Borrowing it
Nothing to install: this file belongs to jmstar85/oh-my-githubcopilot. 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/jmstar85/oh-my-githubcopilot/main/.github/skills/omg-autopilot/SKILL.mdgit clone --depth 1 https://github.com/jmstar85/oh-my-githubcopilotWrote 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/jmstar85/oh-my-githubcopilot/omg-autopilot)<a href="https://agentmods.dev/skills/jmstar85/oh-my-githubcopilot/omg-autopilot"><img src="https://agentmods.dev/badge/skills/jmstar85/oh-my-githubcopilot/omg-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 | $0.00052 | $0.01284 |
| Opus 5 | $0.00026 | $0.00642 |
| Sonnet 5 | $0.00010 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
omg-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 7d 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.
This is a copy
88% identical to omg-autopilot — 71 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMG Autopilot
OMG Autopilot takes a brief product idea and autonomously handles the full lifecycle: requirements analysis, technical design, planning, parallel implementation, QA cycling, and multi-perspective validation.
When to Use
- User wants end-to-end autonomous execution from an idea to working code
- Task requires multiple phases: planning, coding, testing, and validation
- User wants hands-off execution
When NOT to Use
- User wants to explore options → use
/plan - Single focused code change → use
/ralphor delegate to @executor - Quick fix or small bug → delegate directly to @executor
Interactive Hook Protocol
Use vscode_askQuestions at critical decision gates during autopilot execution (when available).
If vscode_askQuestions is NOT available (e.g., Copilot CLI), present numbered options in markdown.
Autopilot is designed to be mostly autonomous, but hooks fire at ambiguity points and failure recovery.
When to Fire Hooks
| Trigger Point | Question Type |
|---|---|
| Phase 0: Vague input | Redirect to deep-interview or proceed with assumptions |
| Phase 0: Spec review | Confirm extracted spec before planning |
| Phase 3: Repeated QA failure | Ask user for direction on persistent errors |
| Phase 4: Validation rejection | Surface reviewer concerns for user decision |
Execution Pipeline
Phase 0 - Expansion
Turn the user's idea into a detailed spec.
- If ralplan consensus plan exists (
.omg/plans/ralplan-*.md): Skip Phase 0 AND Phase 1 → jump to Phase 2 - If deep-interview spec exists (
.omg/specs/deep-interview-*.md): Use pre-validated spec, skip to Phase 1 - If input is vague: HOOK via
vscode_askQuestions:header: "autopilot-vague-input" question: "Your request is broad. How should I proceed?" options: [ { label: "Run /deep-interview first", description: "Thorough requirements gathering", recommended: true }, { label: "Proceed with my best interpretation", description: "I'll extract requirements and show you for approval" }, { label: "Let me clarify — here's more detail..." } ] allowFreeformInput: true - Otherwise: @analyst extracts requirements, @architect creates technical specification
- HOOK: Spec confirmation before proceeding to planning:
header: "autopilot-spec-review" question: "Here's what I understood: [1-line summary]. Proceed?" options: [ { label: "Looks good — proceed", recommended: true }, { label: "Mostly right, but adjust..." }, { label: "Wrong direction — let me re-explain" } ] allowFreeformInput: true - Output:
.omg/autopilot/spec.md - Track phase:
omg_write_state(phase="expansion_done")
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.
- 7d ago First seen · 137 lines · 52 tokens per session scan A cd25c156f249
omg-autopilot is a skill published in the GitHub repository jmstar85/oh-my-githubcopilot (154 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,284 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to omg-autopilot, differing in 71 lines, and is treated as a copy.
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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…