forge-autopilot-stop
Skill2 starsChanged 5 months agoMITView on GitHub
Stop a running Forge autopilot. Use when the user runs /forge:autopilot-stop,
In this repository46 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- forge-opencode/CLAUDE.mdCLAUDE.md
- forge-adoptSkill
- forge-arch-proSkill
- forge-archSkill
- forge-autopilotSkill
- forge-build-proSkill
- forge-buildSkill
- forge-deploySkill
- forge-doctorSkill
- dreamer-runSkill
- forge-evalSkill
- forge-feedbackSkill
- flowSkill
- forge-force-advanceSkill
- graduateSkill
- health-checkSkill
- forge-initSkill
- forge-monitorSkill
- forge-orchestrateSkill
- forge-plan-proSkill
- forge-planSkill
- preflightSkill
- forge-product-proSkill
- forge-productSkill
- forge-releaseSkill
- forge-resolveSkill
- forge-resumeSkill
- forge-retroSkill
- forge-reviewSkill
- forge-rulesSkill
- forge-set-profileSkill
- skill-creatorSkill
- forge-spec-proSkill
- forge-specSkill
- forge-sprint-proSkill
- forge-sprintSkill
- forge-srs-proSkill
- forge-srsSkill
- forge-statusSkill
- forge-trace-matrixSkill
- forge-uninstallSkill
- forge-validateSkill
- watchSkill
- watch-stopSkill
- forge-whySkill
The file
Files
forge-autopilot-stop — halt a running autopilot
Requests a clean stop of an in-progress /forge:autopilot run. The flag is checked
between stages, so the current stage finishes and the loop stops before the next one —
no work is interrupted mid-stage and no gate is forced.
When to Use
- User runs
/forge:autopilot-stopor asks to stop/cancel the autopilot run.
Steps
- Request the stop:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/autopilot.py stop --cwd . - Confirm to the user that autopilot will halt at the next stage boundary, and that they
can resume later with
/forge:autopilot --resume(already-completed stages are skipped via.forge/autopilot-runs.jsonl).
Notes
- Stopping is cooperative: it sets
stop_requestedin.forge/autopilot-session.json; the autopilot loop honors it on its next between-stages check. If no autopilot is running, this is a harmless no-op. - This stops Forge's autopilot only — it is unrelated to any other tool's "autopilot".
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.