Borrowing it
Nothing to install: this file belongs to leemysw/agent-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/leemysw/agent-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/leemysw/agent-kitWrote 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/leemysw/agent-kit/claude-md)<a href="https://agentmods.dev/instructions/leemysw/agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/leemysw/agent-kit/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/leemysw/agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/leemysw/agent-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00884 | $0.00884 |
| Opus 5.5 | $0.00354 | $0.00354 |
| Sonnet 5.5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
agent-kit 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 2mo 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
架构概述
AI 聊天应用: FastAPI 后端 + Next.js 前端 + WebSocket 实时通信 + 多通道消息 核心目录:
agent/- Python 后端 (FastAPI, WebSocket, 数据库)agent/service/channel/- 消息通道抽象层 (WebSocket/Discord/Telegram)web/src/- Next.js 前端 (React, TypeScript, Zustand)alembic/- 数据库迁移 技术栈:- 后端: FastAPI + async SQLite + Alembic
- 前端: Next.js 14 + TypeScript + Tailwind CSS
- 实时通信: WebSocket
- 消息通道: Discord (discord.py) + Telegram (python-telegram-bot)
- AI 集成: Claude Agent SDK
核心 API
WebSocket /agent/v1/chat/ws- 实时聊天GET /agent/v1/sessions- 会话管理GET /agent/v1/sessions/{id}/messages- 消息历史
数据流: 前端 → WebSocket → FastAPI → AI 模型 → 响应 → WebSocket → 前端
配置说明
后端 (.env):
DISCORD_ENABLED/DISCORD_BOT_TOKEN/DISCORD_ALLOWED_GUILDS/DISCORD_TRIGGER_WORDTELEGRAM_ENABLED/TELEGRAM_BOT_TOKEN/TELEGRAM_ALLOWED_USERS前端 (.env.local):
开发文档索引
📚 详细指南
- 前端接口文档 - React 组件、类型定义和 API 接口
- WebSocket 流程 - WebSocket 会话和数据流
📖 技术文档
- 会话管理 - 会话创建、管理和消息处理
- 流式 vs 单次模式 - AI 响应模式对比
- 自定义工具 - 创建和使用自定义 AI 工具
- Slah 命令 - 自定义斜杠命令开发
- Skills 指南 - 技能系统使用和开发
- MCP 集成 - Model Context Protocol 集成
- 托管指南 - 生产环境部署和配置
- 权限管理 - 权限控制和安全设置
- 结构化输出 - AI 响应格式化
- 成本追踪 - API 调用成本监控
- Todo 追踪 - 任务管理和进度追踪
- 插件系统 - 插件开发和管理
代码模式
后端: 异步编程、Pydantic 模型、FastAPI 依赖注入、WebSocket 前端: Zustand 状态管理、自定义 Hooks、Radix UI + Tailwind、React Markdown
开发规范
注释使用中文
- 面对对象开发
- Always respond in 中文
- 不要过度设计，保证代码简洁易懂，简单实用
- 要注意圈复杂度，代码尽可能复用
- 注意模块设计，尽量使用设计模式
- 改动时最小化修改，尽量不修改到其他模块代码
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.
- 2mo ago First seen · 63 lines · 884 tokens per session scan A a1753be9f075
agent-kit CLAUDE.md is an instructions file published in the GitHub repository leemysw/agent-kit (57 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 884 tokens to every session, about $0.0035 per session on Opus 5.5. 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.
agent-kit CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-kit CLAUDE.mdleemysw/agent-kit | Instructions file | 57 | 7mo ago | Apache-2.0 | A | 884 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |