---
title: "Review governance policy author: review, role & definition · Undominated.ai"
canonical: https://undominated.ai/agents/wshobson-review-policy-author/
description: "A policy-authoring component for identifying which review, merge and CI-edit commands need an approval gate."
---

# Review governance policy author: review, role & definition · Undominated.ai

> A policy-authoring component for identifying which review, merge and CI-edit commands need an approval gate.

[← Explore all agents](/agents/)

SECURITY WORKFLOW COMPONENTS / Seth Hobson

# Review governance policy author

A policy-authoring component for identifying which review, merge and CI-edit commands need an approval gate.

 [Use this definition ↓](#setup)[Original source ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/agents/review-policy-author.md)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 7 linked sources
 Publisher Seth Hobson
 Licence [MIT ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE)
 Revision 46891e7e60da
 [Read what was—and wasn’t—checked ↓](#review)

“Cedar policy author specialized in gating AI agent review actions (PR comments, reviews, merges, CI edits) behind human approval. Use when writing, auditing, or extending a review-governance.cedar policy for review-bot governance.”

 [Seth Hobson · upstream description ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/agents/review-policy-author.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - It distinguishes raw-command substring matching from reliable identity or semantic authorization: no human_approved attribute is available.
- It calls out bare-push upstream ambiguity, conservative gh api blocking and side-effecting GET endpoints that require another control.

### A good fit for

 - Supply the actual review tools, protected branches, CI paths and default Cedar policy.
- Receive explicit forbid-rule proposals and documented coverage gaps.

### Weigh up before choosing

 - The approval flag bypasses policy until removed; a writable flag is not independently verified human approval. String matching can be bypassed, and the plugin deliberately permits some other public writes.
- Source-only component: inspect its upstream context and dependencies before adapting it; no standalone runnable bundle is offered.
- The inspected evaluate.sh allows every tool call when the configured policy file is absent, and skips policy while the approval flag exists. Verify both conditions before relying on the gate.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/review-agent-governance/agents/review-policy-author.md (pinned complete source retained)
- LICENSE
- Repository README and current official host configuration documentation
- plugins/review-agent-governance/README.md
- plugins/review-agent-governance/hooks/hooks.json
- plugins/review-agent-governance/hooks/evaluate.sh
- plugins/review-agent-governance/policies/review-agent-governance.cedar

### Our findings

 - It distinguishes raw-command substring matching from reliable identity or semantic authorization: no human_approved attribute is available.
- It calls out bare-push upstream ambiguity, conservative gh api blocking and side-effecting GET endpoints that require another control.

### Not established by this review

 - Source review only: no agent was installed or invoked. Task correctness, effective host restrictions and integration behaviour were not tested.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Use the role in your project.

[Upstream setup instructions ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/agents/review-policy-author.md)
 - Read the pinned source and its licence, then configure an explicitly bounded host context.
- Adapt with the matching policy and hook code, isolate approval-state writes, and review both false positives and bypass paths before enabling enforcement.
- Supply the actual review tools, protected branches, CI paths and default Cedar policy.

### Before you start

 - Matching review-agent-governance plugin and Cedar policy
- protect-mcp runtime and explicitly controlled approval state

### Compatibility

Claude Code

### Implementation

Markdown

### Host-mediated agent profile

 - No tools allowlist is declared. Claude Code can inherit or expose the host’s available tools by default; restrict file, shell and network access in the host.

### Cost model

The definition has the stated open-source licence. Model/host usage and any connected service or execution environment can incur separate costs.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Pinned upstream agent definition ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/agents/review-policy-author.md) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/agents/review-policy-author.md Supports: Workflow, inputs, outputs and stated boundaries
- [Applicable licence ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE Supports: Redistribution and attribution
- [Host configuration and tool inheritance ↗](https://code.claude.com/docs/en/sub-agents.md) Checked 2026-10-14 https://code.claude.com/docs/en/sub-agents.md Supports: Host loading and effective permission boundaries
- [Pinned inspected source: plugins/review-agent-governance/README.md ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/README.md) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/README.md Supports: Dependency setup and source-review boundary
- [Pinned inspected source: plugins/review-agent-governance/hooks/hooks.json ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/hooks/hooks.json) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/hooks/hooks.json Supports: Dependency setup and source-review boundary
- [Pinned inspected source: plugins/review-agent-governance/hooks/evaluate.sh ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/hooks/evaluate.sh) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/hooks/evaluate.sh Supports: Dependency setup and source-review boundary
- [Pinned inspected source: plugins/review-agent-governance/policies/review-agent-governance.cedar ↗](https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/policies/review-agent-governance.cedar) Checked 2026-10-14 https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/policies/review-agent-governance.cedar Supports: Dependency setup and source-review boundary

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Claude Security code explorer ↗ A Claude Security search component that maps one code path for a caller and returns file/line evidence.](/agents/anthropic-explore/)[### Claude Security patch generator ↗ A security-fix component that stages one narrow change in an orchestrator-created scratch checkout.](/agents/anthropic-patch-generator/)[### Claude Security patch verifier ↗ A security-patch verifier that derives the staged diff and separates tested behavior from source-only confidence.](/agents/anthropic-patch-verifier/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
