Execute approved PlanetScale changes end-to-end without per-step approval when the operator has explicitly acknowledged the risk. Defines the risk-acknowledgment contract, scoped autonomy levels, sensible execution ordering, continuous status reporting, halt conditions, and rollback discipline. Extremely safe, very enabling.
Install
npx skills add planetscale/claude-plugin --skill planetscale-autonomous-execution-modenpx skills add planetscale/claude-plugin --skill planetscale-autonomous-execution-mode -a claude-code -gnpx skills add planetscale/claude-plugin --skill planetscale-autonomous-execution-mode -a codex -ggemini skills install https://github.com/planetscale/claude-plugin.git --path planetscale-skills/13-autonomous-execution-modegh skill install planetscale/claude-plugin planetscale-autonomous-execution-modegit clone --depth 1 https://github.com/planetscale/claude-plugin /tmp/planetscale__claude-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/planetscale__claude-plugin/planetscale-skills/13-autonomous-execution-mode ~/.claude/skills/planetscale-autonomous-execution-mode # Claude Code
cp -R /tmp/planetscale__claude-plugin/planetscale-skills/13-autonomous-execution-mode ~/.agents/skills/planetscale-autonomous-execution-mode # Codex, Cursor, Gemini CLI, Copilot, OpenCode