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/biglionx/skillhub/agents-mdgit clone --depth 1 https://github.com/BiglionX/SkillHubWhat 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 | $0.03373 | $0.03373 |
| Opus 5 | $0.01687 | $0.01687 |
| Sonnet 5 | $0.00675 | $0.00675 |
| Haiku 4.5 | $0.00337 | $0.00337 |
Grade A, and why
SkillHub 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 3d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Skill Hub 仓库指南（面向 AI 代理与人类开发者）
本文件是 AI 编码代理（DSH / DeerFlow / Claude Code / Cursor 等）进入本仓库的入口文档。 修改代码前请先通读；任何新增/变更的工程约定都应同步更新到这里。
1. 项目是什么
Skill Hub 是 ProClaw 生态的 AI 技能市场平台（"AI 时代的 npm/Docker Hub"），用于技能开发者发布、管理、变现 AI 技能包（Agent Skills，SKILL.md 标准），用户浏览、搜索、安装、付费订阅。
- 双模式：自主管理平台（用户上传技能包）+ 全球搜索引擎（GitHub API 爬取元数据）
- 参考项目：iflytek/SkillHub（Apache 2.0）、Agent Skills 标准、ClawHub CLI 协议
2. 仓库结构
apps/
web/ @skillhub/web Next.js 15 (App Router) 主站：前台/后台/API/爬虫/审核
cli/ @skillhub/cli 命令行工具：publish/install/search/import/export
packages/
search-sdk/ @skillhub/search-sdk 搜索 SDK（已实现，可发布）
widget/ @skillhub/widget 嵌入式 React 组件（已实现）
skill-validator/ @skillhub/skill-validator 技能包静态校验（zod + 内置 frontmatter 解析，含 skillhub-validate CLI）
skill-test-harness/ @skillhub/skill-test-harness 冒烟测试沙箱（隔离复制 + 任务执行 + 报告，零外部依赖）
skill-eval/ @skillhub/skill-eval 质量评分 qualityScore 0-100（LLM-as-judge + 启发式兜底）
api-client/ @skillhub/api-client 空骨架（待实现）
ui/ @skillhub/ui 空骨架（待实现）
utils/ @skillhub/utils 空骨架（待实现）
deer-flow/ vendored bytedance/deer-flow（智能体编排框架副本，仅供集成参考，不参与构建）
skills/ 仓库技能（Agent Skills 标准 SKILL.md）：repo-dev / skill-package-validator / skill-smoke-test / code-review，可被 DSH / DeerFlow / Claude Code 等 harness 加载
docs/ 开发计划 / 架构 / 集成指南
转型路线：docs/features/ONE_CLICK_INSTALL_DESKTOP_HELPER_PRD.md（v2.0，2026-08：按场景分类 + 三交付物）
.github/workflows/ CI（pnpm + turbo）
部署配置: apps/web/next.config.js（transpilePackages + standalone）、apps/web/vercel.json（Vercel）、根 Dockerfile.web + docker-compose.neon.yml + .dockerignore（Docker）、.env.production.example（env 模板）
3. 常用命令（根目录执行，pnpm workspace + turbo）
| 命令 | 作用 |
|---|---|
pnpm install |
安装全部 workspace 依赖 |
pnpm dev |
启动 web（next dev，:3000） |
pnpm build |
turbo 构建全部包 |
pnpm lint / pnpm lint:fix |
ESLint（flat config，eslint.config.js） |
pnpm typecheck |
turbo 跑各包 tsc --noEmit |
pnpm test |
turbo 跑单元测试 |
pnpm test:e2e |
Playwright E2E（apps/web/tests） |
pnpm test:cypress |
Cypress E2E（apps/web/cypress） |
pnpm db:generate / db:push / db:migrate |
Prisma（schema 在 apps/web/prisma/schema.prisma） |
pnpm ci |
完整质量门禁：lint → typecheck → test → build |
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.
- 3d ago First seen · 123 lines · 3,373 tokens per session scan A faae96b27aa8
SkillHub AGENTS.md is an instructions file published in the GitHub repository BiglionX/SkillHub (34 stars, last pushed 5d ago), licensed Apache-2.0. It adds 3,373 tokens to every session, about $0.0169 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 2026-08-30.
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.