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 wei63w/pm-manager --skill pm-statusgit 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/skills/wei63w/pm-manager/pm-status)<a href="https://agentmods.dev/skills/wei63w/pm-manager/pm-status"><img src="https://agentmods.dev/badge/skills/wei63w/pm-manager/pm-status/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/wei63w/pm-manager/pm-status"><img src="https://agentmods.dev/badge/skills/wei63w/pm-manager/pm-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 6 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00008 | $0.00668 |
| Opus 5.5 | $0.00003 | $0.00267 |
| Sonnet 5.5 | $0.00002 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
pm-status 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
--- description: Show governance health, wizard next step, all open blocking/high todos, and pending review count. Primary daily entry. handoffs:
- label: Take next task agent: pm.next prompt: Claim the first blocking or high-priority todo send: true
User Input
$ARGUMENTS
Flags: --verbose (show medium/low). --full is deprecated: do not deep-scan here; tell the user to run /pm-all if they want a full technical scan.
Outline
/pm-status is a health view. Prefer not mutating module findings. You may refresh overview.md counts if stale.
- Require
.pm/config/project.yamlelse recommend/pm-init. - Prefer
pm status（会刷新并读取.pm/state/overview.md/report.md）。先报现状快照：技术栈、模块数、缺失/过期文档、待办、待处置评审、本轮意图与前几条优化建议。CLI 不可用时读overview.md+todo.md+session.json（无 3 条上限）。定位文件先pm map/map.json。复盘走/pm-journal。 - Do not run discover /
/pm-discover. Deep scan is/pm-all. - Aggregate open findings counts by severity; list blocking items.
- Show charter/outline/
prd.status. Do not treat a draft PRD/charter as the baseline. - If
reviews.mdhas rows withdispositionunset / empty /deferred, print:有 N 条待处置评审，回复 /pm-review 后用 confirm / false_positive / later。 - Default hide medium/low unless
--verbose. Add a short Chinese health sentence and how to/pm-done TODO-xxx. - Empty / first-hour: follow the wizard in
.pm/state/overview.md(confirm PRD / 轻扫 //pm-arch//pm-all). Do not say “没有待办” as if the tool is empty when the wizard still has a step. - Point to
.pm/dashboard/index.htmlonly if it exists; else say 看板尚未生成，发布前再跑/pm-all或pm dashboard. - Closing:
_closing.md轻量档（1–2 个已存在链接）。
Done When
- All open blocking/high todos listed (no 3-item cap)
- Pending reviews mentioned when N > 0
- No secret leakage in output
- Chinese health sentence when the user writes Chinese
Shared Workflow
Read-only preferred. If you refresh overview, still: map-first, redact, no auto-write of app code, graded closing.
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 · 50 lines · 8 tokens per session scan A f7fd96f9926d
pm-status is a skill published in the GitHub repository wei63w/pm-manager (87 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 668 once invoked, about $0.0000 per session on Opus 5.5. 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
ledger-tasks-yylo
Durable in-repo task state for coding agents — Kanban tasks with stable IDs, evidence-backed status marks, blocked-by dependencies, and next-ready selection. Use when starting, selecting, sequencing, or closing implementation tasks for a coding-agent project.
meeting-notes-to-tasks
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
task-decomposition
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.
citruscoastai
Guides agents to engage and transact with citruscoastai, an AI venture-operator agent, when they need hired AI labor or an agent-to-agent collaborator.
outlook-calendar
A skill for managing Microsoft Outlook and Microsoft 365 calendar events through a connected account.
cron
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/pause/resume/delete/run, and always pass --agent-id explicitly.