Borrowing it
Nothing to install: this file belongs to wangjialiang678/claude-omo-agentflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wangjialiang678/claude-omo-agentflow/main/CLAUDE.mdgit clone --depth 1 https://github.com/wangjialiang678/claude-omo-agentflowWrote 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/wangjialiang678/claude-omo-agentflow/claude-md)<a href="https://agentmods.dev/instructions/wangjialiang678/claude-omo-agentflow/claude-md"><img src="https://agentmods.dev/badge/instructions/wangjialiang678/claude-omo-agentflow/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.
<a href="https://agentmods.dev/instructions/wangjialiang678/claude-omo-agentflow/claude-md"><img src="https://agentmods.dev/badge/instructions/wangjialiang678/claude-omo-agentflow/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01781 | $0.01781 |
| Opus 5 | $0.00890 | $0.00890 |
| Sonnet 5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
claude-omo-agentflow 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 9d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RIPER-5 工作流规则
核心原则
本项目采用 RIPER-5 工作流，强制"调研优先，编码在后"。
模式声明要求
每次回复必须在开头声明当前模式：
[MODE: RESEARCH]- 调研阶段[MODE: INNOVATE]- 方案探索阶段[MODE: PLAN]- 规划阶段[MODE: EXECUTE]- 执行阶段[MODE: REVIEW]- 审查阶段
自动阶段判断规则
进入 RESEARCH 模式的条件（自动）
当用户消息符合以下任一条件时，必须先进入 RESEARCH 模式：
- 描述新功能需求（"实现"、"添加"、"创建" + 功能描述）
- 报告复杂 bug（"修复"、"解决" + 非显而易见的问题）
- 请求重构（"重构"、"优化"、"改进" + 模块/功能）
- 涉及你不熟悉的代码区域
- 涉及多个文件的修改
- 技术选型决策
跳过 RESEARCH 的条件（直接执行）
- 用户明确说"直接改"、"简单修复"、"快速"
- 任务明显简单（改配置、修 typo、调样式）
- 用户已提供完整实现方案
- 单文件 10 行以内的修改
RESEARCH 模式行为规范
在 RESEARCH 模式下：
1. 需求澄清（第一步）
在开始调研前，先检查需求是否清晰。如果存在以下不确定性，必须先使用 AskUserQuestion 工具询问：
- 功能的边界和范围不明确
- 存在多种技术路线可选
- 涉及用户偏好（UI风格、库选择等）
- 存在潜在的兼容性要求
- 性能/安全有特殊要求
澄清问题示例：
- "这个功能需要支持哪些边界情况？"
- "你更倾向于使用现有库还是自己实现？"
- "需要兼容哪些浏览器/环境？"
如果需求已经清晰，跳过澄清，直接进入调研。
2. 执行调研
根据任务类型选择调研方式：
| 调研类型 | 触发条件 | 工具 |
|---|---|---|
| 代码库分析 | 涉及现有代码 | Read, Grep, Glob |
| GitHub 调研 | 需要找开源方案 | gh search repos, WebFetch |
| 最佳实践 | 技术选型决策 | WebSearch, context7 |
3. 保存调研结果
- 所有调研报告保存到
.claude/memory-bank/research/对应子目录 - 文件名格式：
{task-slug}-{date}.md
4. 报告并等待确认
- 展示调研摘要（不超过 10 点关键发现）
- 明确询问："调研完成。是否进入规划阶段？还是需要补充调研？"
5. 禁止行为
- ❌ 不要写任何实现代码
- ❌ 不要做技术决策（只提供建议）
- ❌ 不要创建/修改源代码文件
PLAN 模式行为规范
进入条件：用户确认调研完成，同意进入规划
-
读取调研报告
- 从
.claude/memory-bank/research/读取相关报告
- 从
-
创建实施计划
- 保存到
.claude/memory-bank/plans/{task-slug}.md - 计划必须包含：目标、步骤清单、影响文件、测试计划、风险
- 保存到
-
等待批准
- 展示计划摘要
- 询问："计划已制定。是否批准执行？"
- 计划文件首行标记
STATUS: PENDING - 用户批准后改为
STATUS: APPROVED
EXECUTE 模式行为规范
进入条件：存在 STATUS: APPROVED 的计划文件
核心心态：林纳斯模式
目标：在最短时间内做出可运行的版本，而不是完美的产品。
遵循以下原则：
- KISS - Keep It Simple, Stupid（保持简单）
- YAGNI - You Aren't Gonna Need It（不做过度设计）
- DRY - Don't Repeat Yourself（避免重复）
- SOLID - 单一职责、开闭原则等
执行要求
-
严格按 PRD/MVP 实现
- 只做被要求的功能，不做"顺便优化"
- 以「能跑起来」为第一目标
- 有不清楚的地方立即提问确认
-
严格按计划执行
- 每完成一步，更新计划中的 checkbox
- 如需偏离计划，立即停止，返回 PLAN 模式
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.
- 9d ago First seen · 190 lines · 1,781 tokens per session scan A 7c6c8e29d613
claude-omo-agentflow CLAUDE.md is an instructions file published in the GitHub repository wangjialiang678/claude-omo-agentflow (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,781 tokens to every session, about $0.0089 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.