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/samqin123/claude_skill_pool/claude-mdgit clone --depth 1 https://github.com/samqin123/Claude_skill_poolWrote 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/samqin123/claude_skill_pool/claude-md)<a href="https://agentmods.dev/instructions/samqin123/claude_skill_pool/claude-md"><img src="https://agentmods.dev/badge/instructions/samqin123/claude_skill_pool/claude-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 | $0.00939 | $0.00939 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
Claude_skill_pool CLAUDE.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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - 开发规范与元指令
本文件定义了 Claude Skills Pool 项目的开发规范。当你(Claude Code)被要求创建、修改或分析本仓库中的技能时,必须严格遵守以下逻辑。
1. 项目核心逻辑
这是一个 Claude Configuration Factory。每个子目录(如 skills.claude/xxx)本质上都是一个独立的配置包,旨在被复制到其他项目的根目录下作为 .claude 目录使用。
因此,所有技能必须包含标准的 .claude 目录结构。
2. 标准目录结构 (Standard Directory Structure)
当用户要求"创建一个新技能 [SkillName]"时,请初始化以下结构:
skills.claude/[SkillName]/ # 技能根目录 (建议使用英文 kebab-case)
└── .claude/
├── commands/ # 存放 Slash Command 定义
│ └── [command_name].md # 对应 /command_name
├── skills/ # 存放核心 Prompt/Skill 定义
│ └── [skill_id].md # 技能的具体实现
├── agents/ # (可选) 存放子 Agent 定义
│ └── [agent_name].md
└── settings.local.json # (可选) 局部配置文件
3. 文件格式规范
3.1 Commands (.claude/commands/*.md)
定义用户如何调用技能。通常是一个简单的 Markdown 文件,指向 Skill 或 Agent。
模板:
---
description: [简短描述这个命令的作用]
---
# [Command Name]
[详细描述命令的行为]
使用方式:
1. 确保已加载相关 skill
2. 执行逻辑...
3.2 Skills (.claude/skills/*.md)
定义技能的核心 System Prompt。这是智能的核心。
模板:
---
description: [技能描述]
---
# [Role Name]
你现在是 [角色名称]。
## 任务
[详细的任务描述]
## 约束
- [约束 1]
- [约束 2]
## 输出格式
[定义输出的 Markdown 格式]
3.3 Agents (.claude/agents/*.md)
用于定义更复杂的、有特定职责的 Agent(如 research-analyst-system 中的做法)。
4. 开发工作流 (Development Workflow)
当用户指令涉及"新建技能"或"更新技能"时,请执行以下步骤:
-
确认需求:
- 技能名称是什么?
- 希望用什么 Slash Command 触发(例如
/audit)? - 技能的核心逻辑或 Prompt 是什么?
-
创建结构:
- 在
skills.claude/下创建对应文件夹。 - 构建
.claude/commandsand.claude/skills目录。
- 在
-
生成文件:
- 编写
commands/[cmd].md: 确保它能引导用户或直接调用 Skill。 - 编写
skills/[skill].md: 根据用户需求编写高质量的 Prompt。
- 编写
-
验证:
- 检查路径是否为绝对结构:
skills.claude/[name]/.claude/...
- 检查路径是否为绝对结构:
5. 示例参考
在生成代码前,参考现有优秀的实现:
- 简单单体 Skill: 参考
skills.claude/ai-spec(包含 command 和 skill) - 复杂多 Agent 系统: 参考
skills.claude/research-analyst-system - 配置驱动型: 参考
skills.claude/ralph
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.
- 5d ago First seen · 105 lines · 939 tokens per session scan A ec3c0e669897
Claude_skill_pool CLAUDE.md is an instructions file published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 939 tokens to every session, about $0.0047 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
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.
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 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.