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/linshidream/skill-hub/agents-mdgit clone --depth 1 https://github.com/linshidream/skill-hubWhat 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 | $0.01425 | $0.01425 |
| Opus 5 | $0.00713 | $0.00713 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Hub Agent Guide
本仓库是一个面向多 Agent、企业自建 Agent 和服务器运行时的通用 skill-hub，用来沉淀“用户和 agent 在真实任务中共同探索出来的可复用能力”。这里的 skill 需要能被 Claude Code、OpenClaw、Codex、Spring AI Alibaba 应用，以及其他兼容 SKILL.md 的 agent 理解、安装、部署和运行时加载。
项目定位
- 这是 skill 仓库，不是某个单一 agent 的私有配置目录。
- 这是可构建、可发布、可部署的 Agent 能力目录，不只是 Markdown 文档集合。
- 每个 skill 都应该来自可复用的真实工作流，而不是一次性提示词。
SKILL.md必须尽量保持 agent-neutral，只描述任务目标、输入输出、流程、校验标准和必要约束。- 各 agent 的安装方式、工具差异、浏览器差异、权限差异，放到
adapters/或仓库级文档里。 - 可重复、易出错、需要稳定执行的步骤，优先放入
scripts/。 - 企业运行时默认读取部署后的稳定目录，例如
/opt/skill-hub/current/registry.json和/opt/skill-hub/current/skills/<category>/<skill-name>/SKILL.md。
Skill 分类体系
所有 skill 按照应用领域归入四个分类目录，目录结构为 skills/<category>/<skill-name>/：
| slug | 中文名 | 英文名 | 覆盖范围 |
|---|---|---|---|
dev |
开发与运维 | Development & DevOps | 项目脚手架、部署、代码组织、CI/CD、监控运维、服务管理 |
office |
办公与数据 | Office & Data | Office 文件处理、文档识别制作、数据搜索、HR/财务/运营流程优化 |
creative |
创意与媒体 | Creative & Media | 图片、视频、音频、文章排版、设计发布、媒体资源处理 |
product |
产品与设计 | Product & Design | UI/UX 设计、PRD 管理、流程图、Figma、产品语义设计 |
归类规则
- 新增 skill 时必须先确定分类，目录放入
skills/<category>/下。 - 如果一个 skill 横跨多个领域，按其主要使用场景归类，不做多分类挂载。
skill.json中的category字段值必须与所在目录的分类 slug 一致。- 空分类目录保留，不要删除——它们标识未来可用的 skill 方向。
- 分类定义在
registry.json的categories对象中维护，新增分类需同步更新本文件。
文档约定
- 根
README.md只做文件索引和通用入口，不列具体 skill 名称。 - 当前 skill 名称、发布时间、版本和功能摘要维护在
SKILL_CURRENT.md；增量发布历史维护在SKILL_RELEASES.md。 - 机器可读索引维护在
registry.json。 - 构建、部署、回滚和服务器目录说明维护在
DEPLOYMENT.md。 - 面向中文用户的正文默认用中文；
name、脚本参数、文件名、JSON key 使用英文。 SKILL.md的 frontmatter 中，name使用英文 lowercase-hyphen slug，description可用中英双语以增强不同 agent 的触发能力。
新增或更新 Skill
- 在
skills/<category>/<skill-name>/下创建或修改 skill。 - 至少包含
SKILL.md、skill.json、README.md。 - 如果流程需要稳定执行，添加
scripts/。 - 如果要支持不同 agent 的安装或执行差异，添加
adapters/。 - 如果有输入样例或输出格式，添加
examples/。 - 更新
registry.json。 - 更新
SKILL_CURRENT.md，维护一条去重后的当前版本记录。 - 更新
SKILL_RELEASES.md，记录发布时间、版本、变更类型和入口。 - 运行
python3 scripts/validate-skill.py。 - 如需发布单 skill 压缩包，运行
python3 scripts/package-skill.py <skill-name>。 - 如需发布 hub release，运行
python3 scripts/build-hub.py --release-id <release-id>。 - 发布前运行
python3 scripts/verify-release.py <artifact>。
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.
- 2d ago First seen · 85 lines · 1,425 tokens per session scan A 715887ed444d
skill-hub AGENTS.md is an instructions file published in the GitHub repository linshidream/skill-hub (19 stars, last pushed 22d ago), licensed MIT. It adds 1,425 tokens to every session, about $0.0071 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
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.
open-supermarkets AGENTS.md
Instructions for abracadabra50/open-supermarkets, covering agent integration guide, supported frameworks, quick integration, 1. add as skill and 2. agent calls commands.
GENesis-AGI AGENTS.md
AGENTS.md instructions for WingedGuardian/GENesis-AGI, covering agent instructions, code review mandate (adversarial), gitnexus — code intelligence (advisory), genesis capability surface and skills.
helm copilot-instructions.md
Instructions for PetePeter/helm, covering gamepad-cli-hub — copilot instructions, project purpose, system overview, data flow pipeline and key controls.