What is agent-workflow CLAUDE.md?

A set of instructions for an AI coding agent working in a software repository. It explains how to track repository status, propose work through RFCs (written design documents), collaborate on changes, and add tests.

Use it to guide repository startup, plan new work, preserve other contributors’ changes, and require tests for each feature or bug fix.

It gives the agent a consistent way to understand the project before editing and prevents undocumented changes or fixes without tests.

How wangbinquan/agent-workflow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wangbinquan/agent-workflow. 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/wangbinquan/agent-workflow/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wangbinquan/agent-workflow

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wangbinquan/agent-workflow/claude-md/github.svg)](https://agentmods.dev/instructions/wangbinquan/agent-workflow/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wangbinquan/agent-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/wangbinquan/agent-workflow/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wangbinquan/agent-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/wangbinquan/agent-workflow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11,360 This file is loaded in full into every session.

When invoked 11,360 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.

Model	Per session	Once invoked
Fable 5.1	$0.11360	$0.11360
Opus 5.5	$0.04544	$0.04544
Sonnet 5.5	$0.02272	$0.02272
Haiku 4.5	$0.01136	$0.01136

Measured 4d ago against content hash 04f9354d2eaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-workflow 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 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.

CLAUDE.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 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.

RFC 开发与多 session 协作硬规则（用户 2026-10-12 明令）

本节与 AGENTS.md 同步，适用于本仓所有模型与 session，必须执行，不得自行豁免；与仓内旧流程、历史 RFC、STATE.md 或经验文档冲突时，以本节为准。

先完成全部开发和测试用例编写，再集中进行功能验证。 按已批准 RFC 的完整需求清单完成全部生产实现、接线和测试用例，再进入测试执行、功能验收、端到端验证和实现门。设计阶段的需求研究与设计门照常进行。不得自行把完整需求缩成若干小批次，写一部分代码就反复跑测试、门禁、浏览器验收或实现门，以验证循环代替剩余开发。开发期间只做必要的读码、语法与格式静态自查；不得借“自查”提前进行功能验证。集中验证发现本人缺陷后，修复并复验相关范围；候选内容未变时复用已有有效结果，不因 HEAD 前进或他人的无关提交反复重跑全量验证。
禁止发送跨 session 信息。 不得向其他独立 session / chat / thread 发消息、派活、催办、请求确认或协调发布；不得借助 send_message_to_thread、SendMessage、代理转发或其他渠道绕过。需要用户决定的阻塞只在当前会话说明，不能以“协调”为理由联系另一个 session。
允许合并提交他人的修改，禁止回退他人的代码。 提交上库允许完整保留并一起提交其他 session 的现有修改，包括共享文件中的修改及必要的关联文件；不得为剥离归属、制造干净树或让 CI 变绿，删除、覆盖、回滚、暂存移走或先撤掉再补回他人的代码。仍须明确本次提交的路径清单、检查共享 index，按路径提交；不能把未知暂存项或无关在制品不经核对一并扫入。提交说明与实际共同贡献者归属必须覆盖所提交的全部实质内容，交接时说明含有并发产出。
CI 红了先归因，再由责任 session 修复。 依据失败 job / step / 日志、确切提交差异与相关依赖判断根因；本 session 引入的问题由本 session 修复，其他 session 引入的问题保留失败证据并等待其自行修复，禁止代改、催办或回退对方代码。不能仅凭“由我 push”、失败文件名或 RFC 前缀判断责任；归属不明时在当前会话说明依据不足，不擅自认领。等待期间继续不受影响的工作，优先事件驱动等待，避免高频查询与重复验证；共享 CI 未绿时如实报告，不冒充整体通过。

Repository status

v1 已发布：M0–M5 的 81 个 issue 全部完工（STATE.md §路线图全局视图：M0 5/5、M1 18/18、M2 16/16、M3 14/14、M4 11/11、M5 12/12），发布产物由 v* tag 触发的 workflow 产出。此后所有产品 / 技术工作一律以 RFC 形式落地（design/RFC-NNN-{slug}/），见 §RFC workflow。

Read in this order at session start:

STATE.md — session-to-session execution log. Always read first; tells you what's done, what's next, current caveats.
design/plan.md — RFC 索引（编号 / 标题 / 状态；新 RFC 在此登记）+ 已完工的 M0–M5 路线图存档。这里已无待认领 issue，新工作从 RFC 开始。
design/RFC-294-backend-layered-target-architecture/ — 后台全局目标架构总纲；新 RFC 的设计必须朝它演进（见 §RFC workflow 第 8 条）。
design/proposal.md — product spec (authoritative).
design/design.md — technical design (authoritative).
proposal/init.md — original Chinese proposal, preserved for history. When it disagrees with design/*.md, design/*.md wins.
docs/dev-gotchas.md — 跨 RFC 沉淀的通用踩坑（提交纪律 / 迁移 / CI / opencode / impl-gate 经验规律 / 前端 / dev-env）。动手前扫一遍，避免重复踩坑；踩到新的通用坑也补进去（RFC-专属细节仍进各 design/RFC-XXX/）。

Read the full file on GitHub · 284 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.

4d ago Changed · +3 lines · +238 tokens per session 04f9354d2eaa
6d ago Changed · -11 tokens per session ff6d05cb9f08
24d ago Changed · +10 lines · +897 tokens per session 323393221afd
2mo ago Changed · -1 lines · +74 tokens per session c4d314aa0954
2mo ago First seen · 272 lines · 10,162 tokens per session scan A c1e250ad2aec

Subscribe to this mod's changes

agent-workflow CLAUDE.md is an instructions file published in the GitHub repository wangbinquan/agent-workflow (58 stars, last pushed today), licensed Apache-2.0. It adds 11,360 tokens to every session, about $0.0454 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.

Project management

agent-workflow CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-workflow CLAUDE.mdwangbinquan/agent-workflow	Instructions file	58	today	Apache-2.0	A	11,360	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-workflow: Instructions file for Claude Code