A health check and repair command for the .pm project-management records stored in a repository.

Use it to diagnose project metadata and, when asked, restore missing scaffolding, rebuild the architecture map or dashboard, and preserve a backup of readable audit data.

It detects missing files, invalid audit records, unreadable architecture maps, outdated document indexes, and reviews still awaiting a decision without silently replacing confirmed content.

pm-check — Command for coding agents by wei63w: A health check and repair command for the .pm…

Install

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.

agentmods

npx agentmods add commands/wei63w/pm-manager/pm-check

Clone the repo

git clone --depth 1 https://github.com/wei63w/pm-manager

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/wei63w/pm-manager/pm-check.svg)](https://agentmods.dev/commands/wei63w/pm-manager/pm-check)

Your own site

<a href="https://agentmods.dev/commands/wei63w/pm-manager/pm-check"><img src="https://agentmods.dev/badge/commands/wei63w/pm-manager/pm-check.svg" alt="Measured on agentmods" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 470 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00031	$0.00470
Opus 5	$0.00015	$0.00235
Sonnet 5	$0.00006	$0.00094
Haiku 4.5	$0.00003	$0.00047

Measured 4d ago against content hash 76d622819348, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-check 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

check — 100% identical, 0 lines differ

adapters/claude-code/commands/pm-check.md · 42 lines

What it actually says

User Input

$ARGUMENTS

Accepted: repair | empty (diagnose only).

Outline

/pm-check is the recovery command. Prefer pm check from the project root and explain the table in Chinese.

If .pm/ is missing: block → 请先 /pm-init 或 pm init。Do not treat as a new empty project silently.
Read pm check output. Also inspect:
- project.yaml / prd.status（draft → 提醒 confirm / skip，不自动当基线）
- .pm/state/audit.jsonl 是否可逐行 JSON 解析
- .pm/architecture/map.json 是否存在、是否能解析
- .pm/engineering/reviews.md 待处置条数
- 核心文档索引是否过期（pm docs 只更新索引）
If the user said repair (or agrees after you list issues):
- Re-run pm init --scaffold-only --no-skills-sh to fill missing skeleton only (CLI is copy-if-missing).
- Never overwrite user-edited or prd.status=confirmed / charter.status=approved content.
- Rebuild map with pm arch if missing or unreadable.
- Rebuild dashboard with pm dashboard if missing.
- If audit.jsonl is corrupt: keep a .bak of the readable prefix if possible; do not silently truncate confirmed reviews/todos.
Tell the user what was repaired vs what needs a human confirm.
Closing: _closing.md 轻量档。

Done When

Missing .pm/ directed to /pm-init
Diagnosis listed in Chinese
Repair path did not overwrite confirmed baselines

Shared Workflow

Map-first. Redact. No auto-write of app code. Design baseline: docs/prd.md + 宪章。

Changes

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.

4d ago First seen · 42 lines · 31 tokens per session scan A 76d622819348

Subscribe to this mod's changes

pm-check is a command published in the GitHub repository wei63w/pm-manager (96 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 470 once invoked, about $0.0002 per session on Opus 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.

Project Management Project management agent-skills ai-agents claude-code cursor skills

pm-check

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

User Input

Outline

Done When

Shared Workflow

What this file has done since we first saw it

Other commands, from other repositories

webperf

install

audit-rules

search

index

commit