{"kind":"agents","reviewedAt":"2026-09-22","sourceCount":103,"publisherCount":11,"discoverySources":[{"name":"anthropics/claude-plugins-official","url":"https://github.com/anthropics/claude-plugins-official"},{"name":"github/awesome-copilot","url":"https://github.com/github/awesome-copilot"},{"name":"VoltAgent/awesome-claude-code-subagents","url":"https://github.com/VoltAgent/awesome-claude-code-subagents"},{"name":"wshobson/agents","url":"https://github.com/wshobson/agents"},{"name":"msitarzewski/agency-agents","url":"https://github.com/msitarzewski/agency-agents"},{"name":"affaan-m/everything-claude-code","url":"https://github.com/affaan-m/everything-claude-code"},{"title":"AWS Labs AI-DLC Workflows","url":"https://github.com/awslabs/aidlc-workflows","note":"Reviewed authored personas and the documented framework projection; retained the advisory compliance role.","checkedAt":"2026-09-21"},{"title":"Trail of Bits Skills","url":"https://github.com/trailofbits/skills","note":"Reviewed full worker definitions, output contracts, plugin dependencies and the CC-BY-SA licence.","checkedAt":"2026-09-21"},{"title":"Sentry Skills","url":"https://github.com/getsentry/skills","note":"Screened agent originals; recorded frontmatter exclusions and selected the original Anthropic simplifier instead of a duplicate vendored copy.","checkedAt":"2026-09-21"},{"title":"Microsoft Skills","url":"https://github.com/microsoft/skills","note":"Reviewed infrastructure and wiki agent definitions; excluded project-specific or overlapping roles.","checkedAt":"2026-09-21"},{"title":"VoltAgent/awesome-claude-code-subagents — expanded definition review","url":"https://github.com/VoltAgent/awesome-claude-code-subagents/tree/82b73821baa7a911d5b14cfb6da238b7f0db6b42","note":"Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.","checkedAt":"2026-09-21"},{"title":"affaan-m/everything-claude-code — expanded definition review","url":"https://github.com/affaan-m/everything-claude-code/tree/bf70150eb2df8070024e5bdf08e4aa08959e2735","note":"Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.","checkedAt":"2026-09-21"},{"title":"anthropics/claude-plugins-official — expanded definition review","url":"https://github.com/anthropics/claude-plugins-official/tree/c447c3207a425bc4e2a0d068435f64b0477ae981","note":"Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.","checkedAt":"2026-09-21"},{"title":"github/awesome-copilot — expanded definition review","url":"https://github.com/github/awesome-copilot/tree/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","note":"Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.","checkedAt":"2026-09-21"},{"title":"msitarzewski/agency-agents — expanded definition review","url":"https://github.com/msitarzewski/agency-agents/tree/87f8301cad3823a9a34d762036ae923a0eff306f","note":"Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.","checkedAt":"2026-09-21"},{"title":"wshobson/agents — expanded definition review","url":"https://github.com/wshobson/agents/tree/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620","note":"Reviewed complete candidate definitions, licensing and required host/dependency boundaries; selections are source reviews, not runtime benchmarks.","checkedAt":"2026-09-21"},{"title":"Svelte primary source","url":"https://github.com/sveltejs/ai-tools","checkedAt":"2026-09-22","note":"Direct source screening; popularity was not treated as evidence of quality."}],"excluded":[{"id":"anthropic-silent-failure-hunter","reason":"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.","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/silent-failure-hunter.md"},{"id":"anthropic-plugin-validator","reason":"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.","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/plugin-dev/agents/plugin-validator.md"},{"id":"github-api-architect","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/api-architect.agent.md"},{"id":"github-scientific-paper-research","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/scientific-paper-research.agent.md"},{"id":"github-search-ai-optimization-expert","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/search-ai-optimization-expert.agent.md"},{"id":"voltagent-docs-drift-editor","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/06-developer-experience/docs-drift-editor.md"},{"id":"voltagent-dependency-manager","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/06-developer-experience/dependency-manager.md"},{"id":"voltagent-incident-responder","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/03-infrastructure/incident-responder.md"},{"id":"voltagent-data-engineer","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/05-data-ai/data-engineer.md"},{"id":"voltagent-assumption-mapping","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/08-business-product/assumption-mapping.md"},{"id":"voltagent-ab-test-analysis","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/10-research-analysis/ab-test-analysis.md"},{"id":"voltagent-scientific-literature-researcher","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/10-research-analysis/scientific-literature-researcher.md"},{"id":"agency-design-ux-researcher","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/design/design-ux-researcher.md"},{"id":"agency-design-brand-guardian","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/design/design-brand-guardian.md"},{"id":"agency-product-sprint-prioritizer","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/product/product-sprint-prioritizer.md"},{"id":"agency-testing-reality-checker","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/testing/testing-reality-checker.md"},{"id":"agency-project-management-experiment-tracker","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/project-management/project-management-experiment-tracker.md"},{"id":"wshobson-observability-engineer","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/observability-monitoring/agents/observability-engineer.md"},{"id":"wshobson-context-manager","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/context-management/agents/context-manager.md"},{"id":"ecc-build-error-resolver","reason":"Its quick-recovery section deletes the dependency lockfile and reinstalls packages, conflicting with a minimal, reproducible repair role. Excluded from the unchanged downloadable selection.","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/build-error-resolver.md"},{"id":"ecc-e2e-runner","reason":"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.","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/e2e-runner.md"},{"id":"ecc-doc-updater","reason":"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.","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/doc-updater.md"},{"id":"voltagent-content-quality-editor","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/08-business-product/content-quality-editor.md"},{"id":"voltagent-ai-writing-auditor","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/04-quality-security/ai-writing-auditor.md"},{"id":"github-refine-issue","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/refine-issue.agent.md"},{"id":"github-agent-governance-reviewer","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/agent-governance-reviewer.agent.md"},{"id":"github-task-researcher","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/task-researcher.agent.md"},{"id":"sentry-senpai","reason":"The full original fails strict YAML parsing: an unquoted description contains colon-space syntax at Examples:. Excluded from unchanged native-agent downloads.","sourceUrl":"https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/agents/senpai.md"},{"id":"sentry-code-simplifier","reason":"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.","sourceUrl":"https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/agents/code-simplifier.md"},{"id":"awslabs-aidlc-aws-platform","reason":"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.","sourceUrl":"https://github.com/awslabs/aidlc-workflows/blob/3e614b6e55963a2d2390c4d8b0877c5a8a33bb2f/core/agents/aidlc-aws-platform-agent.md"},{"id":"awslabs-aidlc-operations","reason":"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.","sourceUrl":"https://github.com/awslabs/aidlc-workflows/blob/3e614b6e55963a2d2390c4d8b0877c5a8a33bb2f/core/agents/aidlc-operations-agent.md"},{"id":"trailofbits-dimension-validator","reason":"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.","sourceUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/dimensional-analysis/agents/dimension-validator.md"},{"id":"microsoft-coreai-infrastructure","reason":"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.","sourceUrl":"https://github.com/microsoft/skills/blob/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/agents/infrastructure.agent.md"},{"id":"microsoft-wiki-researcher","reason":"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.","sourceUrl":"https://github.com/microsoft/skills/blob/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/deep-wiki/agents/wiki-researcher.md"},{"name":"AWS Incident Triage","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/aws-incident-triage.agent.md"},{"name":"aws-principal-architect","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/aws-principal-architect.agent.md"},{"name":"aws-serverless-architect","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/aws-serverless-architect.agent.md"},{"name":"react19-test-guardian","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/react19-test-guardian.agent.md"},{"name":"arm-migration-agent","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/arm-migration.agent.md"},{"name":"Oracle-to-PostgreSQL Migration Expert","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/oracle-to-postgres-migration-expert.agent.md"},{"name":"OpenAPI to Application Generator","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/openapi-to-application.agent.md"},{"name":"backend-development-performance-engineer","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/performance-engineer.md"},{"name":"backend-development-test-automator","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/test-automator.md"},{"name":"backend-development-graphql-architect","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/graphql-architect.md"},{"name":"monorepo-architect","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/developer-essentials/agents/monorepo-architect.md"},{"name":"eval-orchestrator","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/plugin-eval/agents/eval-orchestrator.md"},{"name":"framework-migration-legacy-modernizer","reason":"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.","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/framework-migration/agents/legacy-modernizer.md"},{"name":"api-designer","reason":"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.","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/01-core-development/api-designer.md"},{"name":"a11y-architect","reason":"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.","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/bf70150eb2df8070024e5bdf08e4aa08959e2735/agents/a11y-architect.md"},{"name":"Software Architect","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/engineering/engineering-software-architect.md"},{"name":"Test Automation Engineer","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/testing/testing-test-automation-engineer.md"},{"name":"Spatial Data Scientist","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/gis/gis-spatial-data-scientist.md"},{"name":"Language Translator","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/specialized/language-translator.md"},{"name":"Lingo.dev Internationalization","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/lingodotdev-i18n.agent.md"},{"id":"github-elasticsearch-observability","name":"GitHub Community Elasticsearch Observability Agent","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/agents/elasticsearch-observability.agent.md"},{"id":"agency-experiment-tracker","name":"Agency Experiment Tracker","reason":"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.","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/project-management/project-management-experiment-tracker.md"}],"records":[{"id":"github-accessibility","name":"Accessibility Expert","publisher":"github","category":"Accessibility","tags":["wcag","keyboard","aria","copilot","verification-steps"],"summary":"Guides web accessibility work through keyboard, focus, screen-reader, zoom and contrast checks, with developer examples and a structured review checklist.","why":"Operating rules require an a11y pre-check before code, verification steps with edits, and rejecting requests that remove focus outlines or otherwise reduce access.","limit":"The definition can edit files and run commands; it is broader than an advisory accessibility audit.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/accessibility.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-accessibility-runtime-tester","name":"Accessibility Runtime Tester","publisher":"github","category":"Accessibility","tags":["keyboard navigation","focus management","forms","browser evidence","accessibility"],"summary":"Exercises keyboard journeys, focus changes and form errors, then records reproducible accessibility findings and retest steps.","why":"Requires observed runtime behaviour and explicitly rejects a Lighthouse pass as proof of accessibility.","limit":"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.","compatibility":["GitHub Copilot custom agents in VS Code (tool adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Runtime browser inspection and local commands","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/accessibility-runtime-tester.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-adr-generator","name":"Adr Generator","publisher":"github","category":"Architecture and decisions","tags":["adr","docs-adr-path","template","no-tools-field","copilot-agent"],"summary":"Turns a concrete architecture decision into a numbered ADR with context, alternatives, consequences and references, asking for missing decision inputs first.","why":"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.","limit":"The /docs/adr/ path is ambiguous outside its expected project layout; choose an explicit repository-relative output directory before use.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/adr-generator.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"voltagent-memory-curator","name":"Agent Memory Curator","publisher":"VoltAgent","category":"Agent development","tags":["agent memory","corrections","provenance","retention","shared context"],"summary":"Maintains a confirmed agent memory store with dated facts, visible corrections and user-reviewed pruning proposals.","why":"Requires confirming the existing store rather than creating a competing memory system, and forbids storing secrets.","limit":"The file is a curation procedure, not a memory database, recall service or cross-session hook installer.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Existing memory-store curation","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/09-meta-orchestration/memory-curator.md","reviewedAt":"2026-09-21","sourceCount":3,"download":true,"hasConfig":false},{"id":"anthropic-agent-sdk-verifier-ts","name":"Agent Sdk Verifier Ts","publisher":"anthropics","category":"Agent development","tags":["claude-agent-sdk","typescript","claimed-tool-execution","no-tools-frontmatter","sonnet-pinned"],"summary":"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.","why":"Checklist is SDK-specific: package name, \"type\":\"module\", engines, MCP/subagent/permissions patterns, ANTHROPIC_API_KEY in .env.example and .env gitignore.","limit":"No tool allowlist is declared, so documentation retrieval and shell execution use inherited host permissions.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/agent-sdk-dev/agents/agent-sdk-verifier-ts.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"voltagent-knowledge-synthesizer","name":"Agent-Log Knowledge Synthesizer","publisher":"VoltAgent","category":"Agent development","tags":["agent logs","evidence synthesis","workflow learning","knowledge files"],"summary":"Finds recurring patterns in an explicitly scoped set of agent logs and writes cited findings with counts derived from the actual files.","why":"Stops on an empty or unspecified source scope and distinguishes recurring evidence from a single unconfirmed anecdote.","limit":"It cannot run analytics jobs or query remote services with its declared file tools; inputs must be accessible files.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Scoped file review and knowledge-file editing","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/09-meta-orchestration/knowledge-synthesizer.md","reviewedAt":"2026-09-21","sourceCount":3,"download":true,"hasConfig":false},{"id":"awslabs-aidlc-compliance","name":"AI-DLC Compliance Agent","publisher":"awslabs","category":"Security and governance","tags":["control mapping","data classification","privacy","evidence collection","risk tracking","AI-DLC"],"summary":"Organizes data classification, requirement-to-control mapping and compliance evidence into an advisory role within an AI-DLC project.","why":"Connects each proposed control to its technical implementation and required evidence such as logs, configuration and test results.","limit":"Requires the AI-DLC framework, active-space policies and resolved knowledge references; the raw persona download is not a complete installation.","compatibility":["AI-DLC Workflows (framework projection required)","Claude Code (AI-DLC project required)"],"language":[],"transports":[],"license":"MIT-0","access":"Project policy documents and web research","cost":"The definition is reusable under MIT-0. Host, model and any connected research services follow their own access and billing terms.","command":null,"installUrl":"https://github.com/awslabs/aidlc-workflows/blob/3e614b6e55963a2d2390c4d8b0877c5a8a33bb2f/docs/guide/18-install-and-lifecycle.md","sourceUrl":"https://github.com/awslabs/aidlc-workflows/blob/3e614b6e55963a2d2390c4d8b0877c5a8a33bb2f/core/agents/aidlc-compliance-agent.md","reviewedAt":"2026-09-21","sourceCount":6,"download":true,"hasConfig":false},{"id":"anthropic-architecture-critic","name":"Architecture Critic","publisher":"anthropics","category":"Architecture and decisions","tags":["architecture","modernization","adversarial-review","untrusted-input","read-only-intent"],"summary":"Challenges modernization designs and transformed code against actual requirements, failure paths and simpler alternatives, ending with prioritized actionable findings.","why":"Separate review lenses distinguish architecture proposals from already-transformed code.","limit":"Read-only shell use is an instruction; Bash remains available and must be constrained by the host.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/architecture-critic.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-business-rules-extractor","name":"Business Rules Extractor","publisher":"anthropics","category":"Modernization and specifications","tags":["legacy code","business rules","specifications","evidence"],"summary":"Extracts domain calculations, validation and policy rules from legacy code into concrete test scenarios with source references and uncertainty questions.","why":"Separates business rules from infrastructure behavior and requires exact code locations.","limit":"Observed legacy behavior is not automatically the business behavior that should be retained.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/business-rules-extractor.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-c4-context","name":"C4 System Context Documenter","publisher":"wshobson","category":"Architecture and decisions","tags":["C4","architecture documentation","system boundaries","Mermaid","user journeys"],"summary":"Synthesizes system and component documentation into a stakeholder-facing context diagram, actor list and external-dependency map.","why":"Defines a full c4-context.md output covering system purpose, personas, features, journeys and external systems.","limit":"Assumes container, component and system documentation are available; the file does not include those inputs or the other C4 agents.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Architecture inputs and context-document output","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/c4-architecture/agents/c4-context.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-code-architect","name":"Code Architect","publisher":"anthropics","category":"Architecture and decisions","tags":["architecture","implementation plans","data flow","Claude Code"],"summary":"Turns observed repository conventions into a concrete feature blueprint with file changes, interfaces, trade-offs and an implementation sequence.","why":"Requires existing patterns and conventions to be supported by file-and-line references before proposing a design.","limit":"The prompt asks for one decisive design; use another review process when competing designs or unresolved requirements need comparison.","compatibility":["Claude Code (frontmatter adjustment required)"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/feature-dev/agents/code-architect.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-code-explorer","name":"Code Explorer","publisher":"anthropics","category":"Codebase understanding","tags":["architecture","code navigation","dependencies","Claude Code"],"summary":"Traces an existing feature from entry points through state changes and storage, producing a source-linked map for the next developer.","why":"Requires call-chain and data-transformation tracing, so the output goes beyond a directory summary.","limit":"It produces an explanatory map rather than implementing changes or proving behavior with executed tests.","compatibility":["Claude Code (frontmatter adjustment required)"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/feature-dev/agents/code-explorer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-code-simplifier","name":"Code Simplifier","publisher":"anthropics","category":"Code maintenance","tags":["refactoring","readability","JavaScript","TypeScript","React","Claude Code"],"summary":"Refines recently changed code for clearer structure and naming while explicitly keeping its behavior and scope intact.","why":"Limits the default pass to code changed in the current session and explicitly prioritizes behavior preservation.","limit":"Its embedded coding preferences target JavaScript, TypeScript and React; they need review against other languages and the project’s own conventions.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"Apache-2.0","access":"Repository editing through host permissions","cost":"The definition is reusable under Apache-2.0. Claude Code access and model usage follow the user’s host plan or provider billing.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-simplifier/agents/code-simplifier.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-comment-analyzer","name":"Comment Analyzer","publisher":"anthropics","category":"Documentation","tags":["comments","docstrings","pull requests","code review"],"summary":"Checks comments and docstrings against implementation behavior, then separates factual errors, worthwhile improvements and obsolete explanations.","why":"Explicitly cross-checks signatures, side effects, error conditions and complexity claims against source code.","limit":"This is advisory review: the body explicitly forbids modifying code or comments.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/comment-analyzer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-data-engineer","name":"Data Engineer","publisher":"wshobson/agents","category":"Data and analytics","tags":["data-engineering","pipelines","streaming","data-quality"],"summary":"A broad design prompt for batch and streaming pipelines, data quality, schema evolution and operational handoffs.","why":"Covers failure handling, incremental processing and schema evolution alongside the happy-path transformation.","limit":"The file supplies instructions, not an executable pipeline or verified expertise across every listed cloud and engine.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed definition; model usage, database queries and infrastructure costs remain separate.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/data-engineering/agents/data-engineer.md","reviewedAt":"2026-09-22","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-database-optimizer","name":"Database Cloud Optimization Database Optimizer","publisher":"wshobson","category":"Data and retrieval","tags":["query-optimization","indexing","explain-analyze","caching","n+1"],"summary":"Investigates database bottlenecks from query plans and workload evidence, then proposes query, index, caching or partitioning changes with validation.","why":"Behavioral trait “Measures performance first using appropriate profiling tools before making optimizations” is the right order for this role.","limit":"This is an implementation-capable role and it declares no tool allowlist; database credentials and migration authority must be scoped in the host.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/database-cloud-optimization/agents/database-optimizer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-devils-advocate","name":"Devils Advocate","publisher":"github","category":"Architecture and decisions","tags":["devils-advocate","one-objection","end-game","role-switch","read-search-web"],"summary":"Stress-tests a proposal through one objection at a time, then switches to a balanced recap when the user ends the debate.","why":"A clear dialogue protocol keeps each challenge focused and gives the user an explicit way to stop adversarial mode.","limit":"It deliberately challenges rather than neutrally weighs a proposal during debate; use the final recap to recover balance.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/devils-advocate.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-devtools-regression-investigator","name":"Devtools Regression Investigator","publisher":"github","category":"Browser and performance","tags":["devtools-mcp","bug-report","no-fix-default","gpt-5","openSimpleBrowser"],"summary":"Reproduces browser regressions and links screenshots, console or network evidence to likely code paths, returning a structured bug report before any requested fix.","why":"The file forbids declaring root cause without browser evidence or code correlation, and forbids treating a flaky repro as solved.","limit":"Chrome DevTools MCP and optional Playwright are described but not installed or explicitly named in the tool allowlist; configure the required browser tools separately.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/devtools-regression-investigator.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-docs-architect","name":"Documentation Generation Docs Architect","publisher":"wshobson","category":"Documentation","tags":["architecture-docs","markdown","codebase-analysis","long-form"],"summary":"Builds a structured architecture manual from an existing codebase, covering design rationale, component interactions, operational behavior and paths into the source.","why":"Output contract is specific: Markdown, heading hierarchy, code blocks, tables, links as file_path:line_number, 10-section skeleton.","limit":"The source favors extensive manuals; choose a bounded audience and scope to avoid documentation that is costly to maintain.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/documentation-generation/agents/docs-architect.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-event-sourcing-architect","name":"Event Sourcing Architect","publisher":"wshobson","category":"Architecture and decisions","tags":["event sourcing","CQRS","sagas","schema evolution"],"summary":"Plans event-sourced systems through aggregate boundaries, immutable event records, projections, sagas and event-versioning decisions.","why":"Covers the practical linkage between command handling, read projections and cross-aggregate workflows.","limit":"The role assumes event sourcing is appropriate; it does not compare simpler persistence designs first.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/backend-development/agents/event-sourcing-architect.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"ecc-fastapi-reviewer","name":"FastAPI Reviewer","publisher":"affaan-m","category":"Testing and review","tags":["FastAPI","Python","async correctness","Pydantic","API review"],"summary":"Reviews FastAPI changes for async blocking, dependency wiring, schema exposure and test setup, with file references and explicit unverified risks.","why":"Focuses on framework-specific failure modes such as blocking clients in async routes, incorrect test overrides and sensitive response fields.","limit":"Its severity checklist includes architectural preferences that require context; an inline database session is not automatically a demonstrated vulnerability.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Python source review and local checks","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/bf70150eb2df8070024e5bdf08e4aa08959e2735/agents/fastapi-reviewer.md","reviewedAt":"2026-09-21","sourceCount":3,"download":true,"hasConfig":false},{"id":"agency-product-feedback-synthesizer","name":"Feedback Synthesizer","publisher":"msitarzewski","category":"Research and product","tags":["customer-feedback","thematic-analysis","product-research","prioritization"],"summary":"Organizes a supplied customer-feedback corpus into themes, product priorities and audience-specific reports for product and support teams.","why":"Specifies separate executive, product-team and customer-success deliverables rather than one undifferentiated summary.","limit":"The definition's accuracy, growth and service-level targets are aspirations; none were demonstrated by this source review.","compatibility":["Claude Code (frontmatter adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/product/product-feedback-synthesizer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-frontend-performance-investigator","name":"Frontend Performance Investigator","publisher":"github","category":"Browser and performance","tags":["core-web-vitals","lighthouse","devtools","frontend","traces"],"summary":"Diagnoses a specific slow web flow from traces, network activity and code paths, then produces prioritized fixes with a validation method for each.","why":"Requires a concrete reproduction path and recorded environment assumptions before recommending optimizations.","limit":"Chrome DevTools MCP and the optional Playwright fallback require separate configuration; neither is explicitly included in this file’s tool allowlist.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/frontend-performance-investigator.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"trailofbits-function-analyzer","name":"Function Analyzer","publisher":"Trail of Bits (Omar Inuwa)","category":"Codebase understanding","tags":["audit preparation","invariants","call chains","source evidence","Claude Code"],"summary":"Builds a line-cited account of one function’s invariants, assumptions and callee dependencies before a later security review.","why":"Requires reading callees and their branches before treating a precondition as enforced; function names are explicitly insufficient evidence.","limit":"The file requires sibling analysis formats and domain references plus a resolved {baseDir}; the download alone does not install the plugin.","compatibility":["Claude Code (plugin resources required)"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Repository reading and analysis-file writes","cost":"The unchanged definition is reusable under CC-BY-SA-4.0 with attribution; shared adaptations have licence obligations. Host and model usage may incur charges.","command":null,"installUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/audit-context-building/README.md","sourceUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/audit-context-building/agents/function-analyzer.md","reviewedAt":"2026-09-21","sourceCount":6,"download":true,"hasConfig":false},{"id":"github-github-actions-expert","name":"Github Actions Expert","publisher":"github","category":"Infrastructure and delivery","tags":["github-actions","supply-chain","oidc","sha-pinning","least-privilege"],"summary":"Designs and reviews GitHub Actions workflows around minimal token permissions, immutable action references, OIDC, deployment concurrency and validation.","why":"Action pinning section forbids `@main`/`@latest`/moving tags, requires full commit SHA plus a version comment, and explains tag-move supply-chain risk.","limit":"The GitHub tool wildcard and terminal access can perform repository actions; the definition itself does not enforce a read-only review.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/github-actions-expert.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"ecc-harness-optimizer","name":"Harness Optimizer","publisher":"affaan-m","category":"Agent development","tags":["eval-harness","hooks","pass-at-k","restore-on-fail","repo-scripts"],"summary":"Tunes agent configuration with an explicit evaluation definition, repeated trials, baseline checks and rollback instructions for failed experiments.","why":"Explicit non-goals: no product-code rewrites; no slash-command invocation; run node scripts/harness-audit.js instead.","limit":"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.","compatibility":["Claude Code (frontmatter adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/harness-optimizer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-team-debugger","name":"Hypothesis Debugging Investigator","publisher":"wshobson","category":"Testing and review","tags":["hypothesis testing","debugging","agent teams","counterevidence","causal chains"],"summary":"Investigates one assigned bug hypothesis and sends the team lead a cited account of supporting evidence, contradictions and remaining gaps.","why":"Defines confirmation, falsification and ambiguous evidence before investigation, reducing one-sided hypothesis confirmation.","limit":"Depends on a lead and the host’s messaging/task tools. The single file does not create a team or an orchestration workflow.","compatibility":["Claude Code (agent-team setup required)"],"language":[],"transports":[],"license":"MIT","access":"Source investigation and team-message tools","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/agent-teams/agents/team-debugger.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-se-ux-designer","name":"Jobs-to-be-Done UX Planner","publisher":"github","category":"Research and product","tags":["UX planning","jobs to be done","journey maps","design handoff","personas"],"summary":"Turns user context and jobs to be done into a journey map, flow specification and design handoff documents.","why":"Starts by asking about users, context and pain points instead of treating a requested interface feature as the underlying goal.","limit":"The agent drafts research artifacts; it does not conduct interviews, validate personas or create Figma designs.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Research documents and design-handoff files","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/se-ux-ui-designer.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-legacy-analyst","name":"Legacy Analyst","publisher":"anthropics","category":"Codebase understanding","tags":["legacy systems","dependency maps","uncertainty","modernization"],"summary":"Builds an evidence-linked account of an unfamiliar legacy system by tracing entry points, stable data structures and actual control flow.","why":"Requires source citations and explicitly distinguishes observed behavior from inferred intent.","limit":"The role is an analyst, not a migration implementer or an executable behavior test.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/legacy-analyst.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-markdown-accessibility-assistant","name":"Markdown Accessibility Assistant","publisher":"github","category":"Accessibility","tags":["markdown","accessibility","markdownlint","human-approval","copilot-agent"],"summary":"Reviews existing Markdown for accessible headings, links, lists and image descriptions, while reserving meaning-changing rewrites for human approval.","why":"Mission forbids generating docs from scratch and limits work to improving existing markdown, which is a real role boundary.","limit":"The scope is selected Markdown accessibility practices, not full web accessibility conformance.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/markdown-accessibility-assistant.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-mongodb-performance-advisor","name":"MongoDB Performance Advisor","publisher":"github","category":"Data and retrieval","tags":["MongoDB","query plans","indexes","performance","MCP"],"summary":"Combines repository query patterns with read-only MongoDB diagnostics to explain query plans and index trade-offs.","why":"Stops when a read-only MongoDB MCP connection is unavailable instead of fabricating database observations.","limit":"Requires the MongoDB MCP server configured read-only; Atlas Performance Advisor also needs the appropriate account access.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Read-only MongoDB diagnostics through MCP","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/mongodb-performance-advisor.agent.md","reviewedAt":"2026-09-21","sourceCount":6,"download":true,"hasConfig":false},{"id":"github-neon-migration-specialist","name":"Neon Migration Specialist","publisher":"github","category":"Modernization and specifications","tags":["Neon","PostgreSQL","database migrations","database branches","ORM"],"summary":"Tests schema changes on a temporary Neon database branch and prepares migration files for a separate production rollout.","why":"Explicitly forbids running migrations on the main Neon database branch and separates database branches from Git branches.","limit":"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.","compatibility":["GitHub Copilot custom agents in VS Code (workflow adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Temporary database branch and repository writes","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/neon-migration-specialist.agent.md","reviewedAt":"2026-09-21","sourceCount":7,"download":true,"hasConfig":false},{"id":"wshobson-observability-engineer","name":"Observability Engineer","publisher":"wshobson/agents","category":"Operations and reliability","tags":["observability","slo","telemetry","incident-response"],"summary":"A planning prompt for telemetry coverage, service objectives, alert design and incident runbooks.","why":"Connects metrics, logs and traces with service-level indicators and actionable incident response.","limit":"This is a broad instruction profile, not an installed collector, dashboard, integration or compliance control.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed definition; model usage, database queries and infrastructure costs remain separate.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/observability-monitoring/agents/observability-engineer.md","reviewedAt":"2026-09-22","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-uplift-migrator","name":"Pilot-Driven Uplift Migrator","publisher":"anthropics","category":"Modernization and specifications","tags":["version upgrades","pilot playbook","minimal changes","build verification","parallel work"],"summary":"Applies a proven version-upgrade playbook to one module, keeping edits within that unit and reporting its actual build result and playbook gaps.","why":"Stops without editing when the pilot playbook is missing, preventing a worker from improvising an untested migration approach.","limit":"Requires a completed pilot, analysis/<system>/PLAYBOOK.md, DELTA_CATALOG.md and a designated module in the modernization working copy.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"Apache-2.0","access":"One migration unit and its local build","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/uplift-migrator.md","reviewedAt":"2026-09-21","sourceCount":3,"download":true,"hasConfig":false},{"id":"github-playwright-tester","name":"Playwright Test Explorer","publisher":"github","category":"Testing and review","tags":["Playwright","browser testing","test generation","TypeScript","MCP"],"summary":"Explores a working interface through Playwright before generating and running TypeScript tests for its observed user flows.","why":"Prohibits writing test code until the agent has navigated the interface and identified its actual flows.","limit":"Requires a configured Playwright MCP connection and a reachable application; the file does not install a browser server or the test framework.","compatibility":["GitHub Copilot custom agents in VS Code (tool adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Browser automation and test-file changes","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/playwright-tester.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-pr-test-analyzer","name":"Pull Request Test Analyzer","publisher":"anthropics","category":"Testing and review","tags":["tests","pull requests","regressions","behavioral coverage"],"summary":"Maps a pull request to its tests and identifies meaningful missing failure cases, brittle assertions and uncovered behavioral contracts.","why":"Prioritizes tests by concrete regressions they would prevent rather than chasing line coverage.","limit":"Its internal numerical criticality rubric is a prioritization instruction, not a measured quality score or a catalogue rating.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/pr-test-analyzer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-qa-subagent","name":"QA Test Planner and Investigator","publisher":"github","category":"Testing and review","tags":["QA","test planning","exploratory testing","requirements","bug reports"],"summary":"Builds a requirement-linked test plan, explores failure paths and reports reproducible bugs separately from potential improvements.","why":"Organizes tests by boundary, negative, failure, concurrency and security cases, then prioritizes by risk.","limit":"It grants broad edit, execute, delegation and web tool categories; the role’s focus is not a technical read-only restriction.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Repository editing and local test execution","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/qa-subagent.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"ecc-rag-pipeline-reviewer","name":"Rag Pipeline Reviewer","publisher":"affaan-m","category":"Data and retrieval","tags":["rag","reranking","ragas","approve-block","read-mostly"],"summary":"Reviews retrieval pipelines for grounding, pruning, fallback behavior and evaluation policy, returning a structured approval, conditional approval or block decision.","why":"Role boundary is negative as well as positive: do not rewrite the LLM answer prompt; hand off to named specialists.","limit":"The read-only Bash rule is an instruction; the host must enforce the intended access boundary.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/rag-pipeline-reviewer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"voltagent-readme-generator","name":"Readme Generator","publisher":"VoltAgent","category":"Documentation","tags":["readme","documentation","repository-analysis","developer-experience"],"summary":"Builds a repository README from inspected manifests, scripts, tests and entry points, explicitly rejecting guessed commands, APIs and configuration.","why":"Requires setup commands, configuration and usage examples to be extracted from actual repository evidence.","limit":"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.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/VoltAgent/awesome-claude-code-subagents/blob/82b73821baa7a911d5b14cfb6da238b7f0db6b42/categories/06-developer-experience/readme-generator.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"agency-research-synthesist","name":"Research Synthesist","publisher":"msitarzewski","category":"Research and product","tags":["literature review","source quality","citations","evidence gaps"],"summary":"Builds an auditable synthesis that traces repeated claims to their origin and separates independent agreement, disagreement and missing evidence.","why":"Explicitly rejects counting repeated citations to one study as independent corroboration.","limit":"The original frontmatter name and hex color need adaptation to the current Claude Code field rules before loading a working copy.","compatibility":["Claude Code (frontmatter adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/research/research-synthesist.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-scaffolder","name":"Scaffolder","publisher":"anthropics","category":"Modernization and specifications","tags":["modernization","scaffolding","acceptance-tests","write-scope","untrusted-input"],"summary":"Creates one modernization service from an approved architecture and specification, including its domain model, API stubs and rule-linked acceptance tests.","why":"Limits the intended work to one caller-selected service directory so independently scaffolded services do not overwrite one another.","limit":"Requires REIMAGINED_ARCHITECTURE.md, AI_NATIVE_SPEC.md and the caller’s modernized service path; the complete modernization workflow is not included.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/scaffolder.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-se-responsible-ai-code","name":"Se: Responsible Ai","publisher":"github","category":"Security and governance","tags":["bias","privacy","accessibility","adr-writing","copilot"],"summary":"Screens user-facing changes for accessibility, privacy and exclusion concerns, then documents decisions and escalation needs in numbered responsible-AI records.","why":"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.","limit":"The illustrative name and demographic examples are screening prompts, not validated fairness tests or a compliance assessment.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/se-responsible-ai-code.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-se-technical-writer","name":"Se: Tech Writer","publisher":"github","category":"Documentation","tags":["technical-writing","templates","adr","tutorials","copilot"],"summary":"Turns code and design context into audience-specific documentation, tutorials, articles and decision records using explicit structures and a verification checklist.","why":"Content-type templates are fully specified, including ADR status/deciders/consequences/alternatives and task-oriented user-guide workflows with verification checkpoints.","limit":"The frontmatter permits file editing and web retrieval but does not name an execution tool; testing or compiling examples needs a separate runner.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/se-technical-writer.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-security-auditor","name":"Security Auditor","publisher":"anthropics","category":"Security and governance","tags":["application-security","owasp","cwe","secrets","untrusted-input"],"summary":"Reviews application code with a stack-specific security checklist, requiring source locations, exploit scenarios, concrete remediation and masked secrets in each finding.","why":"Demands a plausible exploit scenario and a concrete code-level fix rather than unsupported vulnerability labels.","limit":"Bash and package auditors depend on host permissions and tool availability; the definition does not enforce its read-only boundary.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/security-auditor.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"agency-spatial-data-engineer","name":"Spatial Data Engineer","publisher":"Agency Agents","category":"Data and analytics","tags":["geospatial","etl","crs","data-validation"],"summary":"A geospatial ETL planning prompt centered on source preservation, explicit coordinate systems and transformation checks.","why":"Requires original files to be preserved and transformations to write to a new location.","limit":"The original frontmatter name contains spaces. Create a host-valid name in your working copy; this download remains byte-identical to upstream.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed prompt; GIS software licensing, source-data terms, agent usage and hosted processing are separate.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/gis/gis-spatial-data-engineer.md","reviewedAt":"2026-09-22","sourceCount":4,"download":true,"hasConfig":false},{"id":"ecc-spec-miner","name":"Spec Miner","publisher":"affaan-m","category":"Modernization and specifications","tags":["openspec","brownfield","requirements","invariants","write-allowlist"],"summary":"Extracts a selected brownfield capability into source-linked OpenSpec requirements and invariants while limiting writes to the specification directory.","why":"Write may only create openspec/specs/<capability>/spec.md; Bash must stay read-only—rare path-scoped reviewer-writer.","limit":"Its output is tailored to OpenSpec; a different specification workflow requires adaptation.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/spec-miner.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"trailofbits-spec-compliance-checker","name":"Specification-to-Code Checker","publisher":"Trail of Bits (Omar Inuwa)","category":"Testing and review","tags":["specifications","requirements","call chains","source evidence","documentation drift","Claude Code"],"summary":"Checks one quoted requirement against its implementation paths and records the enforcement evidence, gaps and unresolved questions.","why":"Separates implemented, partially enforced, contradicted, absent, stronger-than-specified and undecidable requirements instead of forcing a binary pass/fail.","limit":"The file requires the plugin’s sibling analysis format and domain references; {baseDir} must resolve before use.","compatibility":["Claude Code (plugin resources required)"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Repository reading and analysis-file writes","cost":"The unchanged definition is reusable under CC-BY-SA-4.0 with attribution; shared adaptations have licence obligations. Host and model usage may incur charges.","command":null,"installUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/spec-to-code-compliance/README.md","sourceUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/spec-to-code-compliance/agents/spec-compliance-checker.md","reviewedAt":"2026-09-21","sourceCount":6,"download":true,"hasConfig":false},{"id":"wshobson-sql-pro","name":"SQL Pro","publisher":"wshobson/agents","category":"Data and analytics","tags":["sql","query-plans","indexes","database-design"],"summary":"A SQL review prompt covering query plans, schema design, indexing and read/write performance tradeoffs.","why":"Asks for usage patterns and realistic data before treating an index or rewrite as an optimization.","limit":"SQL features and tuning advice are not portable across all named engines. Supply the exact engine, version, schema and workload.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed definition; model usage, database queries and infrastructure costs remain separate.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/database-design/agents/sql-pro.md","reviewedAt":"2026-09-22","sourceCount":4,"download":true,"hasConfig":false},{"id":"agency-statistician","name":"Study Design and Evidence Statistician","publisher":"msitarzewski","category":"Research and product","tags":["study design","statistics","causal inference","uncertainty","evidence review"],"summary":"Examines the chain from research question and measurement to comparison, analysis and decision, making assumptions and uncertainty explicit.","why":"Separates descriptive, predictive and causal questions before choosing a study or interpreting a result.","limit":"The prompt does not supply data, a statistical runtime or a validated analysis package. Calculations require suitable tools and reproducible inputs.","compatibility":["Claude Code (frontmatter adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Study-design review and configured analysis tools","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/msitarzewski/agency-agents/blob/87f8301cad3823a9a34d762036ae923a0eff306f/academic/academic-statistician.md","reviewedAt":"2026-09-21","sourceCount":3,"download":true,"hasConfig":false},{"id":"svelte-file-editor","name":"Svelte File Editor","publisher":"Svelte","category":"Framework development","tags":["svelte","components","documentation","static-analysis"],"summary":"A focused Svelte editing prompt that consults current documentation and iterates with the Svelte MCP static checker.","why":"Separates Svelte component work into a focused agent context with relevant documentation.","limit":"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.","compatibility":["Claude Code"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed definition; agent usage and any project tooling compute remain separate.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents","sourceUrl":"https://github.com/sveltejs/ai-tools/blob/5c15fbcb5b630ac8ce0281ee1782fc2056fab853/tools/agents/svelte-file-editor.md","reviewedAt":"2026-09-22","sourceCount":6,"download":true,"hasConfig":false},{"id":"github-debug-mode","name":"Systematic Debugging","publisher":"github","category":"Testing and review","tags":["debugging","reproduction","root cause","regression tests"],"summary":"Reproduces an application bug, tests root-cause hypotheses and verifies a minimal fix against the original failure.","why":"Requires reproduction and an expected-versus-actual report before changing code.","limit":"The procedure is a general debugging framework, so the caller must provide a concrete symptom and a usable reproduction environment.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Repository editing and local test execution","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/debug.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-research-technical-spike","name":"Technical Spike Research Mode","publisher":"github","category":"Research and product","tags":["spike","documentation","experimentation","mcp","vscode"],"summary":"Investigates a supplied technical-spike document through cited documentation, repository examples and separately approved experiments, recording findings and dead ends as work proceeds.","why":"Stops when no spike document is provided and ties the work to explicit research questions and success criteria.","limit":"The recursive research policy has no fixed time or cost budget; define a stopping condition for the chosen spike.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/research-technical-spike.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-terraform-iac-reviewer","name":"Terraform Iac Reviewer","publisher":"github","category":"Infrastructure and delivery","tags":["terraform","iac-review","state-safety","plan-apply","secrets"],"summary":"Reviews and drafts Terraform changes with a plan summary, impact assessment, validation sequence, approval before apply, and an explicit recovery discussion.","why":"Every change must include plan summary (add/change/destroy counts), risk assessment, validation commands, and a rollback strategy.","limit":"Terminal and editing access can change infrastructure. Approval before apply is an instruction, not an enforced host permission boundary.","compatibility":["GitHub Copilot custom agents in VS Code"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.visualstudio.com/docs/copilot/customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/terraform-iac-reviewer.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"github-terratest-module-testing","name":"Terratest Module Testing","publisher":"github","category":"Infrastructure and delivery","tags":["Terraform","Terratest","Go","negative-path tests","CI"],"summary":"Designs Terraform module tests around outputs, validation failures and isolated setup and cleanup, with cloud applies explicitly gated.","why":"Distinguishes success paths, expected failures and staged integration tests rather than treating every module test as a deployment.","limit":"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.","compatibility":["GitHub Copilot custom agents in VS Code (tool adjustment required)"],"language":[],"transports":[],"license":"MIT","access":"Go tests, Terraform commands and optional cloud resources","cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","command":null,"installUrl":"https://code.visualstudio.com/docs/agent-customization/custom-agents","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/terratest-module-testing.agent.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-test-engineer","name":"Test Engineer","publisher":"anthropics","category":"Testing and review","tags":["characterization-tests","legacy-oracle","dual-run-harness","secret-substitution","untrusted-source"],"summary":"Writes characterization tests and dual-run harnesses that pin legacy behavior before modernization, preserving unresolved target behavior as explicitly pending tests.","why":"The body pins tests to literal inputs/outputs and dual-run comparison against legacy or a recorded trace, not to spec-as-intent.","limit":"Frontmatter grants Write, Edit, and unrestricted Bash; the modernized/-only and never-edit-legacy/ rules are prompt text, not a sandbox.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/test-engineer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-threat-modeling-expert","name":"Threat Modeling Expert","publisher":"wshobson","category":"Security and governance","tags":["threat modeling","STRIDE","trust boundaries","attack trees"],"summary":"Structures a security design review around trust boundaries, data flows, attack paths, mitigations and residual risks.","why":"Provides a concrete sequence from scope and assets through STRIDE and attack trees to documented residual risk.","limit":"This is a design-review role, not a scanner, penetration test or compliance certificate.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/security-scanning/agents/threat-modeling-expert.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-type-design-analyzer","name":"Type Design Analyzer","publisher":"anthropics","category":"Testing and review","tags":["invariants","encapsulation","pr-review","numeric-rubric","domain-modeling"],"summary":"Reviews domain types by identifying their invariants, checking where those invariants are enforced, and weighing safer designs against complexity and compatibility.","why":"Fixed per-type report: invariants list, four rated axes with justification, Strengths, Concerns, Recommended Improvements.","limit":"Its numerical design rubric is subjective guidance, not a measured quality score or compiler result.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/type-design-analyzer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"wshobson-vector-database-engineer","name":"Vector Database Engineer","publisher":"wshobson","category":"Data and retrieval","tags":["vector-db","embeddings","hybrid-search","rag-implementation","voyage-ai"],"summary":"Plans and implements semantic retrieval systems through corpus analysis, embeddings, chunking, index selection, hybrid search, reranking and monitoring.","why":"Workflow is requirement→embedding→chunk→store→index→hybrid→rerank→monitor, which is a real RAG build path.","limit":"The broad implementation role declares no tool allowlist; access to databases, credentials and file changes comes from the host.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"MIT","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/llm-application-dev/agents/vector-database-engineer.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false},{"id":"anthropic-version-delta-analyst","name":"Version Delta Analyst","publisher":"anthropics","category":"Modernization and specifications","tags":["version-uplift","breaking-changes","delta-catalog","report-mode-tools","read-only-instruction"],"summary":"Maps a same-stack version upgrade to the breaking and behavioral changes the actual codebase encounters, distinguishing available tooling from tooling that was run.","why":"It forbids folding analyzer output into the catalog unless the tool actually ran, and records coverage-lost when restore/network is missing.","limit":"Body says read-only; frontmatter still grants Bash (no Write/Edit). upgrade-assistant and ng update are described as in-place editors—obedience is the only brake.","compatibility":["Claude Code subagents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Host-mediated repository and tool access","cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","command":null,"installUrl":"https://code.claude.com/docs/en/sub-agents.md","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/version-delta-analyst.md","reviewedAt":"2026-09-21","sourceCount":4,"download":true,"hasConfig":false}]}