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 rares77/superpowers-autopilot --skill superpowers-autopilotgit clone --depth 1 https://github.com/rares77/superpowers-autopilotWrote 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/rares77/superpowers-autopilot/superpowers-autopilot)<a href="https://agentmods.dev/skills/rares77/superpowers-autopilot/superpowers-autopilot"><img src="https://agentmods.dev/badge/skills/rares77/superpowers-autopilot/superpowers-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/rares77/superpowers-autopilot/superpowers-autopilot"><img src="https://agentmods.dev/badge/skills/rares77/superpowers-autopilot/superpowers-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 | $0.00118 | $0.04488 |
| Opus 5 | $0.00059 | $0.02244 |
| Sonnet 5 | $0.00024 | $0.00898 |
| Haiku 4.5 | $0.00012 | $0.00449 |
Grade A, and why
superpowers-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 10d 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 — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superpowers Autopilot
Runtime Context
Runtime state is checked explicitly in Resume Check and Phase 0.
Do not execute bash from this section during skill initialization.
Overview
Autonomous outer loop that implements every feature in a PRD.md with a single bootstrap choice at startup. You read the PRD, let the user choose the consultant once during initialization, then queue features, plan and execute each one using Superpowers skills, consult that chosen CLI when stuck, and exit with a summary report.
Invocation: /superpowers-autopilot <path/to/PRD.md>
Autopilot Rules
- Interactive Superpowers skills are blocked by the guard hook —
brainstorming,finishing-a-development-branch,executing-plans, andusing-git-worktreesare denied at the tool level while.claude/autopilot-activeexists. You don't need to avoid them manually; the hook enforces it. - Only ask the user one operational question during Phase 0 — let them choose the consultant from the detected options (or accept the recommended default). After that, do not ask further questions during execution; all ambiguities and clarifications go to the consultant (Phase 2b).
- NEVER wait for user approval after Phase 0 — once initialization is complete, the loop is fully autonomous until all features are done or the circuit breaker fires.
- ALWAYS choose subagent-driven execution when
writing-plansasks — never inline, never ask the user which one. - Design review replaces brainstorming — scan every feature spec for ambiguities before planning, resolve them via the consultant, then invoke
writing-planswith the resolved spec. - When running shell commands from this skill, invoke only the bare wrapper command exactly as written. Do not append
2>&1,; echo,&&,||, or any extra shell decoration.
Prerequisites
- PRD.md exists at the provided path
- Project is a git repository (clean working tree preferred)
- Superpowers skills available:
writing-plansandsubagent-driven-development(prefixed assuperpowers:writing-plans/superpowers:subagent-driven-developmentin Claude Code) - Optional: a consultant CLI installed for second-opinion consultations (falls back gracefully)
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.
- 10d ago First seen · 434 lines · 118 tokens per session scan A 6da42aed9382
superpowers-autopilot is a skill published in the GitHub repository rares77/superpowers-autopilot (5 stars, last pushed 5mo ago), licensed MIT. It adds 118 tokens to every session and 4,488 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
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…