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 konglong87/superPM --skill pm-okrgit 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-okr)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-okr"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-okr/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/konglong87/superpm/pm-okr"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-okr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.01840 |
| Opus 5 | $0.00036 | $0.00920 |
| Sonnet 5 | $0.00014 | $0.00368 |
| Haiku 4.5 | $0.00007 | $0.00184 |
Grade A, and why
pm-okr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建增长迭代目录
mkdir -p docs/03-增长迭代
if [ -f "docs/05-产品战略/战略决策建议.md" ]; then
echo "✅ 战略决策建议 - 已找到(可承接为 O 的来源)"
else
echo "⏳ 战略决策建议 - 未找到(可选)"
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。
适用场景
- 用户说"定 OKR""目标拆解""关键结果怎么写""目标对齐""季度目标"
- 与
pm-iteration(迭代待办)区分:OKR 管方向与可度量结果,iteration 管执行排期。
OKR 基本法(简述)
- O(Objective):方向性、鼓舞人心、定性、不堆指标。
- KR(Key Result):可度量、有基线值与目标值、可验证、通常 2-4 个/每 O。
- 对齐(Cascading):公司 → 产品/团队 → 个人,下层 KR 支撑上层 O。
- 信心指数:制定时标注 50%(有挑战)/ 70%(较稳),用于复盘。
执行流程
步骤 1: 明确目标来源(主 agent - 用户交互)
使用 AskUserQuestion 询问:
🎯 OKR 范围
这次 OKR 落到哪一层?
A) 产品级 OKR(承接公司/战略) B) 团队级 OKR C) 个人/项目级 OKR
目标来源:
- 沿用战略决策建议
- 我手动输入业务重点
- 基于当前增长/数据现状推导
记录 OKR_LEVEL 与 OBJECTIVE_SOURCE。
步骤 2: 提炼 Objective(主 agent)
基于来源,提炼 1-3 个 O,要求:
- 一句话方向、鼓舞人心、不含指标
- 与战略/业务重点一致
示例:「让产品在目标用户中成为首选」「把增长引擎跑通并可持续」
使用 AskUserQuestion 与用户确认 O 的表述与数量。
步骤 3: 拆解为 Key Results(主 agent + 可选 subagent)
为每个 O 拆 2-4 个 KR,遵循:可度量 + 基线 → 目标 + 验证方式。
可选使用 Agent 工具派发 subagent 对复杂主题生成 KR 草案:
Tool: Task
Parameters:
subagent_type: "general-purpose"
description: "OKR-KR草案"
prompt: |
你是目标管理专家。为以下 Objective 拆解 Key Results。
O: {O}
上下文: {产品现状/数据}
要求:每个 O 2-4 个 KR;每个 KR 含 基线值→目标值、度量方式、信心指数(50%/70%);避免把任务当 KR。
输出 Markdown。
主 agent 整合并与用户确认。
步骤 4: 生成对齐地图与复盘节奏(主 agent)
- 对齐地图:上层 O 与下层 KR 的支撑关系
- 复盘节奏:双周打卡进度、季度复盘评分(0-1.0,0.7 为达标)
- 风险与依赖:KR 之间的依赖、资源需求
步骤 5: 生成 OKR 文档(主 agent)
使用 Write 工具生成 docs/03-增长迭代/OKR目标管理.md:
# {产品/团队} OKR({周期})
## 一、Objective 与 Key Results
### O1: {方向性目标}
- KR1: {基线} → {目标},度量: {方式},信心: {50%/70%}
- KR2: ...
### O2: {方向性目标}
- KR1: ...
## 二、对齐地图
| 上层 O | 支撑的下层 KR |
|-------|--------------|
| {公司O} | {产品KR1, KR2} |
## 三、度量与基线
| KR | 当前基线 | 目标 | 数据源 | 负责人 |
|----|---------|------|-------|-------|
| {KR} | {值} | {值} | {源} | {人} |
## 四、复盘节奏
- 双周: 进度打卡
- 季度: 评分复盘(0-1.0,0.7 达标)
## 五、依赖与风险
- 依赖: {列表}
- 风险: {列表}
## 六、下一步建议
1. /pm-iteration - 将 KR 转为迭代待办
2. /pm-retro - 季度复盘
3. /pm-report - 跟踪 KR 进度
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 · 215 lines · 72 tokens per session scan A 19d476ba4922
pm-okr is a skill published in the GitHub repository konglong87/superPM (62 stars, last pushed 5d ago), licensed MIT. It adds 72 tokens to every session and 1,840 once invoked, about $0.0004 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
A web-search helper that chooses among DuckDuckGo, Tavily, Bing API, and Bing scraping based on the available network.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
add-github
Add GitHub channel integration via Chat SDK. PR and 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…