such as rust, and that table does not name cargo_manifest. The Rust mode section then runs only when cargo_manifest is provided and tells the agent to verify that path. Those two instructions do not match, so the file was not selected. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/0-preflight.md)
- **Zeroize PoC generator:** The same file says PoC generation is mandatory and that every finding gets a PoC regardless of confidence, then says Rust PoC generation is enabled for only three categories and that every other Rust category records poc_supported false. That contradiction is why it was not selected. The program-writing steps are not repeated here. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/5-poc-generator.md)
- **Claude Security orchestrator:** The root README says to use each plugin's LICENSE file. plugins/claude-security/LICENSE says this plugin, including its agent definitions, may not be distributed or published to any third party. The root LICENSE is Apache-2.0. Those terms disagree, so this file is not selected. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/claude-security.md)
- **Scan researcher:** The root README says to use each plugin's LICENSE file. plugins/claude-security/LICENSE says this plugin, including its agent definitions, may not be distributed or published to any third party. The root LICENSE is Apache-2.0. Those terms disagree, so this file is not selected. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/claude-security/agents/scan-researcher.md)
- **Code simplifier:** plugins/pr-review-toolkit/README.md states the licence as MIT. The plugin LICENSE at this pin is Apache License Version 2.0 and is byte-identical to the repository root LICENSE. The README and LICENSE disagree, so this file is not selected. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/pr-review-toolkit/agents/code-simplifier.md)
- **Arithmetic scanner:** Pass 0 says the inventory that supplies total_files_scanned already applies the Pass 1 path exclusions. The output section calls that same Pass 0 baseline pre-exclusion and sets total_files_scanned equal to files_excluded plus the post-filter arithmetic and non-match counts. Those definitions of the same count cannot both be true. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/dimensional-analysis/agents/arithmetic-scanner.md)
- **Dimension annotator:** The preserve-annotations section says never to overwrite an existing dimensional annotation, and the next bullet says to update an annotation when it is clearly incorrect. The same section says to add to existing NatSpec and not to replace it. Those instructions disagree about whether an existing annotation may be changed. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/dimensional-analysis/agents/dimension-annotator.md)
- **PoC builder:** Its primary instructions are to build proof-of-concept exploits for a vulnerability that earlier phases already treated as verified, including executable exploit code and tests meant to show impact. This review does not publish that procedure. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/fp-check/agents/poc-builder.md)
- **Rust compiler analyzer:** The input table does not name enable_asm, but assembly analysis is skipped when enable_asm is false and the assembly output is included only when enable_asm is true. An O0 IR emission failure skips Step 4 in the process and skips Steps 4 and 5 in the error section. The opening says Step 7 surveys the crate and writes coverage-gaps.json, while the survey heading and the error section assign that write to Step 6 and assign Step 7 to cleanup. Those instructions do not match, so the file was not selected. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/3b-rust-compiler-analyzer.md)
- **Report assembler:** The same file says each finding's severity is high or medium, then requires a high, medium, and low breakdown and tells final mode to downgrade one result's severity to low. Final mode reads the existing findings file and does not rerun collection, but the error section says a missing source-findings file is fatal. Those instructions do not match, so the file was not selected. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/4-report-assembler.md)
- **PoC validator:** The file's purpose is to compile and run every proof of concept in the manifest and record whether the run is exploitable. That walks through an exploit proof of concept, so it is excluded. The commands and result mapping are not repeated here. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/5b-poc-validator.md)
- **PoC verifier:** The file's purpose is to walk through each proof of concept and judge whether it demonstrates the vulnerability it claims. That walks through an exploit proof of concept, so it is excluded. The checks and examples are not repeated here. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/5c-poc-verifier.md)

04 / PRACTICAL ANSWERS

## Before you add it.

 Is an agent definition a running AI service?

No. These are reusable role and workflow instructions for an agent host. You still need a compatible tool, model access and appropriate permissions. The host and model determine what the definition can actually do.

 Can I copy the complete definition?

When the applicable upstream licence permits redistribution, the detail page includes the exact reviewed definition, a download, attribution and licence text. Preserve those notices when reusing or redistributing it. Other resources link to the original instead.

 Will every definition work in every AI tool?

No. Frontmatter, model aliases, tool names, installation paths and delegation behavior vary by host. Each review lists documented compatibility and relevant limitations. Adaptations need their own review; a downloaded role is not a universal installation package.

 How were these roles selected?

We look for a specific job, an actionable workflow, useful output expectations and explicit checks or boundaries. Each definition has original notes explaining its inclusion. We have not benchmarked these roles against every alternative or executed them across all hosts.

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
