[experimental] Evaluate deployment risk by analyzing code changes against incident history, active incidents, and on-call readiness. Forked-subagent flow may not have MCP access in all Claude Code contexts.
Install
npx skills add Rootly-AI-Labs/rootly-claude-plugin --skill deploy-checknpx skills add Rootly-AI-Labs/rootly-claude-plugin --skill deploy-check -a claude-code -gnpx skills add Rootly-AI-Labs/rootly-claude-plugin --skill deploy-check -a codex -ggemini skills install https://github.com/Rootly-AI-Labs/rootly-claude-plugin.git --path skills/deploy-checkgh skill install Rootly-AI-Labs/rootly-claude-plugin deploy-checkgit clone --depth 1 https://github.com/Rootly-AI-Labs/rootly-claude-plugin /tmp/Rootly-AI-Labs__rootly-claude-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Rootly-AI-Labs__rootly-claude-plugin/skills/deploy-check ~/.claude/skills/deploy-check # Claude Code
cp -R /tmp/Rootly-AI-Labs__rootly-claude-plugin/skills/deploy-check ~/.agents/skills/deploy-check # Codex, Cursor, Gemini CLI, Copilot, OpenCode