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/claude-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 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.
This is a copy
100% identical to claude-code-superpowers AGENTS.md — 5 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 — 72 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 — this file: how to work in this repo
AGENTS.md — same index 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 · 72 lines · 987 tokens per session scan A e43cfda41996
claude-code-superpowers CLAUDE.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. It is 100% identical to claude-code-superpowers AGENTS.md, differing in 5 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.