Borrowing it
Nothing to install: this file belongs to shengyy/agent-skills. 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/shengyy/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/shengyy/agent-skillsWrote 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/shengyy/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/shengyy/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/shengyy/agent-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/shengyy/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/shengyy/agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00908 | $0.00908 |
| Opus 5.5 | $0.00363 | $0.00363 |
| Sonnet 5.5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
agent-skills 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 22d 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.
What it actually says
agent-skills · Agent 指引
公开的 Agent Skills 合集（MIT），用 skills CLI 分发到 Claude Code、Codex、Cursor 等。提交的提示词会影响安装者的 Agent 行为；本文件存放各 Agent 共用的仓库约定，CLAUDE.md 导入本文件。
Skill 行为以各目录的 SKILL.md 为准，结构校验以 scripts/validate_skills.py 为准；其它文档作为入口，冲突时修正对应 owner。
按任务读取
| 范围 | 先读 |
|---|---|
| 派工 skill 的简报结构、分工、档位、CLI 操作与验收 | skills/codex-construction/SKILL.md |
| 新增 skill、本地试装、贡献与发版流程 | CONTRIBUTING.md |
| PR 改动说明与检查清单 | .github/pull_request_template.md |
| 仓库介绍、安装入口与文档和目录地图 | README.md、README.zh-CN.md |
| 变更记录与版本 | CHANGELOG.md、VERSION |
| 结构校验与 CI | scripts/validate_skills.py、校验 workflow |
仓库约定
- 一个 skill 一个
skills/<name>/目录，名字用小写和-连字，frontmatter 的name与目录名一致，description写清触发场景与触发词，便于 CLI 识别和 Agent 路由。脚本、参考资料、模板与素材放在该目录的scripts/、references/、assets/，用相对路径引用，让安装包自包含。 - 一个事实一个 owner，调用方链接它，减少口径漂移。同步点是版本号（
VERSION与CHANGELOG.md版本段，README 徽章读 git tag）和双语 README（两份同步更新）。 - Skill 面向当前一代模型（GPT‑6 / Claude 5+），围绕目标、边界、验收编写，判断交给模型。硬规则只留两类：不可逆的动作边界，以及模型推不出来的实测事实（CLI 契约与易错操作的精确命令）；其余写成原则和理由，担心的偏差写成「说明为什么值得」而非禁令。替代方案落地即删除旧路径，保持唯一执行路径。
- 只留最新事实：过期内容、旧口径、过程记录和已经不再是事实的旧文档、旧记录直接删除，不在仓库里留噪音，历史由 Git 追溯；文档与代码冲突时以代码为准修正文档。
SKILL.md超过 800 行先按职责拆到references/，让使用者按需读取。- 公开内容不含机密、令牌、个人路径或客户信息；安装和传播会把这些内容带到其它项目。
- Skill 行为改动记入
CHANGELOG.md的[Unreleased]，供安装者判断更新影响。
检查与协作
改动后运行 python3 scripts/validate_skills.py；CI 使用同一脚本。文档或指令改动核对本地路径与链接；安装入口改动的本地试装方法见 CONTRIBUTING.md。
中文回复，标识符、命令、路径与服务名保持英文。贡献与 PR 流程见 CONTRIBUTING.md。发版打 tag 先取得用户确认，因为 tag 对外标识可安装版本。
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.
- 22d ago Changed · +46 tokens per session 1db9cbc4c377
- 25d ago Changed · +14 lines · +250 tokens per session c07e3ed7b0b8
- 1mo ago First seen · 19 lines · 612 tokens per session scan A 953a773aef51
agent-skills AGENTS.md is an instructions file published in the GitHub repository shengyy/agent-skills (2 stars, last pushed 22d ago), licensed MIT. It adds 908 tokens to every session, about $0.0036 per session on Opus 5.5. 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 2026-09-06.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.