dev-flow: Instructions file for Claude Code

AGENTS.md

dev-flow AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from daphnee-ovo/dev-flow. It costs 1,675 tokens per session, scanned A, original, MIT.

Repository instructions for dev-flow, a project-management workflow that takes software work from idea exploration through requirements, technical specifications, tasks, development, testing, and delivery.

In plain words
What is it for?
Use them when initializing a project, exploring a requirement, writing a product requirements document, defining a technical specification, creating tasks or issues, fixing issues, testing, checking status, or preparing a release.
Why use it?
They keep the workflow, language, commands, documentation, and isolated testing rules consistent across the project’s different agents.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: UserPromptSubmit hook event, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is daphnee-ovo/dev-flow's own configuration. It tells Claude Code, Codex and OpenCode how to work on dev-flow 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 dev-flow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to daphnee-ovo/dev-flow. 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/daphnee-ovo/dev-flow/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/daphnee-ovo/dev-flow

Made for: Claude Code, Codex, OpenCode.

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 dev-flow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daphnee-ovo/dev-flow/agents-md/github.svg)](https://agentmods.dev/instructions/daphnee-ovo/dev-flow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/daphnee-ovo/dev-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/daphnee-ovo/dev-flow/agents-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 dev-flow AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daphnee-ovo/dev-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/daphnee-ovo/dev-flow/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,675 This file is loaded in full into every session.
When invoked 1,675 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 $0.01675 $0.01675
Opus 5.5 $0.00670 $0.00670
Sonnet 5.5 $0.00335 $0.00335
Haiku 4.5 $0.00168 $0.00168

Measured 2mo ago against content hash 8ad2a77aa03e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-flow 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 2mo 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.

AGENTS.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev-Flow Plugin

项目全流程管理插件,从需求探索到交付的完整生命周期管理。

Language Policy

  • Use English consistently for default workflow prompts, skill metadata, generated artifacts, build output, and new user-facing messages.
  • Keep non-English text only in explicitly localized files, such as README.zh-CN.md, or when preserving user-provided content.

注意事项

  • 禁止直接在开发环境测试导致开发环境的流程管理被污染。如需测试,需要在./tmp/test_target_project 中进行测试
  • 严禁更新 A agent 相关内容的时候导致 B agent的支持被破坏

命令

命令 作用
/init 初始化 dev-flow 项目(创建 .dev-doc、选择模式)
/brainstorm 实现前的协作式需求探索与设计
/prd 启动 PRD agent,进入需求探索阶段
/spec 启动 SPEC agent,进入技术规范阶段
/task 启动 TASK agent,进入任务拆解阶段
/issue 手动创建 issue 文件
/fix User-triggered workflow: read, claim, fix, verify, and close open issues
/test 执行 dow test 全量测试
/status 报告当前项目状态和进度
/check 执行 dow doctor 检查文档和项目状态
/iterate 迭代交付(检查 + 归档 + commit & tag + bump)
/mode 选择开发模式(full/quick/fast/mvp;audit 为自动触发)

流程

头脑风暴(BRAINSTORM) → 需求(PRD) → 规范(SPEC) → 任务(TASK) → 开发(DEV) → 测试(TEST) → 迭代(ITERATE) → 下一轮
        可选                                                  │                ↑
                                                              │  例行TEST      │
                                                              │  (任务级循环)    │ 项目TEST
                                                              └───────────────→│

dow CLI

PATH 中的 dow(默认安装路径为 ~/.local/bin/dow) 是 Rust 编写的统一调度器,所有 hook 和脚本化操作通过它执行。

子命令 作用
dow status 读取 STATUS.yaml
dow status set --phase/--mode/--exec-mode/--name/--goals-minor/--goals-major 更新 STATUS.yaml 字段
dow doctor [--fix] 统一诊断、校验并可修复 .dev-doc;dow fix 是兼容别名
dow issue list [--all] 列出 issue
dow iterate --topic <t> --type <type> [--files f1 f2...] [-v minor] [--confirm ITR-xxxxxx] 迭代交付
dow scan 项目扫描
dow task/issue/prd/spec/brainstorm/changelog schema 获取对应资源的格式定义
dow test 全量测试
dow test <TASK-ID> 执行指定 Task 关联的测试
dow archive list [--branch <b>] 列出所有归档版本
dow archive show <version> 某版本归档详情
dow archive tasks [--version v] [--priority P0] 查询归档任务
dow archive issues [--version v] [--severity P0] 查询归档 issue
dow archive doc <version> <PRD|SPEC|TEST|BRAINSTORM> 输出归档文档原文
dow archive migrate [--delete-originals] 从目录迁移到 SQLite
dow archive stats 归档统计
dow hooks context [--codex-hook] hook:注入上下文;Codex hook 使用协议 JSON envelope
dow hooks guard <file> hook:文件写入守护
dow hooks post-write <file> hook:写后联动
dow hooks save-changelog [--codex-hook] hook:保存 CHANGELOG;Codex hook 使用 Stop 协议 JSON
dow version [--set X.Y.Z] [--bump major|minor|patch] 读写 VERSION

Read the full file on GitHub · 123 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. 2mo ago First seen · 123 lines · 1,675 tokens per session scan A 8ad2a77aa03e

Subscribe to this mod's changes

dev-flow AGENTS.md is an instructions file published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 13d ago), licensed MIT. It adds 1,675 tokens to every session, about $0.0067 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 2026-08-31.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens