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/geermrc/registrytools/claude-mdgit clone --depth 1 https://github.com/GeerMrc/RegistryToolsWrote 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/geermrc/registrytools/claude-md)<a href="https://agentmods.dev/instructions/geermrc/registrytools/claude-md"><img src="https://agentmods.dev/badge/instructions/geermrc/registrytools/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 | $0.01530 | $0.01530 |
| Opus 5 | $0.00765 | $0.00765 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade C, and why
RegistryTools CLAUDE.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| **高危命令** | `rm -rf` 直接删除 | cd 到目录后逐一 rm 或用 `rm -r` | How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
快速开始
开发环境
- Python: >= 3.10（默认 conda base）
- 安装:
pip install -e ".[dev]"
常用命令
| 命令 | 说明 |
|---|---|
pytest |
运行所有测试 |
pytest tests/test_registry.py |
运行单个测试文件 |
pytest --cov=registrytools --cov-report=html |
查看测试覆盖率 |
black src/registrytools/ tests/ |
格式化代码 |
ruff check src/registrytools/ |
代码检查 |
mypy src/registrytools/ |
类型检查 |
开发流程规范
核心原则
每推进下一阶段前必须：
- 明确申明开发流程 - 引用
docs/DEVELOPMENT_WORKFLOW.md- 制定 TODO 清单 - 基于
docs/TASK.md任务追踪文档- 执行交叉验证 - 避免遗漏和技术债务累积
9 阶段开发流程
1. 需求分析 → 2. 方案设计 → 3. 任务拆解 → 4. 代码实现 →
5. 测试验证 → 6. 代码审查 → 7. Git 提交 → 8. 文档更新 → 9. 部署发布
详见: docs/DEVELOPMENT_WORKFLOW.md
禁止行为
| 禁止项 | 说明 | 替代方案 |
|---|---|---|
| 虚假审核 | 跳过验证或形式化检查 | 真实执行交叉验证清单 |
| 跨流程开发 | 跳过阶段直接提交 | 严格按 9 阶段流程执行 |
| 高危命令 | rm -rf 直接删除 |
cd 到目录后逐一 rm 或用 rm -r |
| 批量提交 | 多个阶段合并提交 TASK.md | 每阶段独立提交 TASK.md |
| 盲目创建文档 | 不检查现有文档就创建 | 先查看目录，迭代式更新 |
项目架构
核心模块
src/registrytools/
├── __main__.py # CLI 入口
├── server.py # MCP 服务器核心（965 行）
├── registry/ # 工具注册表
│ ├── models.py # 数据模型
│ └── registry.py # ToolRegistry 核心类（624 行）
├── search/ # 搜索算法
│ ├── base.py # SearchAlgorithm 抽象类
│ ├── regex_search.py
│ ├── bm25_search.py
│ └── embedding_search.py
├── storage/ # 存储层
│ ├── base.py # ToolStorage 抽象类
│ ├── json_storage.py
│ └── sqlite_storage.py
└── auth/ # API Key 认证
├── api_key.py # API Key 管理
└── middleware.py # 认证中间件
MCP 工具接口
| 工具名 | 说明 |
|---|---|
search_tools |
搜索可用工具 |
get_tool_definition |
获取工具完整定义 |
list_tools_by_category |
按类别列出 |
register_tool |
动态注册 |
unregister_tool |
注销工具 |
search_hot_tools |
快速搜索热工具（性能优化） |
代码与质量标准
详见: docs/STANDARDS.md
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 · 170 lines · 1,530 tokens per session scan C e3802540f9e3
RegistryTools CLAUDE.md is an instructions file published in the GitHub repository GeerMrc/RegistryTools (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,530 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.
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.