review-agent-governance

v0.1.1

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.

CodexClaude Code1 skill

by Tom FarleyMIT38.6kupdated 4 days ago

Source

$ git clone https://github.com/wshobson/agents

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is plugins/review-agent-governance/ inside the repository.

Layout

plugins/review-agent-governance/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/review-agent-setup/SKILL.md

Skills1

review-agent-setupskills/review-agent-setup/SKILL.md

Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.

Manifests2

plugins/review-agent-governance/.codex-plugin/plugin.json

{
  "name": "review-agent-governance",
  "version": "0.1.1",
  "description": "Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.",
  "skills": "./skills/",
  "author": {
    "name": "Tom Farley",
    "email": "tommy@scopeblind.com"
  },
  "license": "MIT",
  "interface": {
    "displayName": "Review Agent Governance",
    "shortDescription": "Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config…",
    "category": "Coding"
  }
}

plugins/review-agent-governance/.claude-plugin/plugin.json

{
  "name": "review-agent-governance",
  "version": "0.1.1",
  "description": "Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.",
  "author": {
    "name": "Tom Farley",
    "email": "tommy@scopeblind.com"
  },
  "license": "MIT"
}