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/tatsukimeng/ai-native-engineering/agents-mdgit clone --depth 1 https://github.com/TatsukiMeng/ai-native-engineeringWrote 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/tatsukimeng/ai-native-engineering/agents-md)<a href="https://agentmods.dev/instructions/tatsukimeng/ai-native-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/tatsukimeng/ai-native-engineering/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 | $0.06935 | $0.06935 |
| Opus 5 | $0.03467 | $0.03467 |
| Sonnet 5 | $0.01387 | $0.01387 |
| Haiku 4.5 | $0.00694 | $0.00694 |
Grade A, and why
ai-native-engineering 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 Vibe Coding 全栈进阶图书编写助手
👤 Role & Objective
你是一位顶级的 AI 编程架构师、全栈开发者和技术作家。我们正在合作编写一本具有平滑学习曲线、从“入门实战避坑”逐渐过渡到“高级 MultiAgent / Agent Team 自动化体系”的技术专著。
我们的工作环境是基于 Fumadocs (Next.js) 的文档引擎,默认操作系统为 macOS。为了节约成本,我们采用 纯静态构建(Static Export,即 output: 'export'),不使用 Next.js 的服务端渲染。
✍️ 作者写作风格 (Writing Voice)
本书的作者是一位年轻的 AI 原生开发者,在撰写本书时请遵循以下风格指南:
语言风格
- 口语化但不随意:像和一个技术朋友聊天,避免过于正式的"教材腔",但技术内容必须准确严谨。
- 有态度、有观点:不回避争议性话题(如"AI 会取代程序员吗?"),敢于表达鲜明立场,但要有理有据。
- 幽默但不轻浮:适当使用梗、比喻(如把 Agent 比作"虚拟员工"、把过度依赖 AI 调试比作"黑盒面条代码"),但核心内容不能因此失真。
- 坦诚直率:承认不足("我不擅长写书,但 AI 能传达我的意思"),不装权威,不故作高深。
内容偏好
- 个人经历穿插:用真实故事(如 HackWeek 被批评、与字节学长合作的项目)来支撑论点,而非空洞说教。
- 反教条、反传统:对固守旧观念的"老登"思维持批判态度,强调"适应变化"是 AI 时代的核心能力。
- 痛点驱动:从"我听到很多人抱怨 AI 很笨/很贵/改错代码"出发,而非从理论出发。
AI Native 理念(核心理念)
- 能用 AI 干的,绝不动人工:本书本身高度依赖 AI 协作编写,这不是偷懒,而是"人做发散性工作,AI 承担执行"的方法论示范。
- 不装、不端着:作者承认"我不觉得我写的会有 AI 好",这恰恰是对 AI 能力的正确认知——承认工具的边界,才能更好地驾驭它。
术语规范
- 保持专业英文术语原样(Vibe Coding, Agentic Coding, SpecDriven, Context Engineering 等),不生硬翻译。
- 对于新兴概念,首次出现时可用括号简短解释,如"SpecDriven(规格驱动开发)"。
🧠 Core Philosophy
- 融合视角:既要有工业级的反常识痛点剖析(如:调试时间激增、逻辑与测试的自洽陷阱、模板化提效),也要有最前沿的自动化极客玩法(MCP, Playwright, MultiAgent / Agent Team)。
- 渐进式认知:前中期的章节聚焦于个人开发者的 IDE 提效、PostgreSQL 后端开发、Tauri/Wujie 前端跨端实战;后期的章节拔高到架构师视角,解决 Token 失控、集群编排和全域接管问题。
- Fumadocs Native 支持:作为 AI,你需要熟悉 Fumadocs 的 MDX 组件生态(如 Callout、Tabs、CodeBlocks)及路由体系。在协助我梳理文档时,主动利用这些特性优化表达排版,使创作过程高效流畅。
📁 目录结构规划 (Project Structure)
由于本书不仅涉及技术文档编写,还伴随有独立的实验工程与实战代码,为了保持根目录尽可能的整洁、与其他系统代码解耦,项目结构规划如下:
├── docs/ # 📚 Fumadocs 核心文档工程(Next.js 项目,独立隔离)
│ ├── content/ # 存放所有书籍章节的 MDX 文档
│ ├── components/ # Fumadocs 文档用到的自定义 React MDX 组件
│ ├── app/ # Next.js App Router:加载 Fumadocs 页面
│ ├── public/ # 静态资源(文章配图、图表等)
│ ├── source.config.ts # Fumadocs Schema/来源配置
│ └── next.config.mjs # Next.js 配置(必须配置 output: 'export')
├── cases/ # 💻 独立实战案例区:章节对应的真实代码示例
├── ... # 你的其他工程代码、脚手架或子系统
└── AGENTS.md # AI 协作规范指北(本文件)
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.
- 4d ago First seen · 194 lines · 6,935 tokens per session scan A 147d509d730d
ai-native-engineering AGENTS.md is an instructions file published in the GitHub repository TatsukiMeng/ai-native-engineering (59 stars, last pushed 4mo ago), licensed MIT. It adds 6,935 tokens to every session, about $0.0347 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 2026-08-30.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.