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/all)<a href="https://agentmods.dev/commands/wei63w/pm-manager/all"><img src="https://agentmods.dev/badge/commands/wei63w/pm-manager/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/commands/wei63w/pm-manager/all"><img src="https://agentmods.dev/badge/commands/wei63w/pm-manager/all.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 | $0.00034 | $0.00922 |
| Opus 5.5 | $0.00014 | $0.00369 |
| Sonnet 5.5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
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.
This is a copy
100% identical to pm-all — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 · 53 lines · 34 tokens per session scan A 31ad0904f19f
all is a command published in the GitHub repository wei63w/pm-manager (88 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 922 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to pm-all, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
standup
Generate a standup update based on your recent Slack activity.
spec
Start spec-driven development — write a structured specification before writing code.
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
to-done
Command "to-done" from eyaltoledano/claude-task-master, covering completing a task, pre-completion checks, execution, post-completion actions and celebration & learning.
fetch-task
Retrieve and contextualize a task from the project backlog - either specified or auto-selected next priority.
laravel
Laravel development with Eloquent, Blade, Livewire, queues, and Pest testing.