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/jnmetacode/superpowers-zh/agents-mdgit clone --depth 1 https://github.com/jnMetaCode/superpowers-zhWhat 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 | $0.00004 | $0.00004 |
| Opus 5 | $0.00002 | $0.00002 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00000 | $0.00000 |
Grade A, and why
superpowers-zh 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 yesterday.
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 superpowers AGENTS.md — 0 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.
What it actually says
CLAUDE.md
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.
- yesterday First seen · 1 lines · 4 tokens per session scan A 6ebdb617a810
superpowers-zh AGENTS.md is an instructions file published in the GitHub repository jnMetaCode/superpowers-zh (7,896 stars, last pushed 14d ago), licensed MIT. It adds 4 tokens to every session, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to superpowers AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
spec-kit-zh AGENTS.md
Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
mattpocock-skills-zh CLAUDE.md
Instructions for devcxl/mattpocock-skills-zh, a project described as: Matt Pocock 技能集的中文翻译版 — 地道中文，原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步.
Live-Translator-Hub AGENTS.md
Instructions for Uncle-Gao/Live-Translator-Hub, covering agents.md, commands, install all workspace dependencies (run from repo root), start the desktop app in dev mode (electron + vite hmr) and lint the desktop app.
Live-Translator-Hub CLAUDE.md
Instructions for Uncle-Gao/Live-Translator-Hub: This repository is now maintained with Codex. Keep this file only as a compatibility entry point for Claude Code.
Live-Translator-Hub GEMINI.md
Instructions for Uncle-Gao/Live-Translator-Hub: Canonical development instructions live in AGENTS.md. Keep this file only as a compatibility entry point for Gemini-based tooling.
awesome-coding-skills-cn AGENTS.md
Instructions for Wade-DevCode/awesome-coding-skills-cn, covering 核心纪律, 系统化调试, 测试驱动, 改老项目不崩 and 前端最佳实践（react/vue）.