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 commands/derricktang/pm-workflow-plugin/retrogit clone --depth 1 https://github.com/derricktang/pm-workflow-pluginWhat 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 | $0.00000 | $0.02176 |
| Opus 5 | $0.00000 | $0.01088 |
| Sonnet 5 | $0.00000 | $0.00435 |
| Haiku 4.5 | $0.00000 | $0.00218 |
Grade A, and why
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 2d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retro 命令（问题复盘）
命名说明：
retro即retrospective的简称（agile 团队术语,母语者常说 "run a retro on X"）。本命令的核心不是"过一遍 issue 标 done",而是从积累的已修复问题里找共性根因、沉淀机制改进,从根本上避免同类问题再次发生。历史：本命令早期叫
/issueReview,但 "review" 在编程语境太轻量（与 code review / PR review 同词,容易理解为"看一下 + 标个状态"）,且不暗示"找根因 + 防再发生"的核心目的 — 2026-05-12 改名/retro,语义更精准。
对 process_record/issues/ 中最新的未分析文件进行问题复盘：分析问题底层根因，提出工作流优化方向，等待产品总监确认优化方案后，再将文件标记为已分析。
文件定位：
process_record/issues/下的调整意见文件是产品总监在日常对话中临时提出的修改意见存档。按 CLAUDE.md「调整意见自动记录规则」，每条意见在提出的当下已由编排器派发 PM Agent 即时修复，实际成果文件已按意见调整到位。本目录仅承担事后存档作用。复盘针对已修复的历史问题：本命令是对这些已完成修复的历史调整意见做系统性复盘，目标是识别共性根因、优化工作流规范，从根本上减少同类问题发生。不再执行具体内容整改——整改在问题发生时就已完成。
与 Agent 执行方法论 X4 的关系：X4「外部反馈处置」管的是"Agent 尚未消化、需要回溯修复"的反馈（如 Supervisor 审核意见、
/changeRequest变更）；/retro处理的是"已经修复完毕、归档备查"的历史记录。两者处理的是反馈生命周期的不同阶段，职责不重叠。复盘 ≠ 整改：本命令的目标是找出问题的系统性根因并优化工作流规范，不负责执行具体调整任务。
排查类条目无需重新排查：调整意见记录中若包含排查指令（如"全局检查是否存在同类问题"），视为该排查在产品总监反馈时已完成，复盘时直接将其作为范围说明处理，无需重新执行。
文件命名规范
- 未分析：
YYYY-MM-DD_HHMM.md（无后缀） - 已分析：
YYYY-MM-DD_HHMM_analyzed.md（添加_analyzed后缀）
执行步骤
第一步：定位未分析文件
使用 Glob 工具列出 process_record/issues/ 下所有 .md 文件。
判断规则：文件名不含 _analyzed 后缀的为未分析文件；文件名含 _analyzed 后缀的为已分析文件。
取文件名排序最靠后（即最新）的未分析文件。
若不存在未分析文件，输出提示后停止：
process_record/issues/ 中没有待分析的文件。
所有调整意见均已分析完毕。
若 process_record/issues/ 目录不存在或为空，输出提示：process_record/issues/ 中暂无记录文件。
第二步：分析调整意见
使用 Read 工具读取该文件，逐条阅读调整意见表（格式参见 CLAUDE.md「调整意见自动记录规则」第一步，各列含义：# | 完整描述 | 影响成果文件 | 业务 | 功能逻辑），对所有条目进行结构化分析，识别以下维度：
-
根因分类：将各条问题归入以下类别（一条可归入多类）：
规范缺失：原型/PRD规范文档未明确该设计要求，导致PM实现时未覆盖实现偏差：规范有要求但实现时遗漏或错误需求变更：产品总监在审阅时提出的新增或调整要求（规范中原无此项）细节疏漏：局部细节未对齐（如文案、颜色、编号等）
-
影响范围：标注问题影响的业务模块和页面范围
-
共性规律：识别多条问题背后的共性系统性原因（关注 PM 执行习惯、审核遗漏模式、规范空白点等）
排查类条目的处理规则：若某条目为排查指令（如"全局检查是否存在同类问题"、"系统检查各页面操作入口"等），直接将其标注为「范围界定」类条目，说明其代表该排查已在反馈时完成、结果已体现在其他条目中，无需重新执行排查。
第三步：产出分析报告
在对话中输出完整的问题复盘报告，格式如下：
# 问题复盘报告
来源文件：process_record/issues/[文件名]
复盘时间：[今日日期]
问题总数：[N] 条
---
## 一、逐条分析
| # | 问题摘要 | 根因类别 | 分析说明 |
|---|---------|---------|---------|
| 1 | ... | ... | ... |
...
---
## 二、共性规律与根因总结
[按根因类别分组，聚焦系统性根因：PM执行习惯缺陷、审核盲区、规范空白等；举例说明哪几条问题属于同一根因]
---
## 三、工作流优化建议
[针对共性根因，提出具体可落地的工作流改进项，如：Agent规范新增条目、阶段检查清单新增项、禁止行为补充等；优先考虑能从根本上预防同类问题的规则，而非事后补救]
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.
- 2d ago First seen · 147 lines · 0 tokens per session scan A c2f87fdeed40
retro is a command published in the GitHub repository derricktang/pm-workflow-plugin (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,176 tokens. 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 2026-08-31.
Other commands, from other repositories
review
Review the selected change and report evidence.
iteration-loop
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…
harness-adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.
validate
Validate the operating-model seed — manual binding, adapter drift, adoption state, checkpoint/evidence.
init
Initialise the planning seed and record the human team, roles, and escalation channels.
learn
Capture learnings from a closed spike and optionally promote them to ADR or seed evolution. Provided by the Exploration methodology.