zhishu: Instructions file for Claude Code

CLAUDE.md

zhishu CLAUDE.md is an instructions file for Claude Code from Xuuuuu04/zhishu. It costs 3,424 tokens per session, scanned A, original, MIT.

A set of project instructions for ZhiShu, a macOS desktop application that manages several AI command-line tools in one interface. It documents the architecture, commands, tests, and module layout.

In plain words
What is it for?
Running the app, testing individual modules, packaging the desktop application, rebuilding native dependencies, and navigating its codebase.
Why use it?
It gives an agent the project-specific context needed to make changes without guessing how the application is organized or tested.

Instructions file for Claude Code

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

This is Xuuuuu04/zhishu's own configuration. It tells Claude Code how to work on zhishu 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 zhishu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Xuuuuu04/zhishu. 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/Xuuuuu04/zhishu/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Xuuuuu04/zhishu

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 zhishu CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xuuuuu04/zhishu/claude-md/github.svg)](https://agentmods.dev/instructions/xuuuuu04/zhishu/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xuuuuu04/zhishu/claude-md"><img src="https://agentmods.dev/badge/instructions/xuuuuu04/zhishu/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 zhishu CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xuuuuu04/zhishu/claude-md"><img src="https://agentmods.dev/badge/instructions/xuuuuu04/zhishu/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,424 This file is loaded in full into every session.
When invoked 3,424 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 $0.03424 $0.03424
Opus 5 $0.01712 $0.01712
Sonnet 5 $0.00685 $0.00685
Haiku 4.5 $0.00342 $0.00342

Measured 10d ago against content hash d068abf33df3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

zhishu 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 10d 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 · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 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.

智枢 ZhiShu - AI Terminal Manager

多 Agent AI 编程终端统一指挥台。在一个桌面应用内管理 Claude Code / Codex / Gemini CLI / Qwen / OpenCode / GLM / MiniMax / Kimi 等 8 款 AI CLI 工具。

技术栈: Electron 31 + React 18 + xterm.js (WebGL) + Zustand + node-pty 平台: macOS (当前唯一支持) 协议: MIT | 作者: Xuuuuu04


常用命令

npm start                 # 开发模式 (React dev server + Electron)
npm test                  # 运行所有测试 (Node.js 内置 test runner)
npm run package           # 生产构建 (.dmg/.zip/.app)
npm run verify:desktop    # 验证打包链路(不产完整安装包)
npm run rebuild-native    # 重编译 node-pty(Electron 版本更新后必须)

运行单个测试文件:

node --test electron/gitStatus.test.js
node --test electron/monitor.test.js
node --test electron/tools.test.js
node --test electron/config.test.js
node --test electron/keychain.test.js
node --test electron/pathValidator.test.js
node --test electron/fsImportExternal.test.js
node --test src/store/sessionState.test.js

架构总览

graph TB
    subgraph "Main Process (Node.js)"
        MW[BrowserWindow]
        PTY[node-pty<br/>进程管理]
        MON[Process Monitor<br/>1.5s BFS tick]
        RES[Resource Monitor<br/>CPU/MEM/BAT]
        BUF[Terminal Buffer<br/>持久化 500KB/7天]
        GIT[Git Wrapper]
        FS[FS Handlers<br/>browse/ops/image]
        CFG[Config + Keychain]
        TRAY[Tray / Menu Bar]
        HOOK[Hook Watcher<br/>Stop hook 精确通知]
        TODO[AI TODO 助手]
    end

    subgraph "IPC Bridge (contextIsolation)"
        PRE[preload.js<br/>白名单 API]
    end

    subgraph "Renderer Process (React)"
        ZS[Zustand Store]
        SB[Sidebar + 分组系统]
        TV[TerminalView + ToolSelector + ResourceBar]
        SC[SplitContainer]
        GP[GitPanel]
        FTP[FileTreePanel]
        FPP[FilePreviewPanel]
        SM[SettingsModal<br/>5-tab]
        TP[TodoPanel + AI Chat]
        CP[CommandPalette]
        TS[ToastStack]
    end

    MW --> PRE
    PTY --> PRE
    MON --> PRE
    RES --> MON
    BUF --> PRE
    GIT --> PRE
    FS --> PRE
    CFG --> PRE
    HOOK --> PRE
    TODO --> PRE
    PRE --> ZS
    ZS --> SB
    ZS --> TV
    ZS --> GP
    ZS --> FTP
    ZS --> FPP
    ZS --> SM
    ZS --> TP
    ZS --> TS
    ZS --> SC

Read the full file on GitHub · 259 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. 10d ago First seen · 259 lines · 3,424 tokens per session scan A d068abf33df3

Subscribe to this mod's changes

zhishu CLAUDE.md is an instructions file published in the GitHub repository Xuuuuu04/zhishu (3 stars, last pushed 4mo ago), licensed MIT. It adds 3,424 tokens to every session, about $0.0171 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 2026-08-31.

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

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

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