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 skills add OutlineDriven/outline-driven-development --skill autopilotgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/skills/outlinedriven/outline-driven-development/autopilot)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/autopilot"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/autopilot.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00040 | $0.01329 |
| Opus 5 | $0.00020 | $0.00665 |
| Sonnet 5 | $0.00008 | $0.00266 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
autopilot scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopilot
Contract
| Field | Bound contract |
|---|---|
| Trigger | A human explicitly invokes /autopilot with a feature description and an approved execution plan. |
| Authority | Human-gated: previews the exact target and consequence before credentials, paid actions, data-at-rest changes, publication, deployment, remote bulk mutation, or irreversible deletion, continuing only when the invocation covers that consequence; every other write is reversible local, with version control as the rollback. Pass authorized push and PR targets to review-and-ship; do not publish directly. |
| Side effect | Delegates implementation, simplification, review, and finalization to their respective skills; local artifacts are written by work, commits and PR are created by review-and-ship. No mutation is performed by autopilot itself. |
| Done | Return DONE only after the requested close-out state is observed. Otherwise return BLOCKED with a resumable handoff. |
Inputs
Required: feature description, approved plan, repository, acceptance criteria, and close-out condition.
Optional: scope limits; assigned executor; target branch, remote, and PR destination; required checks; shipping instructions. Derive an omitted value only when repository evidence gives one safe, unique answer.
Procedure
- Parse the plan, scope, assignments, acceptance criteria, repository, required proof, shipping destination, and close-out condition. Reject contradictions and unavailable assigned executors. Done when: every required input is parsed and bound to a concrete value, contradictions are rejected with the conflicting pair named, and unavailable executors are reported; or the run stops on the first unresolvable input.
- Confirm that the human approved the plan. If not, stop before implementation and route to planning. Done when: an approval record is confirmed; the plan was approved through plan mode or an equivalent written approval; or the run stops and routes to planning with no delegation.
- Inspect enough repository evidence to bind the plan to exact artifacts, behavior, verification, and remote targets. Keep the campaign inside the approved scope. Done when: every plan step maps to a named repository artifact (file, directory, or remote target) and the scope boundary is stated with the artifacts inside it and the artifacts excluded from it.
- Preview each risky consequence. Stop when authority is absent or the target is ambiguous. Done when: every credential, paid, data-at-rest, publication, deployment, remote bulk, or irreversible consequence is previewed with its exact target, or the run stops naming the absent authority or ambiguous target.
- Delegate the bounded plan to
workin orchestrated mode. Include acceptance criteria, constraints, repository evidence, required verifier, and the required structured return.workowns implementation and local verification; autopilot does not reproduce those steps. Apply the gate state machine inreferences/pipeline-gates.md: a failing work verifier gets onestrike-the-rootpass and one recheck; a second failure halts the chain. Done when:workreturns a structured result with implementation summary and local verification passing, or the gate halts the chain with the verifier failure and diff recorded. - Delegate simplification to
simplifyon the completed diff. Gate:simplifyexits0,11, or12with behavior preserved. Halt on exit14(new bloat) or15(mixed-concern). Done when:simplifyreturns exit0,11, or12with behavior preserved confirmed by its output, or the chain halts on exit14or15with the exit code and cause recorded. - Delegate review to
reviewon the in-scope change. If critical or high findings remain, delegate onestrike-the-rootpass and re-review the changed files. Halt on residual critical or high findings. Done when:reviewreturns zero critical and zero high findings on the changed files, or the chain halts with the residual findings listed. - Delegate finalization to
review-and-ship. Pass the reviewed diff, explicit delegated shipping authority, branch, remote, PR destination, required checks, and shipping instructions. The finalizer owns checks, commits, publication classification, push, and PR creation or update; autopilot performs none of them. Done when:review-and-shipreturns its report with checks green and PR created or updated (full mode) or commits made and push skipped (local-only), or the finalizer returns blocked with its reason. - Observe authorized close-out. Route any supported in-scope fix back through
workin orchestrated mode, repeat affected gates, and invokereview-and-shipfor each authorized update. Do not merge, deploy, or publish elsewhere without matching authority. Done when: the close-out condition named in the inputs is observed in repository or remote state, or the run stops for absent authority. - Return the terminal classification and include the finalizer report. The gate and handoff formats in
references/pipeline-gates.mdare binding. Done when: the terminal result isDONEwith the finalizer report attached and close-out state quoted, orBLOCKEDwith the failed stage, reason, and next action named.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · -24 tokens per session 2bf899dbbb07
- 4d ago First seen · 49 lines · 64 tokens per session scan A 0b9f14da0cb6
autopilot is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,329 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
drift-detect
Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.
github-backlog-triage
Use when the user invokes backlog triage for a GitHub repo's open issues and PRs. Not for proactive triage, non-GitHub trackers, or single bug issues: use github-bug-report-triage.
setup-repo-skills
Use when the user wants one-time repository setup for tracker, triage labels, and domain conventions. Not for ongoing triage, issue creation, or multi-repo setup.
git-history-analysis
Use when the user asks about recent engineering work, what the team is working on, planning or roadmap material, or an explicitly requested Slack summary. Not for remote or irreversible changes.
graph-backbone
Use when defining, revising, or gate-replanning the project structural backbone in project-root graph.yaml; produces a validated approved revision preserving immutable topology and additive metadata. Not for remote, credential, publish, deploy, or irreversible changes.
wontfix
Use when the user wants to elicit refused directions, generalize them, and close matching tracker items as not planned. Not for duplicates, spam, or items closed as completed or obsolete.