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/wangdabaoqq/linjun/claude-mdgit clone --depth 1 https://github.com/wangdabaoqq/LinJunWrote 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/wangdabaoqq/linjun/claude-md)<a href="https://agentmods.dev/instructions/wangdabaoqq/linjun/claude-md"><img src="https://agentmods.dev/badge/instructions/wangdabaoqq/linjun/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 | $0.03740 | $0.03740 |
| Opus 5 | $0.01870 | $0.01870 |
| Sonnet 5 | $0.00748 | $0.00748 |
| Haiku 4.5 | $0.00374 | $0.00374 |
Grade A, and why
LinJun CLAUDE.md scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const res = await axios.get(`${BASE_URL}/management/status`); Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| **进程管理** | child_process | 管理 CLIProxyAPI 二进制 | How it starts
The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
linjun - 跨平台 CLIProxyAPI 管理工具
项目概述
基于 CLIProxyAPI 构建的跨平台桌面应用,提供类似 Quotio 的功能,支持 Windows / macOS / Linux 三端。
参考项目
- Quotio - macOS 原生 Swift 实现(仅 macOS)
- CLIProxyAPI - 核心代理服务器(Go 实现)
- ProxyPilot - Windows 原生实现
- ZeroLimit - Tauri + React 实现(参考 UI 设计)
技术选型
方案:Electron + React + TypeScript
| 组件 | 技术栈 | 说明 |
|---|---|---|
| 框架 | Electron 33+ | 跨平台桌面应用框架 |
| 前端 | React 18 + TypeScript | UI 开发 |
| 样式 | Tailwind CSS | 快速 UI 开发 |
| 构建 | Vite + electron-builder | 开发构建工具链 |
| 进程管理 | child_process | 管理 CLIProxyAPI 二进制 |
| 系统托盘 | Electron Tray API | 原生托盘支持 |
Electron 优势
- 成熟生态:丰富的 npm 包支持,大量学习资源
- 开发效率:JavaScript/TypeScript 开发,热重载支持
- 跨平台一致:一套代码,三端运行
- 原生能力:完整的系统托盘、通知、菜单支持
CLIProxyAPI 集成方式
由于 CLIProxyAPI 是 Go 编写的,Electron 通过以下方式集成:
- 内嵌二进制:将 CLIProxyAPI 二进制打包到应用中
- 进程管理:使用
child_process启动/停止代理进程 - HTTP 通信:通过 Management API 与代理交互
核心功能规划
Phase 1 - MVP
- 内嵌 CLIProxyAPI 二进制,启动/停止代理服务
- 系统托盘图标 + 基础菜单
- 单账户 OAuth 登录(Claude/Gemini/OpenAI)
- 基础状态显示(运行中/已停止)
- 开机自启动
Phase 2 - 多账户管理
- 多账户管理界面
- Quota 用量追踪(实时刷新)
- 账户切换/负载均衡策略配置(Round Robin / Fill First)
- 自动 Failover 配置
Phase 3 - Agent 配置
- 自动检测已安装的 CLI Agent(Claude Code, OpenCode, Gemini CLI, Amp CLI)
- 一键配置 Agent 使用本地代理
- 配置备份/恢复
Phase 4 - 高级功能
- 请求日志查看
- 实时流量监控图表
- 多语言支持(中/英)
- 自动更新(electron-updater)
- API Key 管理
项目结构
cliPlus/
├── package.json
├── electron.vite.config.ts # Vite + Electron 配置
├── electron-builder.yml # 打包配置
├── tsconfig.json
│
├── src/
│ ├── main/ # Electron 主进程
│ │ ├── index.ts # 主进程入口
│ │ ├── tray.ts # 系统托盘
│ │ ├── proxy/ # CLIProxyAPI 管理
│ │ │ ├── manager.ts # 进程管理
│ │ │ ├── api.ts # Management API 封装
│ │ │ └── binary.ts # 二进制路径处理
│ │ ├── ipc/ # IPC 通信
│ │ │ └── handlers.ts
│ │ └── utils/
│ │ ├── store.ts # electron-store 配置存储
│ │ └── autoLaunch.ts # 开机自启动
│ │
│ ├── preload/ # 预加载脚本
│ │ └── index.ts
│ │
│ └── renderer/ # 渲染进程(React)
│ ├── index.html
│ ├── main.tsx
│ ├── App.tsx
│ ├── components/
│ │ ├── Dashboard/
│ │ ├── Providers/
│ │ ├── Agents/
│ │ ├── Quota/
│ │ └── Settings/
│ ├── hooks/
│ ├── stores/ # Zustand 状态管理
│ ├── services/ # API 调用
│ └── styles/
│
├── resources/ # 静态资源
│ ├── icon.png
│ ├── icon.ico
│ ├── icon.icns
│ └── binaries/ # CLIProxyAPI 二进制
│ ├── darwin-arm64/
│ ├── darwin-x64/
│ ├── win32-x64/
│ └── linux-x64/
│
└── scripts/
└── download-binary.ts # 下载 CLIProxyAPI 二进制
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.
- 4d ago First seen · 578 lines · 3,740 tokens per session scan A 871750f003cd
LinJun CLAUDE.md is an instructions file published in the GitHub repository wangdabaoqq/LinJun (665 stars, last pushed 15d ago), licensed MIT. It adds 3,740 tokens to every session, about $0.0187 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.