← Explore all 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.

“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.”

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.

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 ↗
  1. Read the pinned source and its licence, then configure an explicitly bounded host context.
  2. Adapt with the matching policy and hook code, isolate approval-state writes, and review both false positives and bypass paths before enabling enforcement.
  3. 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

04 / FOLLOW THE EVIDENCE

The source trail.

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

  1. https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/agents/review-policy-author.md

    Supports: Workflow, inputs, outputs and stated boundaries

  2. Applicable licence ↗Checked

    https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/LICENSE

    Supports: Redistribution and attribution

  3. https://code.claude.com/docs/en/sub-agents.md

    Supports: Host loading and effective permission boundaries

  4. https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/README.md

    Supports: Dependency setup and source-review boundary

  5. https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/hooks/hooks.json

    Supports: Dependency setup and source-review boundary

  6. https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/hooks/evaluate.sh

    Supports: Dependency setup and source-review boundary

  7. https://github.com/wshobson/agents/blob/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/review-agent-governance/policies/review-agent-governance.cedar

    Supports: Dependency setup and source-review boundary

Evidence & Ask