Borrowing it
Nothing to install: this file belongs to shihyuho/pangu.skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shihyuho/pangu.skill/main/AGENTS.mdgit clone --depth 1 https://github.com/shihyuho/pangu.skillWrote 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/instructions/shihyuho/pangu.skill/agents-md)<a href="https://agentmods.dev/instructions/shihyuho/pangu.skill/agents-md"><img src="https://agentmods.dev/badge/instructions/shihyuho/pangu.skill/agents-md.svg" alt="Measured on agentmods" 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 | $0.00718 | $0.00718 |
| Opus 5 | $0.00359 | $0.00359 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
pangu.skill 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 6d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repo packages paranoid text spacing (盤古之白) as an agent skill, so the skill's rules must stay faithful to pangu.js, and its own docs must not drift.
Keep the skill name canonical
The SKILL frontmatter name is the source of truth for this repository's
skill/plugin identity. Keep the first H1 and every agent-facing skill/plugin
name or display field exactly equal to it. Marketplace-level identity and UI
titles — and the pangu.skill product brand — stay independent. npm run check
enforces this contract.
The skill must match pangu.js
skills/pangu/SKILL.md documents the spacing rules as before → after
examples, pinned to pangu's real behavior: npm run check asserts every
example — and a generated behavior snapshot — against the pinned pangu
devDependency (the scripts under scripts/ document their own mechanics).
- Run
npm run checkafter editing any example or rule in SKILL.md. - CI runs it on every push / PR; Dependabot bumps
pangu, so an upstream behavior change surfaces as a failing check you then reconcile in SKILL.md. - Never hand-edit an example to a value pangu would not produce — fix the rule or the example until the check passes. The check, not your eyeballs, is the source of truth for what pangu does.
Upgrading pangu
Handling a pangu bump PR (Dependabot; the check opens red on every bump)?
That first red is mechanical until the version stamps are fixed — follow
docs/upgrading-pangu.md.
Writing CJK-mixed prose here
This is a spacing project; its own prose must model the rules. When editing CJK-mixed text (README*.md, SKILL.md wording, commit messages):
- Put one half-width space between a CJK character and an adjacent half-width letter / digit / symbol, per skills/pangu/SKILL.md.
- Use full-width punctuation in Chinese / Japanese prose（，。：；（）「」、）, not half-width.
Keep every surface in sync
The same content lives in several places. When you change install steps, the rules, the family list, the brand mark, or any user-facing wording, update ALL of them together — a change that lands in one place but not the others is drift:
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.
- 6d ago First seen · 60 lines · 718 tokens per session scan A aa40e9ab765a
pangu.skill AGENTS.md is an instructions file published in the GitHub repository shihyuho/pangu.skill (2 stars, last pushed 9d ago), licensed MIT. It adds 718 tokens to every session, about $0.0036 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.