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-agilegit 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-agile)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-agile"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-agile.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.02959 |
| Opus 5 | $0.00028 | $0.01479 |
| Sonnet 5 | $0.00011 | $0.00592 |
| Haiku 4.5 | $0.00006 | $0.00296 |
Grade A, and why
pm-agile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
mkdir -p docs/04-风控管理
echo "🚀 敏捷管理方案制定工具已启动"
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: 了解团队现状
使用 AskUserQuestion:
📊 团队现状评估
请选择团队的规模:
A) 小团队(2-5人) B) 中型团队(6-15人) C) 大型团队(16-30人) D) 多团队协作(30人以上)
继续询问:
🔄 敏捷成熟度评估
团队对敏捷开发的熟悉程度:
A) 初次尝试(需要详细指导) B) 有一定基础(熟悉基本概念) C) 经验丰富(可自主优化)
步骤 2: 设计迭代节奏
使用 AskUserQuestion:
⏱️ 迭代周期规划
推荐的迭代周期:
A) 1周(快速迭代,适合初创期) B) 2周(标准节奏,适合大多数团队) C) 3周(复杂项目,需要更多开发时间) D) 4周(大型项目,协调成本高)
继续询问:
📅 迭代会议规划
需要哪些迭代会议:
A) 标准会议(计划会、每日站会、评审会、复盘会) B) 精简会议(仅计划会和评审会) C) 自定义会议流程
步骤 3: 规划任务看板
使用 AskUserQuestion:
📋 任务看板类型
选择适合的看板模式:
A) 待办-进行中-已完成(基础看板) B) 待办-开发-测试-已完成(标准看板) C) 待办-分析-开发-测试-验收-已完成(详细看板) D) 自定义看板流程
步骤 4: 设计进度跟踪机制
使用 AskUserQuestion:
📈 进度跟踪频率
需要多频繁的进度跟踪:
A) 每日(每日站会 + 看板更新) B) 每周(周报 + 周会) C) 按迭代(仅在迭代结束时统计) D) 实时(自动化工具 + 仪表盘)
步骤 5: 生成敏捷管理方案
使用 Write 工具生成 docs/04-风控管理/敏捷管理方案.md。
Subagent 并行加速(v2.0.0 新增)
利用 Agent 工具并行执行独立子任务,大幅缩短总执行时间。
可并行子任务
当步骤1-4的用户信息收集完成后,以下两个任务可以并行执行:
| 子任务 | 说明 |
|---|---|
| 迭代节奏推演 | 基于团队规模和敏捷成熟度,推演最优迭代周期和会议频次 |
| 看板与追踪设计 | 根据团队偏好,设计任务看板列配置和进度跟踪机制 |
触发方式
在步骤5生成文档前,使用 Agent 工具激活子任务并行执行。
V1 vs V2 对比
| 维度 | V1.1.0(串行) | V2.0.0(Subagent并行) | 节省 |
|---|---|---|---|
| 迭代节奏推演 | 用户逐一回答4轮问题 | Agent并行分析,一步完成 | 约3轮交互 |
| 看板与追踪设计 | 依次设计看板和追踪 | Agent并行输出两个方案 | 约2轮交互 |
| 总交互轮次 | 约8-10轮 | 约4-5轮 | 减少50%+ |
| 耗时估算 | 8-12分钟 | 4-6分钟 | 节省约5分钟 |
输出文件
敏捷管理方案 → docs/04-风控管理/敏捷管理方案.md
输出文档模板
# 敏捷管理方案
## 一、团队概况
- **团队规模**: [从步骤1提取]
- **敏捷成熟度**: [从步骤1提取]
- **迭代周期**: [从步骤2提取]
- **生成时间**: [当前时间]
---
## 二、迭代节奏设计
### 2.1 迭代周期
**周期长度**: X周
**选择理由**: [说明为什么选择这个周期]
### 2.2 迭代会议安排
| 会议类型 | 频率 | 时长 | 参与者 | 目的 |
|---------|------|------|--------|------|
| 迭代计划会 | 迭代首日 | 2小时 | 全员 | 明确迭代目标与任务 |
| 每日站会 | 每日 | 15分钟 | 开发团队 | 同步进度与问题 |
| 迭代评审会 | 迭代末日 | 1小时 | 全员+stakeholder | 展示成果 |
| 迭代复盘会 | 迭代末日 | 1小时 | 全员 | 总结改进 |
---
## 三、任务看板设计
### 3.1 看板列设置
**看板类型**: [从步骤3提取]
**列定义**:
- **待办(To Do)**: 已确认但未开始的任务
- **开发中(In Progress)**: 正在开发的任务
- **测试中(Testing)**: 开发完成,等待测试
- **已完成(Done)**: 测试通过,可发布
### 3.2 任务卡片规范
每个任务卡片必须包含:
- 任务ID(如: TASK-001)
- 任务标题
- 负责人
- 预计工时
- 实际工时
- 优先级(P0/P1/P2/P3)
- 标签(如: 前端、后端、设计)
### 3.3 WIP限制
建议设置在制品限制(WIP Limit):
- 每人同时在开发的任务数 ≤ 2
- 测试队列任务数 ≤ 开发人数
---
## 四、进度跟踪机制
### 4.1 跟踪方式
**跟踪频率**: [从步骤4提取]
**跟踪指标**:
- 迭代燃尽图(Burndown Chart)
- 任务完成率
- 阻塞问题数
- 团队速率(Velocity)
### 4.2 进度报告
**日报模板**:
```markdown
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 · 392 lines · 57 tokens per session scan A 3a361af1085e
pm-agile is a skill published in the GitHub repository konglong87/superPM (62 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 2,959 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
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…