product-os: Command for Claude Code

.claude/commands/review-design.md

review-design is a command for Claude Code from motorway-sandbox/product-os. It costs 0 tokens per session (3,474 once invoked), scanned A, original, MIT.

A design-review command that checks product screenshots against specified product frameworks and saves an evidence-based review.

In plain words
What is it for?
Use it to assess customer-facing or internal designs for journeys such as onboarding, checkout, post-purchase flows, or dashboards.
Why use it?
It prevents design feedback from being based only on personal opinion by requiring screenshots, a testing hypothesis, and relevant product context.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is motorway-sandbox/product-os's own configuration. It tells Claude Code how to work on product-os 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 product-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to motorway-sandbox/product-os. 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/motorway-sandbox/product-os/main/.claude/commands/review-design.md
Clone the repo
git clone --depth 1 https://github.com/motorway-sandbox/product-os

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 review-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/motorway-sandbox/product-os/review-design/github.svg)](https://agentmods.dev/commands/motorway-sandbox/product-os/review-design)
Your own site
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/review-design"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/review-design/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 review-design

Your own site · 80×15
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/review-design"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/review-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,474 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 $0.00000 $0.03474
Opus 5 $0.00000 $0.01737
Sonnet 5 $0.00000 $0.00695
Haiku 4.5 $0.00000 $0.00347

Measured 6d ago against content hash 317b5ae4a8f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-design 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 6d 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/review-design.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Review

Review design screenshots against your product frameworks and save a structured, evidence-based review.

Arguments: $ARGUMENTS (optional — the hypothesis being tested)

Instructions

Phase 1: Gather Context

  1. Check for images. If no design screenshots are visible in the conversation, ask the user to paste them before continuing. Do not proceed without images.

  2. Parse the hypothesis. If $ARGUMENTS contains text, use it as the hypothesis. If it is empty or missing, ask: "What hypothesis is this design testing? (If/then/because format is ideal, but a plain description works too.)"

  3. Determine context. Ask the user (if not obvious from the designs):

    • Is this customer-facing or internal/B2B-facing?
    • What journey stage does this sit in? (e.g. onboarding, checkout, post-purchase, admin dashboard)
    • Is there an existing project file this relates to? (e.g. a file in projects/)
  4. Read reference files silently (do not output their contents). Always read:

    • context/product.md
    • data/funnel-context.md
    • context/brand/messaging/how-we-sound.md
    • context/brand/messaging/our-language.md
    • pm-playbook/process/4-design.md

    If relevant, also read:

    • strategy/activation/activation-strategy.md (Note: this is a DRAFT document — use its frameworks as reference but do not treat its specific recommendations as validated or current strategy)
    • context/personas/customer-personas.md

    For B2B/partner-facing features, also read:

    • strategy/activation/partner-activation-strategy.md (Note: this is a DRAFT document — same caveat as above)
    • context/personas/partner-personas.md

    If a project file was identified, also read it.

Phase 2: Analyse (6 Lenses)

Work through all six lenses below. Do not skip any.

Read the full file on GitHub · 266 lines

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. 6d ago First seen · 266 lines · 0 tokens per session scan A 317b5ae4a8f2

Subscribe to this mod's changes

review-design is a command published in the GitHub repository motorway-sandbox/product-os (9 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,474 tokens. 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 2026-09-04.