The toolkit has two autonomous loops. Both work without you babysitting them, both auto-continue between phases, and both stop at PR creation — merging is always yours. The difference is the shape of the work.
| You have… | Run |
|---|---|
| One objective, fuzzy path (“Cut homepage LCP under 2s”) | /goal |
| Multiple issues, ranked queue (“Work through these 8 issues”) | /autopilot |
| One feature with a written plan | /implement — not an autonomous loop |
| One bug with a clear repro | /fix |
If the work is “I have a destination, figure out the path” — /goal. If it’s “I have a stack of well-scoped tickets, work them” — /autopilot.
/goal Cut homepage LCP below 2s on mobile
A scout reads your knowledge base and project profile first, then scans the codebase to fill gaps; you answer 3–5 context-aware clarifying questions (or say “go” for defaults) and confirm the plan. Then it loops: pick action → execute → mandatory verify (lint + types + tests) → capture evidence → self-evaluate against each subtask’s done_when clause. It runs inline, pulling in Sonnet agents only when needed, with a budget of 6 agents per goal. Lifecycle: /goal pause, resume, clear, status; state lives in .claude/.goals/current.json.
/autopilot --urgent-first
It ranks open issues P0–P5, then per item: classify → verify repro → plan → implement (with backend/frontend/QA agents as needed) → QA → self-review → PR. The PR body is assembled directly from the captured evidence array (git diffs, test results, lint, types). --dry-run shows what it would do without doing it — useful for trust-building. State lives in .claude/.workflow-state.json.
/goal, they stop at PR creation — you run /pr) and wait. Nothing merges without a human./autopilot). Each item is scored 0–12 on blast radius, reversibility, confidence, and domain sensitivity: score ≥ 11 is refused, ≥ 9 escalates to you before work starts./autopilot). Scope drift, QA failures after 2 attempts, or a per-item budget breach (> 6 agents) block the item rather than pushing through./goal, 15 for /autopilot) and wait for you. They stay silent at human-gate phases — awaiting merge, blocked, paused.Both skills ship in the cruise bundle, which requires forge + scalpel + sentinel (see the plugin catalog).
/goal vs /autopilot table