Borrowing it
Nothing to install: this file belongs to meesii/codex-mcp. 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/meesii/codex-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/meesii/codex-mcpWrote 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/meesii/codex-mcp/agents-md)<a href="https://agentmods.dev/instructions/meesii/codex-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/meesii/codex-mcp/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.
<a href="https://agentmods.dev/instructions/meesii/codex-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/meesii/codex-mcp/agents-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 | $0.02201 | $0.02201 |
| Opus 5 | $0.01100 | $0.01100 |
| Sonnet 5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
codex-mcp 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
项目身份
- 本仓库是面向 ChatGPT 的本机 coding MCP,核心由本机 Controller、MCP Runtime、项目注册/会话绑定、OAuth/公网入口和 Web Console 组成。
- Web Console 是本机控制面,不是独立 SaaS:主要入口为
src/ui/console/**,技术栈固定为 Vue 3 + TypeScript + Element Plus + Vite。 - Controller 与 CLI 应尽量复用
src/control/services.ts等共享 service;除纯 UI 状态外,不在 Web 或 CLI 复制一套业务规则。 - 优先最小、可运行、可验证的实现;不要为了统一风格、提前抽象或顺手清技术债扩大 diff。
- 不得以“个人工具”为理由削弱已有的 OAuth、CSRF、Origin、SSRF、路径隔离、Cloudflare 所有权或持久化事务边界。
执行协议
开始修改前按顺序执行:
- 读取当前路径生效的
AGENTS.md。 - 检查
git status,区分已有脏文件和本任务改动;不要碰与任务无关的脏文件。 - 确认真正生效的 CLI → Controller → service → Runtime / Tunnel 调用链,以及 Web route → component → API → service 调用链;存在但没有入口或调用方的旧文件不能作为当前事实。
- 先检查用户需求是否存在错误前提、逻辑跳跃或信息缺失;区分事实、推测和主观判断,发现冲突直接指出。
- 涉及外部系统时确认所有权与回滚边界:Cloudflare DNS/Tunnel、OAuth client、文件系统、项目状态都不能靠名称或猜测直接覆盖/删除。
- 定义最小必要修改范围和能证明结果的最低成本验证方式,再开始修改。
- 修改过程中如果真实测试暴露新的根因,先补行为回归,再修实现;不要顺着现有代码写只会通过的测试。
生命周期不变量
project add/remove只改变项目注册状态,不隐式启动 Runtime。open只确保 Controller / Web Console 可用,不启动 Runtime。start启动 Runtime,并使用显式模式或已持久化的运行偏好;项目注册应先于 Runtime 前置校验完成。stop只停止 Runtime/Tunnel,Controller 与 Web Console 保持在线。shutdown才完全关闭 Runtime 与 Controller。- 配置状态、持久化状态和当前运行状态是不同概念;UI/CLI 不得把其中一个伪装成另一个。
- Runtime、Tunnel、Controller 的长生命周期操作必须使用各自真实 deadline;探活 timeout 不能复用于启动/停止操作。
Web Console 架构
- 页面组件负责页面编排和交互状态;网络请求统一通过
src/ui/console/api.ts,页面不得自行拼 Controller URL、CSRF 或 fetch 基础设施。 - Web 只调用 Controller API;业务语义放到共享 service,确保 CLI 与 Web 对同一操作具有一致行为。
App.vue负责全局导航、跨页面状态和生命周期;View/Component 保持局部职责,不把所有逻辑重新堆回根组件。- 外部 CLI、Runtime 或配置文件可能在页面打开期间改变状态;Web 必须有明确的状态同步策略,不能只依赖用户手动刷新。
- 异步请求、EventSource、timer、AbortController、原生文件选择等由谁创建就由谁 cleanup;组件卸载、Dialog 关闭或 Controller 替换后不得留下 owner 不明的后台任务。
- 异步旧结果不得覆盖更新后的页面状态;轮询/刷新要防并发竞态,长操作结束后再解锁相关 UI。
- 用户未保存的本地表单编辑不能被后台状态刷新静默覆盖;需要同步外部变化时先区分 server state 与 draft state。
Vue / Element Plus
- 使用 Vue Composition API 和明确 TypeScript 类型;当前规模不引入 Pinia,除非出现真实跨页面状态复杂度证明需要。
- Element Plus 使用当前按需导入方案;禁止恢复
app.use(ElementPlus)或element-plus/dist/index.css全量导入。 - 通用 Button、Dialog、Drawer、Table、Tabs、Form、Switch、Message、MessageBox 等优先 Element Plus,不再自建一套通用 UI primitives。
- 所有 Dialog/Drawer 必须有明确取消或关闭路径;异步提交期间防重复触发,同时允许用户理解当前正在做什么。
- 面向用户的默认文案使用中文;内部 PID、revision、Tunnel ID、命令等技术信息只在需要的位置展示,避免首页堆内部术语。
- 操作名称必须描述真实副作用,例如“生成并设置密码”不能写成看起来只会生成。
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.
- today First seen · 97 lines · 2,201 tokens per session scan A f4b19f221a2e
codex-mcp AGENTS.md is an instructions file published in the GitHub repository meesii/codex-mcp (21 stars, last pushed today), licensed MIT. It adds 2,201 tokens to every session, about $0.0110 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 2026-09-16.
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.
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.
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).