Borrowing it
Nothing to install: this file belongs to usk6666/yorishiro-proxy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/usk6666/yorishiro-proxy/main/.claude/skills/autopilot/SKILL.mdgit clone --depth 1 https://github.com/usk6666/yorishiro-proxyWrote 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/usk6666/yorishiro-proxy/autopilot)<a href="https://agentmods.dev/skills/usk6666/yorishiro-proxy/autopilot"><img src="https://agentmods.dev/badge/skills/usk6666/yorishiro-proxy/autopilot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/usk6666/yorishiro-proxy/autopilot"><img src="https://agentmods.dev/badge/skills/usk6666/yorishiro-proxy/autopilot.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.10275 |
| Opus 5.5 | $0.00026 | $0.04110 |
| Sonnet 5.5 | $0.00013 | $0.02055 |
| Haiku 4.5 | $0.00006 | $0.01027 |
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 1mo 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 — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/autopilot
/orchestrate adapted for unattended, scheduled execution (Claude Desktop local
scheduled task, worktree mode, Auto permission mode). Setup and operating guide:
.claude/skills/autopilot/SETUP.md.
It reuses the same building blocks as /orchestrate — .claude/agents/*.md templates and
the /review-gate flow — but replaces every human gate with a deterministic policy:
It does not read /orchestrate's SKILL.md. The rules it borrows (the Phase 0-1 fetch batch,
the 1-1 dependency inference, the 1.5 design-review skip rules and placeholders, the 2-1 prompt
assembly and branch naming, the 2-2-A oversize red flags) are inlined at their points of use and
marked as such. Loading a 600-line sibling skill to use eighty lines of it costs an unattended
run context it cannot spare, and a renumbered heading there would silently break this one. When
a rule genuinely changes, update both.
/orchestrate asks the user… |
/autopilot instead… |
|---|---|
| to approve the execution plan (1-3) | executes the plan; records it in the run report |
| about unresolved design questions (1.5-3) | posts the questions to Linear, labels autopilot:needs-decision, skips the Issue |
| whether to merge before the next batch (2-2) | never merges; only picks Issues whose blockers are Done |
| to intervene on escalations (2.5-7) | labels PR autopilot:needs-human, keeps it draft, comments on Linear |
A run is stateless: all state lives in Linear (status, labels, comments) and GitHub (PR labels, draft flag, marker comments). A crashed run must leave nothing that the next run cannot detect and recover.
The single exception is the agent ledger (Phase 0) — the sub-agent IDs whose worktrees this run must clean up. Those exist nowhere in Linear or GitHub, so they are written to a local file as they are created instead of being kept in the conversation, where a context compaction would lose them.
Arguments
/autopilot— Normal run (Phase 0 → 6)/autopilot dry-run— Phase 0–3 only; print what would be done, write nothing anywhere/autopilot followup-only— Phase 0–2 and 6 only (no new Issue)/autopilot <Issue ID>— Skip selection (Phase 3) and run Phase 4–6 for that Issue. Eligibility checks 3-2 (b)–(f) still apply.
What ships with it
1 file 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.
- 1mo ago First seen · 728 lines · 65 tokens per session scan A 60caada296d4
autopilot is a skill published in the GitHub repository usk6666/yorishiro-proxy (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 10,275 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
papi-build
Invoke when executing a build via buildexecute. Covers branching, gestalt pre-build check, and post-build audit.
papi-auto
Continue an approved PAPI cycle through implementation, verification and review using bounded autonomy. Resume durable work without rebuilding it; propose new scope before persisting it.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
deliver-spec
Use when explicitly asked to deliver an approved GitHub or local spec through a reviewed pull request, or when a Project controller delegates one claimed implementation ticket.