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 agentmods add skills/konglong87/superpm/pm-brainstormnpx skills add konglong87/superPM --skill pm-brainstormgit clone --depth 1 https://github.com/konglong87/superPMWrote 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/konglong87/superpm/pm-brainstorm)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-brainstorm"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-brainstorm.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.06288 |
| Opus 5 | $0.00062 | $0.03144 |
| Sonnet 5 | $0.00025 | $0.01258 |
| Haiku 4.5 | $0.00012 | $0.00629 |
Grade A, and why
pm-brainstorm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 701 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建需求调研目录
mkdir -p docs/01-需求调研
# 检查是否有需求调研报告(仅做状态告知,不做路由推荐)
if [ ! -f "docs/01-需求调研/需求调研报告.md" ]; then
echo "⚠️ 未找到需求调研报告,将进入快速模式收集基础信息"
fi
跨 Agent 交互规则
当流程要求与用户交互时:
- 如果当前环境支持 AskUserQuestion,使用 AskUserQuestion(最佳体验)。
- 如果当前环境不支持 AskUserQuestion,必须用普通聊天消息提出同样问题。
- 一次只问一个问题。
- 提问后必须停止当前回合,等待用户回答(STOP and WAIT)。
- 不得在用户回答前生成文档、调用 /pm-demand、调用 /pm-docs、写入 docs。
- 已有 docs 文件不能替代本轮用户回答。
执行流程
所有步骤均为 [MANDATORY],不得跳过任何步骤。完成当前步骤之前不得进入下一步骤。
例外:在步骤 3.3 中,用户选择 G“跳过整个挑战环节”时,跳过该环节并直接进入下个步骤。
步骤 1 [MANDATORY]: 读取前置数据
如果存在需求调研报告:
使用 Read 工具读取 docs/01-需求调研/需求调研报告.md 作为参考。
⚠️ MUST ask user to confirm: "检测到已有需求调研报告,是否适用于当前产品?"
使用 AskUserQuestion 询问:
检测到已有需求调研报告,是否适用于当前产品?
A) 适用 — 基于已有报告继续,但仍需确认关键信息是否准确 B) 不适用 / 不确定 — 进入快速模式,重新收集基础信息
跨 Agent 兜底:如果当前环境不支持 AskUserQuestion,用普通聊天消息提出同样问题,然后 STOP and WAIT for user response。
- 用户确认适用 → 提取关键信息作为参考,但仍必须使用 AskUserQuestion 向用户逐个确认:产品名称是否准确?目标用户是否准确?核心痛点是否准确?每个确认后 STOP and WAIT。
- 用户确认不适用 / 不确定 → 进入快速模式,使用 AskUserQuestion 收集基础信息。
如果没有需求调研报告:
进入快速模式,使用 AskUserQuestion 收集基础信息:
⚠️ MUST ask user 3 questions ONE AT A TIME. NEVER ask all 3 at once.
📝 快速模式 - 请提供基础信息:
问题1:产品名称是什么? → STOP and WAIT for user response
问题2:目标用户是谁? → STOP and WAIT for user response
问题3:核心痛点是什么? → STOP and WAIT for user response
跨 Agent 兜底:如果当前环境不支持 AskUserQuestion,用普通聊天消息提出同样问题,然后 STOP and WAIT for user response。
步骤 2 [MANDATORY]: 确定发散方向
使用 AskUserQuestion 询问:
⚠️ MUST ask user to choose direction. NEVER assume or skip.
🎯 我要探索产品的哪个方向?
A) 产品功能创新 - 探索核心功能、差异化特性 B) 用户增长方案 - 如何获取、激活、留存用户 C) 商业模式设计 - 如何变现、构建可持续商业模式 D) 用户体验优化 - 如何提升易用性、满意度 E) 灵感火花激发 - 我不知道做什么,需要AI帮我找灵感(v2.1新增) F) 其他方向(请手动输入)
跨 Agent 兜底:如果当前环境不支持 AskUserQuestion,用普通聊天消息提出同样问题,然后 STOP and WAIT for user response。
用户选择后,记录到变量 BRAINSTORM_DIRECTION
如果选择"灵感火花激发"(v2.1新增):
适用场景:用户不知道做什么产品,需要AI主动激发灵感
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.
- yesterday Changed · +9 lines 22f4c6c845dd
- 6d ago First seen · 692 lines · 123 tokens per session scan A bfd389c6d66a
pm-brainstorm is a skill published in the GitHub repository konglong87/superPM (61 stars, last pushed 3d ago), licensed MIT. It adds 123 tokens to every session and 6,288 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
team-tasks
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…
multi-search
智能多引擎搜索,自动检测网络环境并按优先级切换:DuckDuckGo -> Tavily -> Bing API -> Bing爬虫。支持自动配额管理和网络缓存。Invoke when user needs web search with automatic engine selection and network adaptation.
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
slack-construct-agents
Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline. Ships as instructions.md composed into the group's CLAUDE.md at spawn; there is no workflow to invoke.
clawteam
Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies, broadcast messages between agents, monitor progress via kanban board, or launch pre-built team templates (hedge-fund, code-review…