review-agent-governance
This Claude Code plugin gates AI agent actions on PR reviews, comments, merges, and CI config writes behind mandatory human approval, using Cedar policies and Ed25519-signed receipts to prevent unvetted automated changes. It intercepts tool calls via PreToolUse and PostToolUse hooks, blocking sensitive GitHub and GitLab operations unless an approval flag is set or the `/approve-review` slash command is used.
Install
Source: https://github.com/wshobson/agents/tree/HEAD/plugins/review-agent-governance
What it's made of
2 commands · 1 agent · 1 skill · 2 hooks
- Commands
- 2
- Agents
- 1
- Skills
- 1
- MCP servers
- 0
- Hooks
- 2 · PostToolUse, PreToolUse
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
evaluate.shsign.sh- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (wshobson).