What is LinJun AGENTS.md?

A project guide for coding agents working on Linjun, a desktop app built with Electron, React, and TypeScript. It documents the project structure and commands for installing, developing, testing, checking, and packaging the app.

Use it when developing Linjun, running its development server with automatic reloads, checking code, running tests, or building installers for macOS, Windows, and Linux.

It gives an agent the project context and the exact commands used by the team, reducing guesswork when making or checking changes.

LinJun AGENTS.md — Instructions file by wangdabaoqq

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/wangdabaoqq/linjun/agents-md

Clone the repo

git clone --depth 1 https://github.com/wangdabaoqq/LinJun

Made for: Codex, OpenCode.

Per session 1,456 This file is loaded in full into every session.

When invoked 1,456 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.01456	$0.01456
Opus 5	$0.00728	$0.00728
Sonnet 5	$0.00291	$0.00291
Haiku 4.5	$0.00146	$0.00146

Measured 3d ago against content hash 436ba095860a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

LinJun AGENTS.md scanned grade A 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { spawn } from "child_process";

AGENTS.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - linjun Development Guide

Instructions for AI coding agents working on this Electron + React + TypeScript codebase.

Project Overview

linjun is a cross-platform desktop application for managing CLIProxyAPI, built with:

Electron 33+ - Desktop framework
React 18 - UI library
TypeScript 5 - Type safety
Vite - Build tool (via electron-vite)
Tailwind CSS - Styling

Build Commands

# Install dependencies
bun install

# Development mode (hot reload)
bun dev

# Build for production
bun run build

# Platform-specific builds
bun run build:mac      # macOS (dmg, zip)
bun run build:win      # Windows (nsis)
bun run build:linux    # Linux (AppImage, deb)
bun run build:all      # All platforms

# Download CLIProxyAPI binary
bun run download:binary

Lint & Format Commands

# Lint all files
bun run lint

# Lint with auto-fix
bun run lint:fix

# Format code with Prettier
bun run format

# Type check without emitting
bun run typecheck

Test Commands

# Run all tests
bun test

# Run tests in watch mode
bun run test:watch

# Run a single test file
bun test src/main/proxy/manager.test.ts

# Run tests matching a pattern
bun test -t "ProxyManager"

# Run with coverage
bun run test:coverage

Project Structure

src/
├── main/           # Electron main process (Node.js)
├── preload/        # Preload scripts (bridge)
└── renderer/       # React frontend (browser)

Code Style Guidelines

TypeScript

Strict mode enabled - No any types unless absolutely necessary
Explicit return types on exported functions
Interface over type for object shapes
Enums for fixed sets of values

// ✅ Good
interface ProxyStatus {
  running: boolean;
  port: number;
  uptime: number;
}

export function getStatus(): ProxyStatus {
  // ...
}

// ❌ Bad
export function getStatus(): any {
  // ...
}

Imports

Order imports in this sequence (with blank lines between groups):

Read the full file on GitHub · 266 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.

3d ago First seen · 266 lines · 1,456 tokens per session scan A 436ba095860a

Subscribe to this mod's changes

LinJun AGENTS.md is an instructions file published in the GitHub repository wangdabaoqq/LinJun (665 stars, last pushed 14d ago), licensed MIT. It adds 1,456 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

LinJun AGENTS.md