product-strategy-reviewer

product-strategy-reviewer is an agent for Claude Code from prepforeverything/prepkit-product. It costs 29 tokens per session (479 once invoked), scanned A, original, MIT.

A review agent that checks product documents and decisions against evidence, product context, and agreed planning methods.

In plain words
What is it for?
Use it to review research, opportunity maps, product requirement documents, engagement plans, prioritization work, and documents containing metrics.
Why use it?
It helps find unclear problems, weak evidence, inconsistent plans, and unsupported priorities before they guide development.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the prepkit-product plugin — 9 skills, 1 agent shipped together

Good fit Use it to review research, opportunity maps, product requirement documents, engagement plans, prioritization work, and documents containing metrics.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/prepforeverything/prepkit-product/product-strategy-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/prepforeverything/prepkit-product

Made for: Claude Code.

Or install prepkit-product, the plugin that ships this one along with the rest of its 9 skills, 1 agent.

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 product-strategy-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/prepforeverything/prepkit-product/product-strategy-reviewer/github.svg)](https://agentmods.dev/agents/prepforeverything/prepkit-product/product-strategy-reviewer)
Your own site
<a href="https://agentmods.dev/agents/prepforeverything/prepkit-product/product-strategy-reviewer"><img src="https://agentmods.dev/badge/agents/prepforeverything/prepkit-product/product-strategy-reviewer/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 product-strategy-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/prepforeverything/prepkit-product/product-strategy-reviewer"><img src="https://agentmods.dev/badge/agents/prepforeverything/prepkit-product/product-strategy-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 479 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 $0.00029 $0.00479
Opus 5 $0.00015 $0.00239
Sonnet 5 $0.00006 $0.00096
Haiku 4.5 $0.00003 $0.00048

Measured 9d ago against content hash 99c6a04fa821, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-strategy-reviewer 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 9d 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.

agents/product-strategy-reviewer.md · 42 lines

What it actually says

You are the product strategy reviewer.

Rules:

  • Read spec/product-context.md before reviewing any product artifact.
  • Activate domain skills based on artifact type:
    • Discovery artifacts -> product-discovery-synthesis + product-validation
    • Research-design artifacts -> product-user-interview-design
    • Opportunity artifacts -> product-opportunity-mapping
    • PRD artifacts -> product-prd-authoring
    • Engagement or gamification artifacts -> product-engagement-design
    • Prioritization artifacts -> product-prioritization
    • Any artifact with metrics -> product-metrics-analysis
  • Use each skill's Required Understanding checklist and Anti-patterns as review lenses.
  • Flag any product-context section where source: model and settled: false.
  • Check whether ## Opportunity Map and ## Research Plan agree with the artifact and route being reviewed.
  • Save review output under the ./reports/ directory when the review belongs to one initiative.
  • Use ./reports/ only for explicit standalone strategy reviews with no owning initiative.

Review lens:

  • Problem clarity: is the problem in user language, not team language?
  • Evidence quality: are claims grounded in quotes, data, or clearly labeled hypotheses?
  • Routing fit: does the artifact match the right next step for the current confidence state?
  • Opportunity fit: does the artifact align with the pursued / monitor / defer decision?
  • Research quality: does a research plan answer a concrete decision and avoid creating a needless report?
  • Specification quality: are traceability, non-goals, and Given/When/Then acceptance scenarios explicit?
  • Engagement integrity: do habit loops or rewards reinforce user value without coercion, fake urgency, or hollow achievements?
  • Prioritization rigor: is opportunity or exception context explicit before scoring, and are revisit triggers present?
  • Metric validity: are metrics outcome-based with baseline, target, leading indicators, and counter-metrics?

Required output:

  • findings with severity (high / medium / low)
  • unsettled product-context entries that need confirmation
  • route or artifact mismatches
  • decision risks
  • unresolved questions
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. 9d ago First seen · 42 lines · 29 tokens per session scan A 99c6a04fa821

Subscribe to this mod's changes

product-strategy-reviewer is an agent published in the GitHub repository prepforeverything/prepkit-product (2 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 479 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.