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-retrogit 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-retro)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-retro"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-retro.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 | $0.00052 | $0.02470 |
| Opus 5 | $0.00026 | $0.01235 |
| Sonnet 5 | $0.00010 | $0.00494 |
| Haiku 4.5 | $0.00005 | $0.00247 |
Grade A, and why
pm-retro scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
mkdir -p docs/03-增长迭代/迭代复盘
echo "📝 迭代复盘工具已启动"
# 检查迭代计划
if [ -f "docs/03-增长迭代/迭代计划.md" ]; then
echo "✅ 迭代计划 - 已找到"
else
echo "⏳ 迭代计划 - 未找到"
fi
# 检查迭代完成情况
if [ -f "docs/03-增长迭代/数据报告与用户反馈.md" ]; then
echo "✅ 数据报告 - 已找到"
else
echo "⏳ 数据报告 - 未找到"
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: 复盘准备
使用 AskUserQuestion 询问:
🎯 迭代复盘准备
迭代信息:
- 迭代编号:第X次迭代
- 迭代周期:YYYY-MM-DD 至 YYYY-MM-DD
- 参与角色:产品、开发、设计、QA、运营(可多选)
迭代目标回顾:
本次迭代原定的核心目标是什么?
A) 目标1:{描述} B) 目标2:{描述} C) 目标3:{描述} D) 没有明确目标
记录到变量 ITERATION_INFO
步骤 2: 目标达成评估
📊 目标达成评估
目标1:{目标描述}
- 完成情况:{X}%
- 是否达成:✅/🟡/❌
- 说明:{完成/未完成的原因}
目标2:{目标描述}
- 完成情况:{X}%
- 是否达成:✅/🟡/❌
- 说明:{完成/未完成的原因}
整体完成率:{X}%
需求完成统计:
优先级 计划 完成 未完成 完成率 P0 X X X X% P1 X X X X% P2 X X X X% 上述数据是否准确?
步骤 3: 收集团队反馈(KPT)
使用 AskUserQuestion 收集 KPT(Keep-Problem-Try):
📝 团队反馈收集(KPT模型)
Keep - 做得好的地方(值得继续保持)
示例:
- 代码审查流程规范,Bug率降低
- 每日站会效率高
- 设计评审及时
请列举做得好的地方(每行一个,输入"完成"结束):
收集到列表 KEEP_ITEMS
Problem - 需要改进的问题
示例:
- 需求变更频繁,影响开发节奏
- 测试时间不足,线上Bug较多
- 跨部门沟通不及时
请列举需要改进的问题(每行一个,输入"完成"结束):
收集到列表 PROBLEM_ITEMS
Try - 尝试的行动方案
针对上述问题,尝试以下行动:
示例:
- 建立需求变更审批机制
- 预留20%测试缓冲时间
- 建立跨部门沟通群,每天同步进展
请列举尝试的行动(每行一个,输入"完成"结束):
收集到列表 TRY_ITEMS
步骤 4: 根因分析
对 TOP 问题(团队反馈最多的)进行根因分析:
🔍 根因分析
TOP问题:{问题描述}
5 Whys 分析:
问题:{问题} Why 1:{直接原因} Why 2:{深层原因} Why 3:{根本原因} Why 4:{系统性原因} Why 5:{根因结论}根因:{根因结论}
解决方案:
- {短期措施} - 立即执行
- {长期措施} - 持续改进
- {预防措施} - 防止复发
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.
- 8d ago First seen · 326 lines · 52 tokens per session scan A 98780c9b213e
pm-retro is a skill published in the GitHub repository konglong87/superPM (62 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 2,470 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…