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.
git clone --depth 1 https://github.com/wei63w/pm-managerWrote 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/commands/wei63w/pm-manager/_closing)<a href="https://agentmods.dev/commands/wei63w/pm-manager/_closing"><img src="https://agentmods.dev/badge/commands/wei63w/pm-manager/_closing/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/commands/wei63w/pm-manager/_closing"><img src="https://agentmods.dev/badge/commands/wei63w/pm-manager/_closing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00410 |
| Opus 5.5 | $0.00000 | $0.00164 |
| Sonnet 5.5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
_closing 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 1mo 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.
What it actually says
收尾输出（按命令分级）
会改 .pm/ 的 /pm-* 回复必须有一句中文摘要。链接只列已经存在的文件，不要指向还没生成的路径。
用户以中文交互时，摘要、待办、评审、报告必须中文。命令名保持 /pm-*。
轻量（/pm-status / /pm-next / /pm-done / /pm-fix / /pm-check）
最多 1–2 个有效链接：
## 摘要
- <一句健康 / 刚发生了什么>
- <未关闭阻断+高优先级待办条数；正文不用三条上限>
## 打开这些（若文件存在）
- 总览: `.pm/state/overview.md`
- 看板（仅当 `.pm/dashboard/index.html` 已存在）: `.pm/dashboard/index.html`
完整（/pm-init 确认或跳过之后 / /pm-all / /pm-arch / /pm-export / /pm-review）
## 摘要
- <一句健康 / 本轮改了什么>
- <未关闭阻断+高优先级待办条数，正文列出，无三条上限>
## 打开这些（只列已生成的）
- 治理看板（浏览器）: `.pm/dashboard/index.html`
- 治理看板（IDE）: `.pm/dashboard/overview.md`
- 架构与地图: `.pm/architecture/overview.md`
- 总览 / 待办: `.pm/state/overview.md`
- PRD（草稿或已确认）: `.pm/prd/prd.md`
没有的文件不要列。明确请用户打开上面还在的链接。不要只写「完成」而不给路径。
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.
- 1mo ago First seen · 37 lines · 0 tokens per session scan A c1baf2e99553
_closing is a command published in the GitHub repository wei63w/pm-manager (88 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 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 2026-08-30.
Other commands, from other repositories
prd
Prepare work for agents: turn a request into an execution-ready issue with requirements, plan, and readiness gate.
board
Inspect, audit, configure, or reconcile a GitHub or Jira project board.
loop
Execute one authorized dispatch:claude prepared issue through executing-plans.
roadmap
Product planning chain: document the ICP, rank the backlog by revenue, and schedule dated milestones.
bug
Turn a description of something broken into a GitHub issue of type Bug. Drafts a structured report, previews it, and files it only after you confirm — typed Bug where the repo supports issue types, otherwise labelled bug.
feature
Turn a rough requirement into one execution-ready feature issue with a plan and readiness verdict.