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/odin-claude-plugin --skill autopilotgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/odin-claude-plugin/autopilot)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/autopilot"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/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 | $0.00057 | $0.02029 |
| Opus 5 | $0.00028 | $0.01014 |
| Sonnet 5 | $0.00011 | $0.00406 |
| Haiku 4.5 | $0.00006 | $0.00203 |
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 8d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopilot: hands-off plan→ship pipeline that chains existing skills
autopilot runs a build request from plan to shipped without re-prompting at every step. It is a chain: each phase invokes an existing ODIN skill via the Skill tool and gates on the result before the next phase begins. It owns sequencing, the phase gates, and the terminal report; nothing else. It writes no code surface of its own; the chained skills do.
When to Apply
- The user hands an execution-ready task and wants it taken from plan to shipped without step-by-step approval: "autopilot", "ship it end to end", "take it from plan to PR".
- A concrete change is specified, enough for the approved plan to name implementation units. The pipeline executes; it does not discover what to build.
When NOT to Apply
- A single execution step against an approved plan →
work. autopilot wrapsworkwith the rest of the arc; if that arc is unwanted, callworkdirectly.
Inputs and Flags
[task]: the execution-ready request the approved plan covers. Required; an empty or ambiguous task fails the precondition below — the chain does not start.against <ref>: base-ref override forwarded to the diff-scoped phases (simplify,review).mode:local: force local-only (skip push + CI) even when a remote exists.mode:headless: non-interactive overlay; pass through to each chained skill's headless variant where it has one. No phase prompts the user; a gate that would prompt instead HALTs with the question in the report.
Precondition: an approved plan exists
The chain begins only when an approved plan exists — one the user approved through Claude Code's built-in plan mode (ExitPlanMode), or an equivalent written plan the user has approved. autopilot does not produce that plan and never invents one: "scope unknown" is not autofixable. No approved plan → do not start; return to plan mode, or hand off upstream to askme / strategy for an execution-ready task.
The chain
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.
- 8d ago First seen · 95 lines · 57 tokens per session scan A 6746ad414a90
autopilot is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 2,029 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…