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/ethanyoq/skill-hub/agents-mdgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/agents-md)<a href="https://agentmods.dev/instructions/ethanyoq/skill-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/ethanyoq/skill-hub/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 | $0.03141 | $0.03141 |
| Opus 5 | $0.01571 | $0.01571 |
| Sonnet 5 | $0.00628 | $0.00628 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
Skill-hub 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 4d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent 上传与维护规则
本文件写给 Agent 和人类贡献者。上传或修改 skill 前，先读这份文档。 它说明了仓库架构、命名规则、索引机制、上传 checklist 和脱敏要求。 读完你应该知道：skill 放哪个目录、SKILL.md 怎么写、上传后要更新哪些索引。
1. 仓库定位与双仓库关系
Skill-hub 是面向 Codex、Claude Code、Antigravity 等 Agent 的中文技能仓库。每个 skill 是一个目录，核心文件是 SKILL.md，让 AI 编程助手在相似任务中复用稳定流程。
本仓库（个人仓库）是单一事实源，组织仓库是选择性镜像（自动同步，但排除 .github/org-exclude.txt 列出的 skill）：
| 仓库 | 地址 | 角色 | 可见性 | 贡献方式 |
|---|---|---|---|---|
| 个人仓库 | EthanYoQ/Skill-hub |
单一事实源（全部 skill） | public | 直接编辑 |
| 组织仓库 | Singularity-AI-Gamer/agent-skills |
选择性镜像（排除列表之外的 skill） | private | 通过个人仓库 PR，合并后自动镜像 |
镜像机制：个人仓库 push to mine 时，GitHub Actions 自动把排除列表之外的 skill 同步到组织仓库。新增 skill 默认同步；不想同步的两种方式：
- 傻瓜式（推荐）：在 SKILL.md frontmatter 加
org-sync: false，创建 skill 时加一行即可 - 批量排除：加路径到
.github/org-exclude.txt（适合已有 skill 的批量管理）
朋友/团队成员通过个人仓库提 PR，合并后自动镜像到组织仓库。
2. 目录架构
skills/ # 共享技能，按能力域分组
|-- 01-agent-engineering/
|-- 02-coding-languages/
|-- 03-frameworks/
|-- 06-data-search/
|-- 07-media-content/
|-- 08-writing-marketing/
`-- 10-business-industry/
projects/ # 项目私有技能（仅特定项目使用）
_meta/ # 索引（机器可读 + 人类可读）
docs/ # 约定文档（本文件、命名约定、隐私脱敏）
scripts/ # 同步与索引重建脚本
assets/ # README 使用的图标
.github/workflows/ # CI：镜像到组织仓库
3. 能力域编号
新增 skill 时先确定归属能力域。编号保证 GitHub 文件浏览器按字母序展示时也保持分组顺序。
| 编号 | 目录名 | 包含什么 |
|---|---|---|
| 01 | 01-agent-engineering |
Agent 构建、调试、自治循环、harness、提示工程、skill 生命周期 |
| 02 | 02-coding-languages |
纯语言类（编码标准、patterns、testing），按语言分子目录 |
| 03 | 03-frameworks |
具体框架 / 技术栈（Next.js、Flutter、Netlify 等） |
| 06 | 06-data-search |
数据抓取、检索、搜索、深度研究 |
| 07 | 07-media-content |
PPT、视频、PDF、Excel、Word、图像、HTML 美化、设计 |
| 08 | 08-writing-marketing |
写作、公众号、品牌、SEO |
| 10 | 10-business-industry |
行业垂直（医疗、金融、法律、物流、能源） |
分类判断优先级：xxx-patterns / xxx-testing / xxx-security 这类名字，先看 xxx 是框架名（→ 03-frameworks/<框架>/）还是语言名（→ 02-coding-languages/<语言>/）。
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.
- 4d ago First seen · 230 lines · 3,141 tokens per session scan A 2c757b9c5474
Skill-hub AGENTS.md is an instructions file published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed today), licensed MIT. It adds 3,141 tokens to every session, about $0.0157 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
Mira AGENTS.md
Instructions for byteseek/Mira, covering mira agent guide, read order, fast paths, research rules and expected artifacts.
pm-copilot AGENTS.md
Instructions for Leo-maomao/pm-copilot, covering pm copilot repository guidance, runtime loading, boundaries and verification.
specship CLAUDE.md
Instructions for bonnguyenitc/specship, covering specship — dev guide, verify every change and learnings.
PixelPilot uiux-forms.instructions.md
Multi-step forms, validation, autocomplete, and submission patterns.
PixelPilot uiux-footer.instructions.md
Footer design, links, and site information.
PixelPilot component-storybook.instructions.md
Storybook story generation skill. Load when the user asks to "generate stories", "add Storybook", "document this component", or "create stories for". Analyses React or Vue component files, extracts props, variants, and states, and outputs production-quality .stories.tsx / .stories.ts files using the project's design…