Review a proposed AI-agent action or human-approval packet before execution. Use when an agent wants to run a consequential tool, command, deployment, message, purchase, credential operation, or data mutation; when checking whether approval still matches the exact action; or when auditing action evidence for forged results, parameter swaps, replay, correlated reviewers, missing evidence, expiry…
Install
npx skills add github/awesome-copilot --skill verify-agent-actionnpx skills add github/awesome-copilot --skill verify-agent-action -a claude-code -gnpx skills add github/awesome-copilot --skill verify-agent-action -a codex -ggemini skills install https://github.com/github/awesome-copilot.git --path skills/verify-agent-actiongh skill install github/awesome-copilot verify-agent-actiongit 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/verify-agent-action ~/.claude/skills/verify-agent-action # Claude Code
cp -R /tmp/github__awesome-copilot/skills/verify-agent-action ~/.agents/skills/verify-agent-action # Codex, Cursor, Gemini CLI, Copilot, OpenCode