Autopilot

Run approved pipeline work until it is complete or reaches a genuine human gate. Keep wayfinder, to-spec, to-tickets, and implement authoritative; this skill adds a fresh-process loop around them.

Start the loop

1. Require a reference to a wayfinder map, a spec, or a ticket. Run from the target Git repository.
2. Select the current harness as the provider: claude in Claude Code, codex in Codex, grok in Grok. When running directly from a terminal, require the user to choose.
3. Resolve this skill's installed directory, then run the bundled script by absolute path while keeping the target repository as the working directory:

bash <autopilot-skill-dir>/scripts/autopilot.sh --provider <claude|codex|grok> --root <ref>

Pass --repo <path> when the target is not the current repository, --max-iterations <n> to replace the default limit of 50, and --log-file <path> to mirror the per-run log to another path.

Run the script as a background task and poll its output: one iteration is a full build lifecycle and routinely outlasts a foreground shell-command timeout. Immediately report the run ID, worker session model and effort, log path, and printed observer commands. Then report worker milestones and five-minute heartbeats from stderr as they arrive; leave routine tool events in the log.

Foreground run mode prints progress to stderr and one terminal result object to stdout; completion is exit code 0 with status: complete. Observer modes keep their operational messages on stderr: --status prints one state object, --history prints an array of retained states, --tmux prints one launch object, and --follow streams the human-readable run log to stdout.