build_a_product_agent: Instructions file for Claude Code

CLAUDE.md

build_a_product_agent CLAUDE.md is an instructions file for Claude Code from ADW-19/build_a_product_agent. It costs 2,469 tokens per session, scanned A, original, MIT.

A set of project instructions for a Chinese technical documentation repository. It explains the project structure, naming rules, writing conventions, and how to work with Markdown articles.

In plain words
What is it for?
Use it when adding or changing Chinese documentation, choosing file locations and names, or following the repository’s article-writing rules.
Why use it?
It gives the coding agent the context needed to edit the documentation consistently, even though the repository has no application code or build system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is ADW-19/build_a_product_agent's own configuration. It tells Claude Code how to work on build_a_product_agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything build_a_product_agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ADW-19/build_a_product_agent. 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/ADW-19/build_a_product_agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ADW-19/build_a_product_agent

Made for: Claude Code.

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.

agentmods badge for build_a_product_agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adw-19/build_a_product_agent/claude-md/github.svg)](https://agentmods.dev/instructions/adw-19/build_a_product_agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/adw-19/build_a_product_agent/claude-md"><img src="https://agentmods.dev/badge/instructions/adw-19/build_a_product_agent/claude-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.

agentmods 80×15 button for build_a_product_agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/adw-19/build_a_product_agent/claude-md"><img src="https://agentmods.dev/badge/instructions/adw-19/build_a_product_agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,469 This file is loaded in full into every session.
When invoked 2,469 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02469 $0.02469
Opus 5.5 $0.00988 $0.00988
Sonnet 5.5 $0.00494 $0.00494
Haiku 4.5 $0.00247 $0.00247

Measured 1mo ago against content hash e4306dac6235, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build_a_product_agent CLAUDE.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 1mo 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.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

项目本质(README 概览之外)

这是一个纯文档项目——没有源码、没有依赖、没有构建/测试命令,内容是一份面向开发者的中文技术手册,主题是"如何从零构建生产级 AI Agent 后端"。所有内容在 docs/ 下,全部为简体中文 Markdown。

唯一的"可执行部分"是 scripts/check_snippets.py(文档代码块静态校验闸门),它校验的是文档里的代码块,不是项目源码。因此本项目的"开发任务"几乎都是写/改 Markdown 文章,而非写代码。代码块只是文章内容的一部分(示例代码)。

  • 作者:Andy Yanqi Wang (ADW-19),中国,上海市,浦东新区,陆家嘴
  • 许可:MIT
  • 提交信息使用中文(如 增加AI Infra章节)
  • 英文版:根目录和 docs/01-首页/ 下有 README-en.md 落地页;正文英文版暂未发布(TBD)。新增正文无需同步英文。

目录与编号规范

docs/ 下共 4 个一级目录,按"第 N 章"连续编号展开(一章一个二级目录):

build_a_product_agent/
├── scripts/
│   └── check_snippets.py            # 文档代码块校验闸门(语法 / YAML / 语言标注 / 已弃用 API)
└── docs/
    ├── 01-首页/                     # 落地页 README(中英各一份)
    ├── 02-生产级开发-通用知识/       # 第1~4章
    │   ├── 第1章:技术选型/          # 技术栈 / 中间件 / 协议与架构模式 / 运维架构
    │   ├── 第2章:开发基本要求/      # 开发习惯(.env、Redis、async、日志、异常处理、类型注解)
    │   ├── 第3章:模块开发/          # 对话接口 / 记忆 / 工具 / 工作流 / RAG
    │   └── 第4章:Agent通路/         # 单Agent / Multi-Agent(A2A)
    ├── 03-生产级测试-系统测试/       # 第5章:系统测试
    └── 04-生产级AI Infra-基座与运维/ # 第6章:AI Infra基础知识

命名规则:

  • 一级目录:NN-中文主题名(01-首页、02-生产级开发-通用知识…)
  • 章目录:第N章:主题名
  • 文章文件:NN-标题.md,章内序号从 01 开始
  • 章内 H1 编号在每个章目录内重置:每个章目录下的文章各自用 # 第一章/第二章/…,与全局章号无关(例如"第3章:模块开发"内的文件标题是 # 第一章:对话接口、# 第二章:长期记忆与短期记忆)。不要想当然地把 H1 的"第N章"当作全局章号。
  • 文件系统目录名(含冒号 :、空格、括号)是真实路径,编写/引用时原样保留,不要改写。

文章写作规范(新增/修改文章时必须遵循)

每一篇独立成文,遵循统一模板与叙事线 工业界标准 → 为什么课堂不教 → 你应该怎么写:

  1. 开头:H1 # 第N章:主题名,紧接一行 > **核心论点**:… 引言块(用一两句话概括本章最核心的判断)。
  2. 正文:小节标题 ## 1.1 小节标题、## 1.2…(章内小节号从 1.1 递增)。
  3. 叙事结构:每个主题按 问题场景(学生/课堂典型错误代码)→ 本质原因 → 正确做法(带完整可运行代码)→ 对比表格 → 一句话总结 展开。先给错误示范再给正确做法是强约定。
  4. 表达手段:大量使用对比表格(错误做法 vs 正确做法、维度对比)、ASCII 示意图(时序/架构图)、错误代码 vs 正确代码并置。每条关键结论通常以 **一句话…:** 加粗短句收束。
  5. 示例代码:均为 Python 3.13+。Web 层用 FastAPI(async def 路由),Agent 编排用 LangGraph(StateGraph/astream_events/checkpointer),工具层用 LangChain(@tool),数据校验用 Pydantic v2,Redis 一律用 redis.asyncio,LLM 客户端用 AsyncOpenAI。
    • 基线(校对于 2026-09):Python 3.14(3.13 亦可)、FastAPI 0.141、LangGraph 1.2、LangChain 1.4、Pydantic 2.13、pymilvus 3.x。写法是"基线快照"而非版本下限——只写 ≥ 会让人误以为 API 也是旧的。
    • 禁止的已弃用写法(scripts/check_snippets.py 的 BANNED 清单会拦,改脚本时两处要保持一致):set_entry_point/set_finish_point、langgraph.prebuilt.create_react_agent、from langchain.chains|retrievers|indexes、MemorySaver、checkpointer=RedisSaver.from_conn_string(...)(它是 @contextmanager)、await httpx.post(...)、await xxx.invoke(...)、pymilvus 的 connections.connect/utility.has_collection、A2A 的 tasks/send 与 /.well-known/agent.json、Cohere rerank-multilingual-v3.0/rerank-english-v3.0、Langfuse v2 的 from langfuse.callback import 与 langfuse.trace(、RagasEvaluator。注意这里只收"照抄必然出错"的写法:/health_generate 在 SGLang 示例里是正确端点,因此不入清单。
    • 模型 ID 与单价只作占位:模型生命周期很短(gpt-4o 已于 2026-02 从 ChatGPT 退役、Azure 侧 2026-10-01 退役)。新增示例请用当前在役模型,不要引入已退役的模型 ID;价格一律标注取价日期。
  6. 收尾:章末通常有 常见踩坑清单(表格:坑/现象/原因/解法)和 本章小结(表格:要点/核心原则/一句话记住)。新文章建议沿用。
  7. 全章示例代码假设统一的项目骨架:core/(config、llm、cache、database、agent、logger、middleware 单例封装)+ routes/ + services/ + models/ + tools/ + main.py。各章代码示例互相引用这个结构(如 from core.llm import call_llm_with_retry),写新文章时保持该骨架一致,不要引入与已有章节冲突的目录约定。

Read the full file on GitHub · 77 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.

  1. 1mo ago Changed · +21 lines · +1,047 tokens per session e4306dac6235
  2. 2mo ago First seen · 56 lines · 1,422 tokens per session scan A 5e1eb98fdf47

Subscribe to this mod's changes

build_a_product_agent CLAUDE.md is an instructions file published in the GitHub repository ADW-19/build_a_product_agent (117 stars, last pushed 1mo ago), licensed MIT. It adds 2,469 tokens to every session, about $0.0099 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 2026-08-30.

Related

build_a_product_agent CLAUDE.md compared with instructions from other repositories

build_a_product_agent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
build_a_product_agent CLAUDE.mdADW-19/build_a_product_agentInstructions file1171mo agoMITA2,469Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode