본문으로 건너뛰기
이 콘텐츠는 아직 사용자의 언어로 제공되지 않아 영어로 표시됩니다.

Review Agent Governance

Plugin 확인됨
95

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI configuration. Joins protect-mcp and signed-audit-trails in the governance category; composes with protect-mcp for runtime enforcement.

AI 요약

It enforces approval for PR reviews, comments, merges, and CI configuration changes using Cedar policies and generates cryptographically signed receipts for every action. The plugin includes commands to approve actions and list denied attempts, with clear documentation on setup and verification.

Invocation

  • warning:Hook matcher tightnessThe 'PreToolUse' and 'PostToolUse' hooks both use a 'matcher: "*"', which applies the hook to every tool call, potentially impacting performance and indicating a lack of fine-grained scoping where possible.

설치

먼저 마켓플레이스를 추가하세요

/plugin marketplace add wshobson/agents
/plugin install review-agent-governance@claude-code-workflows
7 days ago에 업데이트됨
소스 코드 보기