What is mcpane AGENTS.md?

Repository execution rules for MCPane, a desktop app that lets several coding clients share connections to tool servers through a local hub. They define fixed product names, identifiers, protocols, task phases, and required reporting after each task.

Use them to follow MCPane's mandated development sequence, preserve its compatibility rules, and document the result of each completed task.

They prevent incompatible naming and architecture changes and make work easier to review by requiring each task to report edits, tests, risks, and prerequisites.

How yeuxuan/mcpane configures Codex and OpenCode

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/yeuxuan/mcpane/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/yeuxuan/mcpane

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yeuxuan/mcpane/agents-md/github.svg)](https://agentmods.dev/instructions/yeuxuan/mcpane/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yeuxuan/mcpane/agents-md"><img src="https://agentmods.dev/badge/instructions/yeuxuan/mcpane/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yeuxuan/mcpane/agents-md"><img src="https://agentmods.dev/badge/instructions/yeuxuan/mcpane/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,319 This file is loaded in full into every session.

When invoked 1,319 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.

Model	Per session	Once invoked
Fable 5.1	$0.01319	$0.01319
Opus 5.5	$0.00528	$0.00528
Sonnet 5.5	$0.00264	$0.00264
Haiku 4.5	$0.00132	$0.00132

Measured 8d ago against content hash 3e37afa86418, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpane AGENTS.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 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.

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.

AGENTS.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCPane 工程执行规则（AGENTS.md）

本文件是所有 AI Agent 与人类贡献者的强制约束，内容源自 docs/MCPane_EXECUTION_PLAN.md 第 0 节，冲突时以执行计划为准。

1. 品牌与工程标识冻结

项目	冻结值
正式产品名	`MCPane`
品牌解释	`MCP + Pane / MCP Control Plane`
桌面应用显示名	`MCPane`
仓库标识	`mcpane`
Desktop 可执行标识	`mcpane`
Hub 名称与二进制	`MCP Hub` / `mcpane-hub`
兼容 Bridge	`mcpane-hub bridge` 子命令（stdio 桥；`mcpane-bridge` 为保留标识）
客户端 MCP Entry	`mcpane`
Rust crate 前缀	`mcpane-*`
TypeScript package 前缀	`@mcpane/*`
环境变量前缀	`MCPANE_*`
逻辑数据目录变量	`MCPANE_HOME`
SQLite 文件	`mcpane.db`
Keychain/Credential Service	`MCPane`
默认上游地址	`http://127.0.0.1:24860/mcp`
Tauri Bundle Identifier	`io.mcpane.desktop`（首次签名发布前最终确认）

默认应用数据目录：

macOS   ~/Library/Application Support/MCPane/
Windows %APPDATA%\MCPane\

强制规则：

新代码不得使用任何旧项目代号；
MCP Tool 的产品自带前缀统一为 mcpane__；
对外文案统一写作 MCPane，禁止其他大小写变体（详见 docs/branding/NAMING.md）；
CI 运行 scripts/brand-scan.sh 扫描品牌标识混用；
Bundle Identifier 发布后视为永久兼容标识。

2. 执行总规则

严格按 Phase 和 Task 顺序执行，不得跳过 Gate。
每次只完成一个 Task；不要顺手重构无关模块。
每个 Task 完成后必须输出：修改文件列表、实现说明、执行过的测试及结果、新增风险或未决问题、下一 Task 前置条件是否满足。
参考竞品的公开功能、交互和架构，不复制竞品源代码、函数、组件、目录或资源。
官方 MCP 规范、Claude Code 官方文档、Codex 官方文档优先级高于竞品实现。
依赖使用执行当日最新稳定且相互兼容的版本，不得使用 beta、RC、nightly 或 Git main 依赖；确认后锁定 Cargo.lock 与 pnpm-lock.yaml。
不得静默覆盖 Claude Code 或 Codex 的已有配置。
不得把 API Key、Bearer Token、OAuth Token、Cookie 或密码写入 SQLite、普通日志、测试快照或导出文件。
Rust 与 TypeScript 不允许以忽略类型错误、关闭校验或大量 unwrap() 的方式赶进度。
任何配置写入功能必须同时提交失败恢复测试。
任何 Hub 路由功能必须同时提交并发、鉴权和会话隔离测试。
无法在当前机器完成真实 Claude Code/Codex 测试时，必须明确记录"未验证"，不得伪造通过结果。

3. 协议与依赖基线

双栈协议（ADR-019）：2026-07-28 是主协议，2025-11-25 及更早版本长期并行。Hub 宣告 KNOWN_VERSIONS 全集（2024-11-05 / 2025-03-26 / 2025-06-18 / 2025-11-25 / 2026-07-28），请求哪个就给哪个。 get_info() 里的 2025-11-25 只是协商回退值，不是上限；
写代码时不得假设对端版本。按版本分叉的三处已有先例，照抄它们： HubService::is_modern(context) 判本次请求；apply_cache_hints 门控 ttlMs/cacheScope；覆写的 initialize 裁掉 legacy 的 listChanged；
新协议字段绝不能漏进 legacy 响应。rmcp 只按版本清理 resultType，我们自己填的字段（ttlMs/cacheScope/capability 项）SDK 不管，必须自己门控。守卫在 tests/http_discover.rs，改协议面的东西必跑；
rmcp 必须来自 crates.io 稳定发行版（基线 3.1.4）；
版本快照与偏差记录见 docs/architecture/DEPENDENCIES.md；
架构决策见 docs/adr/。

Read the full file on GitHub · 91 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.

8d ago First seen · 91 lines · 1,319 tokens per session scan A 3e37afa86418

Subscribe to this mod's changes

mcpane AGENTS.md is an instructions file published in the GitHub repository yeuxuan/mcpane (2 stars, last pushed 9d ago), licensed MIT. It adds 1,319 tokens to every session, about $0.0053 per session on Opus 5.5. 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 2026-10-29.

Building agents Planning ai-tools claude codex desktop-app developer-tools

mcpane AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcpane AGENTS.mdyeuxuan/mcpane	Instructions file	2	9d ago	MIT	A	1,319	Codex, OpenCode
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

mcpane: Instructions file for Codex