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-decisionnpx skills add konglong87/superPM --skill pm-decisiongit 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-decision)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-decision"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-decision.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 | $0.00056 | $0.04674 |
| Opus 5 | $0.00028 | $0.02337 |
| Sonnet 5 | $0.00011 | $0.00935 |
| Haiku 4.5 | $0.00006 | $0.00467 |
Grade A, and why
pm-decision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 661 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建目录
mkdir -p docs/05-产品战略
# 检查是否有相关前置文档
if [ -f "docs/05-产品战略/产品组合战略.md" ]; then
echo "✅ 检测到产品组合战略文档"
fi
if [ -f "docs/05-产品战略/资源分配方案.md" ]; then
echo "✅ 检测到资源分配方案文档"
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、写入 docs。
- 已有 docs 文件不能替代本轮用户回答。
执行流程
步骤 1: 明确决策问题
询问方式:使用 AskUserQuestion 逐个询问
问题 1: 决策类型
使用 AskUserQuestion 询问:
请问您面临的决策类型是?
A) 自研 vs 外包决策 B) 自研 vs 收购决策 C) 产品投资决策 D) 市场进入决策 E) 业务转型决策 F) 合作伙伴选择 G) 其他(请手动输入)
问题 2: 决策背景
询问:
请简要描述决策背景
引导用户输入:
- 决策触发因素
- 面临的问题或机会
- 决策时间要求
- 决策影响范围
问题 3: 决策约束条件
询问:
决策面临的主要约束条件是?(可多选)
A) 资金预算限制 B) 时间紧迫性 C) 技术能力限制 D) 人才资源限制 E) 风险承受能力 F) 战略一致性要求 G) 其他(请手动输入)
步骤 2: 识别决策选项
根据决策类型,识别可选方案:
场景A: 自研 vs 外包决策
可选方案:
- 完全自研
- 部分外包
- 完全外包
- 混合模式(自研核心,外包非核心)
场景B: 自研 vs 收购决策
可选方案:
- 完全自研
- 收购成熟公司
- 投资参股
- 战略合作
- 专利授权
场景C: 产品投资决策
可选方案:
- 重大投资(全力以赴)
- 中等投资(稳健推进)
- 小额试探(快速验证)
- 暂不投资(观望等待)
步骤 3: 决策矩阵评估
对每个决策选项,进行多维度评估:
评估维度定义:
询问:
请选择决策评估维度
推荐维度:
- 财务维度:成本、收益、ROI
- 时间维度:上市时间、开发周期
- 技术维度:技术风险、技术可控性
- 战略维度:战略一致性、竞争优势
- 资源维度:人力需求、资金需求
- 风险维度:市场风险、技术风险、执行风险
逐项评估:
针对每个维度,使用 AskUserQuestion 询问每个选项的得分(1-10分):
示例(自研 vs 外包):
请为"完全自研"方案在"财务成本"维度打分(1-10分,分数越低成本越高)
A) 1-2分(成本极高) B) 3-4分(成本较高) C) 5-6分(成本适中) D) 7-8分(成本较低) E) 9-10分(成本极低)
依次评估所有选项、所有维度。
权重设定:
询问:
各评估维度的权重如何分配?
引导用户分配权重(总和100%):
| 维度 | 权重 |
|---|---|
| 财务成本 | [X]% |
| 上市时间 | [X]% |
| 技术风险 | [X]% |
| 战略一致性 | [X]% |
| 长期竞争力 | [X]% |
| 合计 | 100% |
步骤 4: 决策树分析
针对复杂决策,构建决策树:
决策树构建:
询问关键决策节点:
决策的关键不确定性因素是什么?
示例:
- 市场需求是否达标?(概率:[X]%)
- 技术难题能否攻克?(概率:[X]%)
- 竞品是否会提前入场?(概率:[X]%)
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.
- 6d ago First seen · 661 lines · 56 tokens per session scan A f399c4ff8c80
pm-decision is a skill published in the GitHub repository konglong87/superPM (61 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 4,674 once invoked, about $0.0003 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
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.
freeride
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
deepsafe-scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced…
mapick
Mapick — Skill recommendation & privacy protection for OpenClaw. Scans your local skills, suggests what you're missing, and keeps other skills from seeing your sensitive data.
douyin-upload-mcp-skill
通过抖音创作者平台(creator.douyin.com)发布视频和图文内容。首选调用 MCP 工具完成操作,MCP 无法满足时可运行 Skill 脚本兜底。禁止自行启动外部浏览器访问抖音。.
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…