Borrowing it
Nothing to install: this file belongs to ianf-ai/take-ur-turn. 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/ianf-ai/take-ur-turn/main/AGENTS.mdgit clone --depth 1 https://github.com/ianf-ai/take-ur-turnWrote 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/ianf-ai/take-ur-turn/agents-md)<a href="https://agentmods.dev/instructions/ianf-ai/take-ur-turn/agents-md"><img src="https://agentmods.dev/badge/instructions/ianf-ai/take-ur-turn/agents-md.svg" alt="Measured on agentmods" 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 | $0.00978 | $0.00978 |
| Opus 5 | $0.00489 | $0.00489 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
take-ur-turn 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件给参与本仓库开发的 coding agent(Codex CLI / ZCode / Pi 等)提供项目约定。
项目简介
TUT(Take Ur Turn):多 coding agent 协作系统。核心是 Context Hub——本地 MCP Server,作为 Agent 之间的共享记忆;任务状态由记录序列派生(纯函数,写入永不因流程被拒),Notifier 轮询状态变化、按 manual/auto 模式驱动设计 → 实现 → Review → 修改的流转,人只做关键节点审批。
当前有效方案是 design/system-design.md(系统设计文档),开发以它为准。开发前必读:
design/system-design.md— 架构、状态派生规则、MCP 工具 schema、代码结构design/context-design.md— 上下文放什么、怎么管理(scope、记录类型、payload 信封与 body 模板)
技术栈
- 语言:TypeScript(Node.js ≥ 20)
- MCP SDK:@modelcontextprotocol/sdk
- 存储:当前为本地 JSON 文件(
.context-hub/目录,按 task 组织,每次写入带版本号),存储层设计为可插拔,后续可换 git/GitHub 后端 - 依赖原则:当前零运行时外部依赖(MCP SDK 除外,zod 与 SDK 并列显式声明以保单实例),不引入数据库
目录结构(约定)
take-ur-turn/
├── design/
│ ├── system-design.md # 系统设计(当前有效方案)
│ ├── context-design.md # 上下文设计(放什么、怎么管理)
├── skills/ # Agent skill 文本
├── scripts/ # 粘合脚本(信号源 / 启动器契约)
├── src/ # Context Hub 源码
├── test/ # vitest 测试
└── .context-hub/ # 运行时数据(gitignore)
开发约定
- 完成编码后必须运行测试/构建验证,不允许只改代码不验证就交差
- 状态派生规则以
design/system-design.md3.1 节的规则表为准,修改规则属于设计变更,先在 system-design.md 中更新 - MCP 工具的输入输出 schema 保持向后兼容;破坏性变更需在任务中明确说明
- 并发写入同一任务时需处理文件锁或乐观并发
- 提交信息使用英文,格式:
type: summary(如feat: add context.publish tool)
不变量(所有 Agent 必须遵守)
- 记录永不删除:
.context-hub/落盘的记录是不可变的审计材料;处置误写的正确动作是tut decide close或补一条说明 note,绝不是删文件 - 写入永不拒绝 ≠ 许可:Hub 不做流程执法是信任设计,任何 Agent 不得利用写入自由绕过人工审批门
- 预写答案的评测材料存放纪律:预先写明答案或预期结果的材料(预写答案的评测方案、含预选结果的实验材料)不得放入本仓库——Agent 会读到预写内容——存于仓库外
角色分工(多 Agent 协作时)
| 角色 | 职责 | 典型载体 |
|---|---|---|
| Architect | 需求分析、技术方案、架构决策 | Codex CLI (GPT) |
| Executor | 编码实现、按 review 反馈修改 | Pi (GLM) |
| Reviewer | 代码与方案 Review | Codex CLI (GPT) |
| Host(驱动者) | 主会话驱动:环境检查、任务发起、轮次推进、审批点汇报、异常处置——驱动不代工 | 任一主会话 Agent(ZCode / codex 等);担任时加载 skills/host.md |
各 Agent 通过 Context Hub 的 MCP 工具发布/读取上下文,不依赖手工维护的中转文件(传统 design.md / review.md 转交模式)。
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.
- 7d ago First seen · 59 lines · 978 tokens per session scan A b88a87dd44ee
take-ur-turn AGENTS.md is an instructions file published in the GitHub repository ianf-ai/take-ur-turn (1 stars, last pushed today), licensed Apache-2.0. It adds 978 tokens to every session, about $0.0049 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.
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.
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.
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).
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).
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.
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.