Borrowing it
Nothing to install: this file belongs to yeuxuan/mcpane. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yeuxuan/mcpane/main/CLAUDE.mdgit clone --depth 1 https://github.com/yeuxuan/mcpaneWrote 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/yeuxuan/mcpane/claude-md)<a href="https://agentmods.dev/instructions/yeuxuan/mcpane/claude-md"><img src="https://agentmods.dev/badge/instructions/yeuxuan/mcpane/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.
<a href="https://agentmods.dev/instructions/yeuxuan/mcpane/claude-md"><img src="https://agentmods.dev/badge/instructions/yeuxuan/mcpane/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03153 | $0.03153 |
| Opus 5.5 | $0.01261 | $0.01261 |
| Sonnet 5.5 | $0.00631 | $0.00631 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade B, and why
mcpane CLAUDE.md scanned grade B 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 8d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
adapter,负责把 MCPane 的领域模型翻译成该客户端原生配置文件格式(`~/.claude/settings.json`、 How it starts
The opening of the file, as written. The whole thing — 155 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.
品牌命名冻结、协议双栈规则、Phase/Task 执行流程、密钥红线等强制工程规则见根目录
AGENTS.md——冲突时以AGENTS.md及其引用的docs/MCPane_EXECUTION_PLAN.md为准, 本文件只补充「怎么跑起来、代码长什么样」。
项目是什么
MCPane:Claude Code / Codex 与 MCP 工具的统一控制面(macOS/Windows 桌面应用)。 核心是一个本地 MCP Hub,把多个下游 MCP Server(stdio/HTTP/SSE)聚合到单一 Streamable HTTP 端点,供多个客户端(Claude Code、Codex、Claude Desktop 等)复用。
Claude Code ────┐
Codex ──────────┼─ Streamable HTTP ─→ mcpane-hub ─→ stdio / HTTP / SSE MCP Servers
兼容客户端 ─────┘ (127.0.0.1:24860/mcp)
Claude Desktop ── stdio ─→ mcpane-hub bridge ──┘
常用命令
# 前端 + 桌面(monorepo 用 pnpm workspace,仅 apps/*)
pnpm install
pnpm dev # Tauri 桌面:Vite + sidecar Hub 一起拉起
pnpm --filter @mcpane/desktop dev # 仅 Vite(不开桌面窗口,调前端用)
pnpm typecheck && pnpm lint && pnpm test && pnpm build
pnpm lint:fix # biome 自动修复
pnpm e2e # Playwright e2e(chromium+webkit,独立于 vitest)
# 单个前端测试
pnpm --filter @mcpane/desktop test -- src/lib/clients.test.ts # vitest 单文件
pnpm --filter @mcpane/desktop test -- -t "某个 test 名" # vitest 按名筛选
pnpm --filter @mcpane/desktop e2e -- e2e/servers.spec.ts # playwright 单个 spec
# Rust:根 workspace(Hub + 领域 crates,不含桌面壳)
cargo build --workspace
cargo test --workspace
cargo test -p mcpane-storage # 单 crate
cargo test -p mcpane-storage --test backup_restore # 单个集成测试文件
cargo test -p mcpane-hub-downstream some_test_name # 按名筛选
cargo run -p mcpane-hub # 单独起 Hub(仅调试 Hub 本体需要;
# tauri dev/build 会自动构建并托管 sidecar)
# Rust:桌面壳是独立的第二个 Cargo workspace(apps/desktop/src-tauri/Cargo.toml
# 里 [workspace] 为空表,与根 workspace 完全隔离),日常由 `pnpm tauri dev/build` 驱动,
# 需要单独 fmt/clippy 时:
(cd apps/desktop/src-tauri && cargo fmt --check && cargo clippy --all-targets --all-features -- -D warnings)
# 提交前建议全跑一遍(见 CONTRIBUTING.md)
cargo fmt --check
cargo clippy --workspace --all-targets --all-features -- -D warnings
cargo test --workspace --all-features
pnpm typecheck && pnpm lint && pnpm test && pnpm build && pnpm e2e && pnpm brand-scan
# target/ 清理(两个 workspace 共享依赖各编译一份,容易堆到十几 GB)
pnpm clean:target # 清 7 天前陈旧产物
pnpm clean:target --deep # 连增量缓存一起清
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.
- 8d ago First seen · 155 lines · 3,153 tokens per session scan B b7f32653be74
mcpane CLAUDE.md is an instructions file published in the GitHub repository yeuxuan/mcpane (2 stars, last pushed 9d ago), licensed MIT. It adds 3,153 tokens to every session, about $0.0126 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.
mcpane CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcpane CLAUDE.mdyeuxuan/mcpane | Instructions file | 2 | 9d ago | MIT | B | 3,153 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |