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/techymt/claude-code-superpowers/agents-mdgit clone --depth 1 https://github.com/TechyMT/claude-code-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 | $0.00987 | $0.00987 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
claude-code-superpowers AGENTS.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
1 near-identical copy found in the catalogue:
- claude-code-superpowers CLAUDE.md — 100% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Superpowers — Repository Guide
This repository is a collection of engineering skills for AI coding assistants. Each skill is a structured markdown file that teaches a specific pattern — extracted from production source code, validated against real implementations, and tested against the six-test standard to ensure it's transferable beyond the source codebase.
Repository structure
skills/ — one subdirectory per skill, each containing SKILL.md
docs/ — REFERENCE.md: domain model, architecture overview, vocabulary
assets/ — banner.svg, banner-footer.svg
CLAUDE.md — working guide for Claude Code agents
AGENTS.md — this file: working guide for Codex/OpenAI agents
GEMINI.md — skill includes for Gemini CLI
README.md — user-facing introduction, AI-native format
Adding a new skill
- Create
skills/[skill-name]/SKILL.md - Follow the skill structure in
CONTRIBUTING.mdexactly - Add a row to the skills table in
README.md,CLAUDE.md, andAGENTS.md - Add an
@include line toGEMINI.md - Run the six-test standard (see
CONTRIBUTING.md) before committing
Naming: lowercase, hyphens only, verb-first where possible (creating-skills, error-handling, not skillCreation or ErrorHandling)
See CONTRIBUTING.md for the full skill structure, section-by-section requirements, and the six-test standard. That file is the single source of truth for contribution rules.
Reference
docs/REFERENCE.md is the foundational context for this repo — domain model, architecture overview, and vocabulary. Read it before working on any skill.
What not to do
- Do not add skills that only make sense if you are contributing to the source codebase
- Do not use source-codebase-specific function names or file paths in the generic sections
- Do not write code examples to illustrate a pattern — extract real code from the source
- Do not update
CLAUDE.mdorAGENTS.mdwith source-codebase-specific internal conventions
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 · 71 lines · 987 tokens per session scan A 8baa31a3efe0
claude-code-superpowers AGENTS.md is an instructions file published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 987 tokens to every session, about $0.0049 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 instructions, from other repositories
skills CLAUDE.md
Claude Code instructions for ai-shifu/skills, a project described as: Skills for creating 1v1 interactive courses with AI-Shifu.
custom_github_copilot_agent_builder agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
building-a-coding-agent-from-scratch-course CLAUDE.md
Instructions for decodingai-magazine/building-a-coding-agent-from-scratch-course, a project described as: From agent user to agent builder: build a Claude Code-style coding agent from scratch in Python: 8 articles, 4 videos, one codebase.
better-skill-builder CLAUDE.md
Instructions for gmickel/better-skill-builder, covering gmickel-skill, structure, updating, official docs and skills referenced.
skill_steward CLAUDE.md
Instructions for Arenukvern/skill_steward, a project described as: “What’s the thing?” You’d answer: “Skills that teach you how to maintain skills & repos”. Engineering Stewardship for any repository (app, library, tool), a structural governance and quality layer for agent-operated engineering repos.
better-skill-builder AGENTS.md
Instructions for gmickel/better-skill-builder, a project described as: Skill that teaches AI agents how to build Agent Skills for Claude Code, Codex, Amp, and OpenCode. Production patterns from gno, sheets-cli, raindrop, outlookctl, and flow.