Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/roam-bit/ai-collaboration-notebook/agents-mdgit clone --depth 1 https://github.com/roam-bit/ai-collaboration-notebookWrote 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/roam-bit/ai-collaboration-notebook/agents-md)<a href="https://agentmods.dev/instructions/roam-bit/ai-collaboration-notebook/agents-md"><img src="https://agentmods.dev/badge/instructions/roam-bit/ai-collaboration-notebook/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 | $0.08509 | $0.08509 |
| Opus 5 | $0.04254 | $0.04254 |
| Sonnet 5 | $0.01702 | $0.01702 |
| Haiku 4.5 | $0.00851 | $0.00851 |
Grade A, and why
ai-collaboration-notebook AGENTS.md scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**真相**:当场 curl 官方 `/models` 实测,现役就是用户说的 V4——我记忆里的旧名是训练截止时代的,厂商早升级了。 How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md · AI 协作错题本
本文件供 AI 助手直接读取,包含完整的协作协议 + 错题本内容。 适用于 Claude Code、Cursor、GitHub Copilot、ChatGPT 等支持 AGENTS.md 的工具。
项目地址:https://github.com/roam-bit/ai-collaboration-notebook 完整说明见 README.md;本文件 = PROTOCOL.md + MISTAKE-LOG.md 合并版。
这是什么
跟 AI 协作久了你会发现:AI 经常犯同一种错,纠正成本极高,规则越列越多但 AI 选择性遵守。
这是一套已经跑了几个月的协作机制,核心思想:
把 AI 协作当工程问题做反馈循环,不当玄学碰运气。
三层架构(v3):
┌──────────────────────────────────────────────┐
│ CLAUDE.md(自动加载层) │
│ 内嵌「核心卡」= 30 秒自检 + 17 条规则速查 │
│ + 意图路由表(按任务类型决定深读什么) │
├──────────────────────────────────────────────┤
│ PROTOCOL.md(规则层) │
│ 17 条协作规则——按路由表按需深读 │
├──────────────────────────────────────────────┤
│ MISTAKE-LOG.md(观察层,v2 内部分两档) │
│ 活跃层:根因索引 + 聚类视图(开工扫这个) │
│ 归档层:完整推理路径(复盘才读) │
│ ↑ 同根因 ≥ 3 次 → 升级到规则层 │
│ ↓ 根因休眠 2 次回顾 → 规则退役降级 │
└──────────────────────────────────────────────┘
▲ v3 新增:巡检员 agent 定期扫日志补录漏记的失误 + 记量化账本
给 AI 的使用建议:别把本文件全文当"每次开工必读"——把「30 秒自检清单」+ 下面的「17 条规则一行速查」抄进你的自动加载文件(CLAUDE.md / .cursorrules),其余按需回来查。这正是 v2 核心卡机制本身的用法。
17 条规则一行速查:
1指令模糊先问别猜 ·2见次优解主动建议 ·3技术内容配生活比喻 ·4回复末尾带 TL;DR ·5工具产出=待验证 ·6不迎合反驳必带依据 ·7事实vs推测分开 ·8提方案前先搜轮子 ·9方案选择给对比表+推荐 ·10"已X"必对应真实工具调用 ·11责任范围强制兑现 ·12视觉类需求先要参考 ·13验收归用户 ·14持久偏好立刻落盘 ·15UI完工给截图证据 ·16说"完工"前过完整验证面 ·17创意模式强发散先出demo
第一部分:协作协议(PROTOCOL.md)
这是用户(你)跟 AI 助手(Claude / Cursor / Gemini 等)协作的通用规则手册。 跨项目可复用——任何新项目都适用,只需要把这份协议链接进项目的 CLAUDE.md / .cursorrules。
🚨 开工前 30 秒自检清单(每次新任务必跑)
接到任何新任务时,30 秒内回答这 6 个问题,任何一个"不"都要停下补做:
-
数字加总验证:用户需求里有没有数字(时长 / 字数 / 预算 / 数量 / 范围)?我准备的方案里这些数字加总后等于用户给的总数吗?
-
盘点现成资源:这个需求有没有现成轮子?三个来源都查过吗?
- ① GitHub / Hacker News 开源工具
- ② AI 工具内置的专业 agent / 子代理
- ③ AI 工具自带能力(FFmpeg / Python / 系统命令等)
-
备选方案:我准备给的方案,有 ≥ 2 种备选可对比吗?还是只想到一种就直接给?
-
历史教训:上次类似任务踩过什么坑?已升级为硬规则的高频教训:动作 ≠ 结果 / 跨 agent 产出对账 / 推测当事实 / 没搜轮子 / 完工验证不彻底
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.
- 6d ago First seen · 548 lines · 8,509 tokens per session scan A afff38cdd28e
ai-collaboration-notebook AGENTS.md is an instructions file published in the GitHub repository roam-bit/ai-collaboration-notebook (129 stars, last pushed 2mo ago), licensed MIT. It adds 8,509 tokens to every session, about $0.0425 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Seo-Promt-Master GEMINI.md
Instructions for umutxyp/Seo-Promt-Master, covering seo prompt master, the short version, run the tool and ground rules.
Seo-Promt-Master copilot-instructions.md
Instructions for umutxyp/Seo-Promt-Master: This repository is a prompt-driven SEO audit-and-fix workflow with a runnable live audit tool.
Seo-Promt-Master AGENTS.md
Instructions for umutxyp/Seo-Promt-Master, covering agent instructions for this repository and before you open start.md.
embedded-api-mcp-server CLAUDE.md
Claude Code instructions for digitalsamba/embedded-api-mcp-server, covering claude.md, project overview, api reference, development commands and build & development.
SKILLS_All-in-one GEMINI.md
Gemini CLI instructions for eric861129/SKILLS_All-in-one, covering skillsall-in-one project identity, 🎯 核心目標, 🛠️ 技術棧 (tech stack), 📜 核心規範 (mandates) and 1. 內部能力規範 (elite 18 policy).
prompt-engineering-in-action CLAUDE.md
Claude Code instructions for Exponential-OS/prompt-engineering-in-action, covering prompt-engineering-in-action — agent instructions, repo structure, private repo references (anand-career-os), plugin system and skill / readme architecture (v2.2+).