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-allgit 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-all)<a href="https://agentmods.dev/skills/wei63w/pm-manager/pm-all"><img src="https://agentmods.dev/badge/skills/wei63w/pm-manager/pm-all/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-all"><img src="https://agentmods.dev/badge/skills/wei63w/pm-manager/pm-all.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 | $0.00940 |
| Opus 5.5 | $0.00003 | $0.00376 |
| Sonnet 5.5 | $0.00002 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
pm-all 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
--- description: Full technical governance scan; rebuild .pm/dashboard. Default does not wait on draft PRD. Use --compare-baseline only after a confirmed PRD/charter. handoffs:
- label: Status agent: pm.status prompt: Summarize after full scan send: true
User Input
$ARGUMENTS
Flags: --compare-baseline | --skip-charter-gate (default technical mode) | --modules=... | --path=... | --verbose.
Outline
Default mode is a technical debt scan. Do not block on prd.status=draft. Unconfirmed PRD/charter must not be used to judge “是否合理”.
- Gate:
.pminitialized? else block → recommend/pm-init. - Modes:
- Technical (default): scan architecture + enabled modules.
--skip-charter-gateis an alias of this default. - Baseline compare (
--compare-baseline): only ifprd.status=confirmedorcharter.status=approved. If still draft, wait and offer confirm / revise / skip / 继续技术扫描.
- Technical (default): scan architecture + enabled modules.
- Run module scans (arch, engineering, env, api, test, release, db, ops, cost) then bugs if log sources/
--path/paste exist; else skip bugs with recommendation.- Architecture step must produce diagrams and
.pm/architecture/map.json: runpm arch//pm-arch. - Module deep-scan internals live in
templates/commands/discover.md— do not tell the user to run/pm-discover.
- Architecture step must produce diagrams and
- Merge findings/todos; write
evidence/scans/pm-all-*.json. 4b. Qualified reviews: every finding written to.pm/engineering/reviews.mdMUST include reasoning + cited snippet. Unqualified rows MUST NOT enterrules.md. If there is no local diff, say there is nothing to review. Load enabled rules from.pm/engineering/rules.md. Onlydisposition=confirmedmay become rules. P0/blocking MUST interrupt; P1/P2 stay in the report. Prefer/pm-reviewfor a dedicated review pass. Full checkup is/pm-checkuponly — do not run it here by default. - Rebuild the dashboard (required):
- Prefer running:
pm dashboard(from project root) - Output:
.pm/dashboard/index.html、overview.md、findings.md、todos.md、stats.json
- Prefer running:
- Chat summary (中文): all blocking+high todos (no 3-item cap) unless
--verbose. - Closing:
_closing.md完整档；只列已生成文件。 - Finish with
/pm-statusstyle Chinese health line.
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 · 58 lines · 8 tokens per session scan A 8163139c3c2e
pm-all 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 940 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.