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 skills/0xrafasec/ai-workflow/autopilotnpx skills add 0xrafasec/ai-workflow --skill autopilotgit clone --depth 1 https://github.com/0xrafasec/ai-workflowWrote 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/0xrafasec/ai-workflow/autopilot)<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/autopilot"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/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 5.1 | $0.00120 | $0.03599 |
| Opus 5 | $0.00060 | $0.01800 |
| Sonnet 5 | $0.00024 | $0.00720 |
| Haiku 4.5 | $0.00012 | $0.00360 |
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 6d 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.
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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the roadmap at: $ARGUMENTS
What autopilot is
Autopilot is autonomous, end-to-end roadmap delivery. You read a roadmap and, for every
task in every phase, you run the full delivery pipeline yourself — develop → review → fix →
merge to main — looping until the roadmap is delivered or a genuine blocker stops you. The
default is no human checkpoint: autopilot self-merges each reviewed, green PR to main and
moves on. "Autopilot should be autopilot."
This is the deliberate difference from /factory, which builds one milestone's PRs and stops
with them open for a human to merge. Autopilot does merge — invoking it in the default
(autonomous) mode is the user granting that merge authority. If the user wants the old
stop-at-every-phase behaviour, they pass --supervised (see Modes).
You are still an orchestrator: you do not implement or review code yourself. You parse the roadmap, dispatch worktree agents for development, dispatch fresh-context agents for review, triage their verdicts, perform the mechanical git merge, update roadmap status, and loop. The merge is the one state-changing action you perform directly; everything intellectual is delegated.
Modes
- autonomous (default) — develop, review, fix, and merge to
mainfor every task, phase after phase, with no human gate. Only stop on a genuine blocker (see Stop conditions). --supervised— run each phase, but stop at the phase boundary with PRs open and hand them to the human to review + merge before continuing (the pre-0.7 behaviour). Use when the user says "let me review before merge", the repo has protected branches requiring human approval, or the work is high-stakes.
Detect the mode from $ARGUMENTS (a --supervised token) or from explicit user intent. When in
doubt for a brand-new/unfamiliar repo, ask once which mode they want, then proceed.
Process
1. Parse the roadmap
Read the roadmap file. For each phase extract:
- Phase name and goal, and any feature flag the phase ships behind.
- Tasks — each with: name, spec path, files touched, dependencies, verification command, test
layers.
complexity:hightasks point at a sliced spec directory — each slice is its own task/PR; expand them. - Which tasks run in parallel (no file overlap, no dependency between them) vs sequential (depend on another task in the same phase).
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.
- 6d ago First seen · 272 lines · 120 tokens per session scan A 73946b612964
autopilot is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 4d ago), licensed MIT. It adds 120 tokens to every session and 3,599 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.