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.
安装
npx skills add wshobson/agents --skill review-agent-setupnpx skills add wshobson/agents --skill review-agent-setup -a claude-code -gnpx skills add wshobson/agents --skill review-agent-setup -a codex -ggemini skills install https://github.com/wshobson/agents.git --path plugins/review-agent-governance/skills/review-agent-setupgh skill install wshobson/agents review-agent-setupgit clone --depth 1 https://github.com/wshobson/agents /tmp/wshobson__agents
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/wshobson__agents/plugins/review-agent-governance/skills/review-agent-setup ~/.claude/skills/review-agent-setup # Claude Code
cp -R /tmp/wshobson__agents/plugins/review-agent-governance/skills/review-agent-setup ~/.agents/skills/review-agent-setup # Codex, Cursor, Gemini CLI, Copilot, OpenCode