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 skills add kelegele/oh-my-pm --skill ompmgit clone --depth 1 https://github.com/kelegele/oh-my-pmWrote 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/skills/kelegele/oh-my-pm/ompm)<a href="https://agentmods.dev/skills/kelegele/oh-my-pm/ompm"><img src="https://agentmods.dev/badge/skills/kelegele/oh-my-pm/ompm/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/skills/kelegele/oh-my-pm/ompm"><img src="https://agentmods.dev/badge/skills/kelegele/oh-my-pm/ompm.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 | $0.00134 | $0.02417 |
| Opus 5 | $0.00067 | $0.01208 |
| Sonnet 5 | $0.00027 | $0.00483 |
| Haiku 4.5 | $0.00013 | $0.00242 |
Grade A, and why
ompm 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 10d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMPM 意图路由（全局前门）
Oh-My-PM 的全局入口：理解你想做什么，路由到最合适的 skill 或 workflow。
本 skill 是意图路由逻辑的唯一权威；Claude Code 的 /ompm 命令（commands/ompm.md）只是激活本 skill 的 shim。
路由判定
按以下优先级处理输入：help → workflow 直派 → 新手引导 → 模式 B 任务后导航 → 意图路由（一般规则）→ 空对话引导。
1. Help Detection
如果输入是 help 或 ?，输出下方「能力图」，然后结束。
2. Workflow 直派（兼容用法）
如果输入的第一个词是 workflow 名（quick-prd / full-pm-cycle / feature-launch），将剩余内容原样传给该 workflow 执行。
| 用法 | 示例 |
|---|---|
quick-prd "功能描述" [竞品...] |
ompm quick-prd "用户改版" 淘宝 京东 |
full-pm-cycle "产品名" [type] |
ompm full-pm-cycle "新项目管理工具" |
feature-launch "功能名" [日期] |
ompm feature-launch "注册流程" 2026-05-01 |
在 Claude Code 中以上用法对应 /ompm <workflow> ...；直接命令（不带 /ompm 前缀）等效：/quick-prd、/full-pm-cycle、/feature-launch。
3. 新手引导（首次使用）
判定：输入为"新手"、"新手入门"、"第一次用"、"guide"、"教程"等引导类请求；或无输入参数，且 docs/product/ 下完全无任何产物（首次使用的信号）→ 进入新手引导。
教程话术（输出后紧接实战，不要只发说明）：
我能交付什么
- 竞品与市场研究——摸清对手在做什么、市场往哪走
- 策略三件套——定位 → 优先级 → 路线图
- PRD——把需求落成可评审的文档
- HTML 原型——可交互的设计验证
- 发布准备——从 PRD 到上线的检查与协调
- 复盘——上线效果分析，排出下轮迭代计划
我怎么工作：你描述处境 → 我选当前最合适的一个能力直接开始做 → 你补充反馈 → 我判断下一步。每次只决定当前一步，你不需要规划全程。
怎么开始：直接说说你正在做的产品、功能，或者卡住的地方——说得乱也可以，我来整理。
教程后接续：用户描述处境后，按下方「意图路由」的规则立即路由执行，不让用户重新输入；任务完成后，用一句话告诉用户刚才使用了哪个能力，例如"刚才帮你完成的是竞品分析"。
硬性规则：
- 已在对话中出现的信息不重复提问
- 不要求用户记住任何命令——教程之后全程自然语言
- 教程用任务语言表达，不展示完整 skill 目录（完整清单只在
help时输出）
4. 意图路由（无参或自然语言输入）
无输入、或输入是一段自然语言需求描述时，执行意图路由：
Step 1 — 读取上下文：
- 当前对话上下文（用户刚才在讨论什么、已经做过什么）
docs/product/.ompm/current-workflow.json（如存在）— 进行中工作流的阶段与状态docs/product/下已有产物（PRD、定位、竞品分析、发布计划等，确认存在性即可）
Step 2 — 判断"当前最有价值的下一步"：
- 有进行中的工作流 → 继续该工作流的下一阶段（按
current_stage推断） - 需求描述模糊、关键信息缺失 → 先
clarify-requirements - 已有竞品/市场研究但无策略 →
product-strategy - 已有 PRD 但尚未发布 →
feature-launch - 明确要 PRD → 要竞品上下文用
quick-prd，直接写用prd-gen - 上线后话题（数据、反馈、下一步做什么） →
retrospective/feedback-synthesis - 都不匹配 → 按下方能力图给出 2-3 个候选，让用户选择
Step 3 — 路由并用一句话说明理由，然后激活对应 skill / workflow。例如：
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.
- 10d ago First seen · 172 lines · 134 tokens per session scan A a867bb63845d
ompm is a skill published in the GitHub repository kelegele/oh-my-pm (4 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 2,417 once invoked, about $0.0007 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 skills, from other repositories
build-flow
Autonomously build a complete Power Automate flow from a description. Use when you need to generate a full flow definition and create it.
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
route-environments
Check Power Platform environment routing status and understand default environment resolution. Use when the user asks about environment routing, developer environments, or new maker landing. Routing is configured in the admin center, not here. NOT for listing flows or managing connections.
create-flow
Guided flow creation wizard. Use when the user wants to create a new flow interactively.
manage-flows
Manage flow lifecycle - publish, test, batch operations, inventory reports. Use when the user asks to publish, test, batch manage, or get an inventory of flows.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.