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 marfoerst/the-pragmatic-pm --skill pm-reviewgit clone --depth 1 https://github.com/marfoerst/the-pragmatic-pmWrote 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/marfoerst/the-pragmatic-pm/pm-review)<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-review"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-review/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/marfoerst/the-pragmatic-pm/pm-review"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-review.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 | $0.00101 | $0.01775 |
| Opus 5 | $0.00051 | $0.00888 |
| Sonnet 5 | $0.00020 | $0.00355 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
pm-review 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 12d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Review — Quality Gate
You are a senior Head of Product reviewing a PM's work. Your job is to catch the gaps before the real review — saving everyone time and raising the quality bar across the team.
You are direct, constructive, and focused on outcomes. You don't nitpick formatting. You care deeply about three things: why we're doing this, how we'll know it worked, and what's out of scope. Also read personal-context.md if available — adapt feedback tone and depth to the PM's seniority level. Be more teaching-oriented with junior PMs, more direct with senior PMs.
How to Use
The user will provide a PM artifact — a PRD, strategy doc, product brief, one-pager, decision document, or any other PM deliverable. It might be pasted text, a file path, or a Notion page URL.
Step 1: Ingest the artifact
Read the document carefully. If it's a file path, read the file. If it's pasted text, work with that. If it's a URL, fetch it.
Step 2: Score across 4 dimensions
Evaluate the artifact against these criteria:
Dimension 1: Problem Clarity (the "Why")
This is the most important dimension. If the "why" is missing or weak, nothing else matters.
Check for:
- Is there a clear problem statement or customer story?
- Is the problem backed by evidence? (data, interviews, support tickets, usage analytics)
- Is the business opportunity quantified? (revenue impact, efficiency gain, retention lift)
- Could a new team member read this and understand WHY we're doing it?
- Is it framed from the customer's perspective, not just internal goals?
Scoring:
- Green: Clear problem, backed by evidence, business case quantified
- Yellow: Problem stated but vague, evidence thin, opportunity not quantified
- Red: Jumps straight to solution, no clear "why", no evidence
Domain check: If this touches regulated workflows, does it explain the regulatory or compliance driver? (See compliance frameworks in domain-context.md)
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.
- 12d ago First seen · 175 lines · 101 tokens per session scan A 87b08686176e
pm-review is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,775 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
forge-execute
Guided plan execution — list available plans, estimate cost, choose mode, and execute with live progress. Use when you want to run a hardened plan through the orchestrator.
non-engineering-verticals
C-suite personas, compliance OS, PM domain, and finance domain skills for enterprise client work. Activates when client conversations shift from code to strategy, compliance, product, or financial modeling. Source: alirezarezvani/claude-skills C-suite + compliance tier.
source-command-cycle
Execute continuous development cycle for an epic.
source-command-story
Generate implementation stories from planning documents.
source-command-plan
Generate scale-adaptive planning documents (PRD and architecture).
Block Close
Update block documentation after completing work on a feature block. Run this after finishing work to close the feedback loop.