Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building…
Install
npx skills add github/awesome-copilot --skill agent-governancenpx skills add github/awesome-copilot --skill agent-governance -a claude-code -gnpx skills add github/awesome-copilot --skill agent-governance -a codex -ggemini skills install https://github.com/github/awesome-copilot.git --path skills/agent-governancegh skill install github/awesome-copilot agent-governancegit clone --depth 1 https://github.com/github/awesome-copilot /tmp/github__awesome-copilot
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/github__awesome-copilot/skills/agent-governance ~/.claude/skills/agent-governance # Claude Code
cp -R /tmp/github__awesome-copilot/skills/agent-governance ~/.agents/skills/agent-governance # Codex, Cursor, Gemini CLI, Copilot, OpenCode