weixin_claude_code CLAUDE.md

A set of project instructions for connecting Claude Code to WeChat through an MCP adapter, a small service that lets software exchange messages and tools in a standard way.

In plain words
What is it for?
It helps developers build, run, check, and develop the adapter; handle WeChat login, logout, status, and replies; and forward messages and permission approvals.
Why use it?
It documents which part handles WeChat communication, which part handles Claude Code integration, and how permission requests and credentials are passed between them.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/dcatfly/weixin_claude_code/claude-md
Clone the repo
git clone --depth 1 https://github.com/Dcatfly/weixin_claude_code
Per session 583 This file is loaded in full into every session.
When invoked 583 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00583 $0.00583
Opus 5 $0.00292 $0.00292
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00058 $0.00058

Measured 3d ago against content hash f9137568cad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

weixin_claude_code 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 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.

CLAUDE.md · 48 lines

What it actually says

weixin-claude-code

微信 Channel for Claude Code — MCP 适配层,依赖 weixin-bot-plugin 库实现微信通信。

命令

bun run build      # 编译(bun build 打包为单文件 dist/index.js)
bun run start      # 启动 MCP 服务器(自动安装依赖)
bun run typecheck  # TypeScript 类型检查
bun run dev        # 开发模式(tsc --watch)

架构

src/
├── index.ts          # 入口:创建 WeixinBotClient + MCP Server,事件绑定 + 权限拦截
└── mcp-server.ts     # MCP Channel 服务器,注册 reply/login/logout/status 工具,权限转发

# weixin-bot-plugin    npm 包,独立微信通信库,源码在 ../weixin_bot_plugin/

本项目仅包含 Claude Code MCP 协议适配层。微信通信功能(API、认证、CDN、媒体、消息收发、poll-loop) 全部由 weixin-bot-plugin 库提供。

关键设计

  • MCP stdio 服务器,声明 claude/channel capability,消息通过 notification 推送
  • 通过 WeixinBotClient 的 EventEmitter 事件接收微信消息,转发为 MCP notification
  • 权限转发:Claude Code 权限请求 → 微信文本 → 用户回复 yes/no → 权限审批 notification
  • 权限回复拦截(PERMISSION_REPLY_RE)保留在此层,是 Claude Code 特有概念
  • 凭证存储路径通过 stateDir 配置,向后兼容 ~/.claude/channels/wechat/
  • vendor/ 目录已移至 ../weixin_bot_plugin/vendor/,本项目不再包含

插件发布

  • .claude-plugin/ 包含插件清单,.mcp.json 使用 ${CLAUDE_PLUGIN_ROOT}
  • dist/ 预编译后提交到 git,用户安装插件后无需编译
  • start 脚本中 bun install 确保运行时依赖就绪
  • bun build 会将 weixin-bot-plugin 打包进单文件,分发时不依赖外部路径

注意事项

  • contextToken 是每条消息的会话令牌,由 weixin-bot-plugin 内部管理
  • session 过期(errcode -14)后需要用户手动重新 login,不会自动恢复
  • Typing 状态由本层在收到消息时手动 start,reply 时手动 stop
Changes

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.

  1. 3d ago First seen · 48 lines · 583 tokens per session scan A f9137568cad0

Subscribe to this mod's changes

weixin_claude_code CLAUDE.md is an instructions file published in the GitHub repository Dcatfly/weixin_claude_code (57 stars, last pushed 5mo ago), licensed MIT. It adds 583 tokens to every session, about $0.0029 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens