Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/damusix/atomic-claude/autopilotgit clone --depth 1 https://github.com/damusix/atomic-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/damusix/atomic-claude/autopilot)<a href="https://agentmods.dev/commands/damusix/atomic-claude/autopilot"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/autopilot.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00106 | $0.03657 |
| Opus 5 | $0.00053 | $0.01828 |
| Sonnet 5 | $0.00021 | $0.00731 |
| Haiku 4.5 | $0.00011 | $0.00366 |
Grade C, and why
autopilot scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **One deliberate deletion, at the very end.** Phase 6 removes `tmp/trash/` only, in a single `rm -rf` — the one place a deletion permission prompt is expected and harmless. The task scratchpad is not deleted; it is ret How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the autopilot orchestrator. The user has handed you a unit of work and authorized you to take it from nothing to shipped without further input — except one decision: how to merge. You drive the full atomic lifecycle (plan → implement→review loop → ship) autonomously. You do NOT implement code yourself; you drive fresh-context subagents, exactly as /subagent-implementation does.
$ARGUMENTS: <task description | issue#> [merge-verb]. The optional trailing merge-verb is one of commit, commit push, commit pr, commit merge, commit squash, commit squash merge. If present, skip the Ship gate's question and use it.
<the_five_rules>
This command exists to codify five non-negotiable behaviors. They override the corresponding interactive defaults because the user opted into autonomy by invoking /autopilot:
- Always use the
/subagent-implementationloop. The implement→review→commit-per-green loop is the engine. The orchestrator never writes implementation code inline; every change goes through a fresh-context builder/surgeon and is checked by a fresh reviewer. - Every reviewer finding is addressed in-iteration. Blocking and non-blocking (🔴/🟡/🔵). Fold each into the next builder dispatch or a surgical pass before the checkpoint is considered done. The scratchpad
FOLLOWUPS.mdends empty — nothing is deferred to a Phase 3 triage, because there is no interactive Phase 3 here. (This overrides/subagent-implementation's normal "harvest non-blockers for user disposition.") - Auto-dispatching
atomic-strategistis allowed. When the stuck-fix escalation fires (same blocking signal across 2 rounds), do NOT surface-and-wait. Dispatchatomic-strategist(high effort, read-only) for root-cause analysis, then feed its findings into the next builder dispatch. Safe to do unprompted because the strategist never writes — it only reasons. (This overrides the normal "surfaced, never auto-invoked" rule, which exists to gate the cost; the user accepted that cost by invoking autopilot.) - Always ask how to merge — and only that. The merge method is the single human decision. If
$ARGUMENTSsupplied a merge-verb, use it silently. Otherwise the Ship gate asks. Nothing else in the run prompts the user. - The spec is currency-clean before every dispatch. Produce and maintain the spec under the planning rule in
CLAUDE.md("Specs: the body is current truth, the change log is history"): the body describes only the current decision, never superseded content. A fresh subagent reads the spec body verbatim — nothing that could divert it may live there. Re-verify before each builder dispatch.
</the_five_rules>
<scratch_hygiene>
Autopilot runs unattended, so a mid-run permission prompt stalls the whole run waiting on a human who may be away. The two usual triggers are rm and chained shell commands (a && b, a; b). Avoid both:
- Experiments are quarantined, never deleted mid-run. All probes, scratch scripts, and one-off test files live under
tmp/(gitignored — seeCLAUDE.md). Createtmp/trash/once at the start of the run (mkdir -p tmp/trash). To discard scratch,mvit intotmp/trash/— a singlemvis one plain command;rmis the one that prompts. - No
rm, no command chaining, during the run. Prefer one simple command per Bash call. If you catch yourself reaching forrmor&&to clean up an experiment, move the file totmp/trash/instead and keep going. - Brief the subagents. Every
atomic-implementerdispatch brief includes the line: "Discard scratch by moving it totmp/trash/; neverrmand do not chain shell commands." So subagents quarantine instead of deleting too. - One deliberate deletion, at the very end. Phase 6 removes
tmp/trash/only, in a singlerm -rf— the one place a deletion permission prompt is expected and harmless. The task scratchpad is not deleted; it is retired only viaatomic scratchpad archive <slug>, driven by/git-cleanup. If the user is not present to grant thetmp/trash/deletion, leave it in place: it is gitignored and never ships. This is a Bash permission grant, not anAskUserQuestion, so it does not violate rule 4 (the ship gate stays the only decision prompt).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 143 lines · 0 tokens per session scan C 445df1797126
autopilot is a command published in the GitHub repository damusix/atomic-claude (83 stars, last pushed 10d ago), licensed MIT. It adds 106 tokens to every session and 3,657 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
go-review
Go code review for idiomatic patterns.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
test
Run all PandaFilter verification steps in order. Stop and report on first failure. This is the required pre-commit gate.
dev-planner
Generate or update DEV-PLAN.md with phased development plan from Product-Spec.md.