pm-prompts: Command for Claude Code

.claude/commands/prd-review.md

prd-review is a command for Claude Code from MrJoeSack/pm-prompts. It costs 15 tokens per session (267 once invoked), scanned A, original, MIT.

A command that reviews product-management documents such as product requirements documents, specifications, strategy documents, and emails. It checks their writing, feature planning, strategic fit, and clarity for engineering.

In plain words
What is it for?
Use it to improve a draft product document or communication. It returns specific recommendations and rewrites an important section to show the improvements.
Why use it?
It finds vague requirements, unnecessary wording, missing success measures, and unclear trade-offs before they create confusion. It also checks whether the proposed work supports the broader strategy.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is MrJoeSack/pm-prompts's own configuration. It tells Claude Code how to work on pm-prompts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pm-prompts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MrJoeSack/pm-prompts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MrJoeSack/pm-prompts/main/.claude/commands/prd-review.md
Clone the repo
git clone --depth 1 https://github.com/MrJoeSack/pm-prompts

Made for: Claude Code.

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.

agentmods badge for prd-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrjoesack/pm-prompts/prd-review/github.svg)](https://agentmods.dev/commands/mrjoesack/pm-prompts/prd-review)
Your own site
<a href="https://agentmods.dev/commands/mrjoesack/pm-prompts/prd-review"><img src="https://agentmods.dev/badge/commands/mrjoesack/pm-prompts/prd-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.

agentmods 80×15 button for prd-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/mrjoesack/pm-prompts/prd-review"><img src="https://agentmods.dev/badge/commands/mrjoesack/pm-prompts/prd-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00267
Opus 5 $0.00008 $0.00133
Sonnet 5 $0.00003 $0.00053
Haiku 4.5 $0.00002 $0.00027

Measured 10d ago against content hash aa741e3ac1e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prd-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 10d 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.

.claude/commands/prd-review.md · 47 lines

What it actually says

PRD Review Engine

Apply multiple frameworks to evaluate and improve Product Requirements Documents:

Framework Application

  1. McCloskey Writing Test

    • Cut needless words and throat-clearing
    • Use active voice and concrete language
    • Lead with conclusions
  2. Feature Planning Discipline

    • Clear problem/solution statements
    • Explicit trade-offs
    • Measurable success criteria
  3. Strategy Alignment Check

    • Does this advance the broader strategy?
    • Are priorities coherent?
    • What are we not building?
  4. Communication Clarity

    • Can engineering understand exactly what to build?
    • Are stakeholder concerns addressed?
    • Is the timeline realistic?

Input Instructions

Paste any PM document content, or describe what you're working on.

Works best with:

  • Complete document text
  • Draft emails or communications
  • Strategy or planning documents
  • Feature specifications

Output

Provide specific improvement recommendations organized by framework, plus a rewritten key section demonstrating the principles.

Arguments: {{args}}

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.

  1. 10d ago First seen · 47 lines · 15 tokens per session scan A aa741e3ac1e8

Subscribe to this mod's changes

prd-review is a command published in the GitHub repository MrJoeSack/pm-prompts (6 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 267 once invoked, about $0.0001 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.