yoji: Instructions file for Claude Code

CLAUDE.md

yoji CLAUDE.md is an instructions file for Claude Code from wangxijie001/yoji. It costs 4,956 tokens per session, scanned A, original, MIT.

Repository instructions for a local AI-agent desktop application built with Electron, React, TypeScript, and Vite. The application uses separate main, preload, and interface processes, with the main process handling agent calls, files, and tools.

In plain words
What is it for?
Use them when developing, formatting, linting, type-checking, building, or packaging the desktop application for macOS or Windows.
Why use it?
They explain the project's process layout and development commands, helping agents place code in the correct layer and check that the application still builds and passes its checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is wangxijie001/yoji's own configuration. It tells Claude Code how to work on yoji itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yoji configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wangxijie001/yoji. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wangxijie001/yoji/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wangxijie001/yoji

Made for: Claude Code.

Wrote 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.

agentmods badge for yoji CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wangxijie001/yoji/claude-md/github.svg)](https://agentmods.dev/instructions/wangxijie001/yoji/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wangxijie001/yoji/claude-md"><img src="https://agentmods.dev/badge/instructions/wangxijie001/yoji/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.

agentmods 80×15 button for yoji CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wangxijie001/yoji/claude-md"><img src="https://agentmods.dev/badge/instructions/wangxijie001/yoji/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,956 This file is loaded in full into every session.
When invoked 4,956 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04956 $0.04956
Opus 5 $0.02478 $0.02478
Sonnet 5 $0.00991 $0.00991
Haiku 4.5 $0.00496 $0.00496

Measured 9d ago against content hash 4e55368c5948, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

yoji 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 9d 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 · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 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.

项目概述

本地 AI Agent 桌面应用。技术栈:Electron + React + TypeScript + Vite,基于 electron-vite 脚手架创建,包管理器 pnpm。

常用命令

pnpm install              # 安装依赖
pnpm dev                  # 启动开发环境(支持 HMR 热更新)
pnpm build                # 类型检查 + 构建
pnpm build:mac            # 构建并打包 macOS 应用
pnpm build:win            # 构建并打包 Windows 应用
pnpm format               # Prettier 格式化代码
pnpm lint                 # ESLint 检查
pnpm typecheck            # 运行所有 TypeScript 类型检查

三进程架构

Electron 应用由三个独立进程组成,源码分别对应 src/ 下的三个目录:

1. 主进程 (src/main/)

Node.js 环境,负责窗口创建、系统交互、IPC 通信。LangChain Agent、模型调用、文件读写、工具执行等核心逻辑全部在这里

src/main/
├── index.ts               # 入口:窗口创建 + 注册所有 IPC
├── config.ts              # 配置读写(getConfig/setConfig)
├── http.ts                # HTTP 请求工具
├── ipc/                   # IPC 处理器
│   ├── index.ts           # registerAll() 汇总注册
│   ├── agent.ts           # agent:chat / agent:chat:stream / wechat:toggle(微信连接切换)
│   ├── config.ts          # 配置 IPC(通用 config:getAll/set/delete)
│   ├── emotion.ts         # emotion:log(情绪日志查询)
│   ├── file.ts            # file:readAgentsMd / file:export / file:import
│   ├── http.ts            # HTTP IPC
│   ├── mcp.ts             # mcp:testConnection / mcp:updateMcpStoreVersion
│   ├── tts.ts             # tts:getEnabled / tts:setEnabled / tts:toggle
│   ├── broadcast.ts       # 通用广播工具(主→渲染主动推送)
│   └── browser-window.ts  # browserWindow:open(额外开无框窗口加载指定地址/应用内路由)
├── mcp/                   # MCP 客户端管理(预留)
└── agent/                 # AI Agent 核心
    ├── index.ts           # chat / chatStream(对话入口 + 流式处理)
    ├── create-agent.ts    # Agent 工厂(createAgent / getCheckpointer / companion 初始化,MCP 子 Agent 注入)
    ├── model.ts           # 模型工厂(DeepSeek / Qwen)
    ├── system-prompt.ts   # System Prompt 构建
    ├── children-agent/    # 子 Agent 定义
    │   └── mcp-execute-agent.ts  # MCP 工具执行子 Agent(SubAgent 定义 + getTools)
    ├── emotion/           # 激素情绪系统
    │   ├── schema.ts      # emotion_log 表操作(CRUD)
    │   ├── index.ts       # changeEmotion() 情绪变化引擎
    │   └── emotion_model.ts # LLM 情绪分析
    ├── tools/             # Agent 工具集(含 mcp-manage.ts MCP 管理工具)
    ├── skills/            # 内置 Skills
    ├── middleware/         # Agent 中间件
    │   ├── tool-error-handler.ts  # 工具调用容错
    │   ├── file-read-guard.ts     # 文件读取拦截:PDF→pdf-parse 提取文字、二进制拦截、兼容 DeepSeek/Qwen
    │   └── summarization.ts       # 摘要中间件
    ├── children-agent/    # 子 Agent:async/(异步任务队列 + 事件循环 executor)、sync/(同步子 Agent)、agent-list、mcp-execute-agent
    ├── task-monitor/      # 任务运行信息缓存(updateTaskRunningInfo 增量写入 / queryTaskQueue 查询;主对话与异步任务共用)
    ├── wechat-connect/    # 微信 iLink Bot 连接
    │   ├── index.ts       # toggleWechat / initWechatConnect 入口
    │   ├── request.ts     # HTTP 工具(get/post,统一 BASE_URL + 公共请求头)
    │   └── wechat-server.ts # 扫码登录、消息轮询、发送/回复、输入状态、AI 回复
    └── utils/             # checkpoint 清理(含 deleteMessageByIndex 精确删消息)、chat-history、TTS 播报、
                            # token-logger、embedding、speech(macOS 原生语音识别)、tem-file-manage(临时文件读写)

Read the full file on GitHub · 322 lines

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. 9d ago First seen · 322 lines · 4,956 tokens per session scan A 4e55368c5948

Subscribe to this mod's changes

yoji CLAUDE.md is an instructions file published in the GitHub repository wangxijie001/yoji (776 stars, last pushed 27d ago), licensed MIT. It adds 4,956 tokens to every session, about $0.0248 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

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.

vercel/next.js · 7,296 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 · 5,153 tokens

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

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

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 · 4,469 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