prd-review

prd-review is a skill for Claude Code from adamfaik/claude-code-pm-starter. It costs 52 tokens per session (390 once invoked), scanned A, original, MIT.

A review process for a product brief, PRD, or specification before it is shared. A PRD is a document describing a product, its problem, and the decision or plan being proposed.

In plain words
What is it for?
Use it to review product documents and return prioritized findings rather than a rewritten draft. It checks the problem, decision, evidence, risks, scope, and known writing rules.
Why use it?
It finds weak problem statements, unsupported claims, unclear decisions, missing boundaries, and conflicts with the user's established preferences before others rely on the document.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review product documents and return prioritized findings rather than a rewritten draft. It checks the problem, decision, evidence, risks, scope, and known writing rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adamfaik/claude-code-pm-starter/prd-review
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.

Any agent
npx skills add adamfaik/claude-code-pm-starter --skill prd-review
Clone the repo
git clone --depth 1 https://github.com/adamfaik/claude-code-pm-starter

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/skills/adamfaik/claude-code-pm-starter/prd-review.svg)](https://agentmods.dev/skills/adamfaik/claude-code-pm-starter/prd-review)
Your own site
<a href="https://agentmods.dev/skills/adamfaik/claude-code-pm-starter/prd-review"><img src="https://agentmods.dev/badge/skills/adamfaik/claude-code-pm-starter/prd-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 390 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 $0.00052 $0.00390
Opus 5 $0.00026 $0.00195
Sonnet 5 $0.00010 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 8d ago against content hash bb9e543f582e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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/skills/prd-review/SKILL.md · 24 lines

What it actually says

PRD review

Be the demanding colleague who reads the draft before the real audience does. Findings, not a rewrite.

Steps

  1. Load the bar. Read context/preferences.md (writing preferences and corrections log), context/users.md (who this is ultimately for), and the project's brief.md if the document belongs to a project.
  2. Read the document end to end before flagging anything.
  3. Review against four lenses, in order of importance:
    • The problem. Is it stated with evidence, or assumed? Would someone who disagrees be convinced there's a problem at all?
    • The decision. What is this document asking the reader to decide or accept? If you can't find it, that's the first finding.
    • The evidence. Every claim needs a source, a number, or a named observation. Flag each claim that has none.
    • The edges. What's out of scope, what could go wrong, what's the cost of being wrong? Silent edges get flagged.
  4. Check it against the user's own rules. Anything in the corrections log that this draft violates gets flagged with the rule quoted.

Output

Prioritized findings: must-fix first, then should-fix, then nits. Each finding quotes the passage, says what's wrong in one line, and proposes the concrete fix. Cap at ten findings; if there are more, the top ten are the review. End with the one-line verdict you'd give the user across a desk: ready to share, or not yet, and why.

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. 8d ago First seen · 24 lines · 52 tokens per session scan A bb9e543f582e

Subscribe to this mod's changes

prd-review is a skill published in the GitHub repository adamfaik/claude-code-pm-starter (10 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 390 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens