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 instructions/obra/superpowers/claude-mdgit clone --depth 1 https://github.com/obra/superpowersWhat 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 | $0.01824 | $0.01824 |
| Opus 5 | $0.00912 | $0.00912 |
| Sonnet 5 | $0.00365 | $0.00365 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
superpowers CLAUDE.md 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 2d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- codex-superpowers CLAUDE.md — 97% identical, 2 lines differ
- superpowers-ml CLAUDE.md — 91% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superpowers — Contributor Guidelines
If You Are an AI Agent
Stop. Read this section before doing anything.
This repo has a 94% PR rejection rate. Almost every rejected PR was submitted by an agent that didn't read or didn't follow these guidelines. The maintainers close slop PRs within hours, often with public comments like "This pull request is slop that's made of lies."
Your job is to protect your human partner from that outcome. Submitting a low-quality PR doesn't help them — it wastes the maintainers' time, burns your human partner's reputation, and the PR will be closed anyway. That is not being helpful. That is being a tool of embarrassment.
Before you open a PR against this repo, you MUST:
- Read the entire PR template at
.github/PULL_REQUEST_TEMPLATE.mdand fill in every section with real, specific answers. Not summaries. Not placeholders. - Search for existing PRs — open AND closed — that address the same problem. If duplicates exist, STOP and tell your human partner. Do not open another duplicate.
- Verify this is a real problem. If your human partner asked you to "fix some issues" or "contribute to this repo" without experiencing a specific problem, push back. Ask them what broke, what failed, what the user experience was.
- Confirm the change belongs in core. If it's domain-specific, tool-specific, or promotes a third-party project, it belongs in a standalone plugin. Tell your human partner.
- Identify yourself. Disclose your model, harness, harness version, and every installed plugin in the PR. Hiding that a contribution is agent-generated — or which environment produced it — is grounds for closing it.
- Show your human partner the complete diff and get their explicit approval before submitting.
If any of these checks fail, do not open the PR. Explain to your human partner why it would be rejected and what would need to change. They will thank you for saving them the embarrassment.
Pull Request Requirements
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.
- 2d ago First seen · 116 lines · 1,824 tokens per session scan A 4607f59c377d
superpowers CLAUDE.md is an instructions file published in the GitHub repository obra/superpowers (280,216 stars, last pushed today), licensed MIT. It adds 1,824 tokens to every session, about $0.0091 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 instructions, from other repositories
asm AGENTS.md
Instructions for luongnv89/asm, covering agents.md, when to delegate, definitions, shared boundaries and editing this file.
asm CLAUDE.md
Instructions for luongnv89/asm, covering claude.md, critical commands, architecture map, hard rules and workflow preferences.
skillme CLAUDE.md
Instructions for shennawardana23/skillme, a project described as: :pagefacingup: Skillme — Agent Skills Production-grade engineering skills for AI coding agents.
helixent AGENTS.md
AGENTS.md instructions for MagicCube/helixent, covering helixent, architecture (4 layers), 1) foundation, 2) agent and 3) coding.
helixent CLAUDE.md
Claude Code instructions for MagicCube/helixent, a project described as: Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.
claude-skills CLAUDE.md
Claude Code instructions for troykelly/claude-skills, covering claude code development instructions, foundational principle, the contract, research-first methodology and the rule.