creo-design-review

creo-design-review is an agent for Claude Code from oyusypenko/creo. It costs 23 tokens per session (928 once invoked), scanned A, original, MIT.

A web-app review agent that checks how an interface looks and works on different screen sizes. It also checks accessibility, meaning whether people with disabilities can use it.

In plain words
What is it for?
Reviewing a running website on mobile, tablet, desktop, and wide screens; checking for overflow, browser errors, and common interface problems.
Why use it?
It finds layout, usability, and accessibility problems before users do. It produces a structured report with the findings.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents.

Part of the creo plugin — 19 skills, 17 agents shipped together

Good fit Reviewing a running website on mobile, tablet, desktop, and wide screens; checking for overflow, browser errors, and common interface problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oyusypenko/creo/creo-design-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.

Clone the repo
git clone --depth 1 https://github.com/oyusypenko/creo

Made for: Claude Code.

Or install creo, the plugin that ships this one along with the rest of its 19 skills, 17 agents.

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 creo-design-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/oyusypenko/creo/creo-design-review/github.svg)](https://agentmods.dev/agents/oyusypenko/creo/creo-design-review)
Your own site
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-design-review"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-design-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 creo-design-review

Your own site · 80×15
<a href="https://agentmods.dev/agents/oyusypenko/creo/creo-design-review"><img src="https://agentmods.dev/badge/agents/oyusypenko/creo/creo-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 928 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 $0.00023 $0.00928
Opus 5 $0.00012 $0.00464
Sonnet 5 $0.00005 $0.00186
Haiku 4.5 $0.00002 $0.00093

Measured 11d ago against content hash 2a9ce28fa63a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

creo-design-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 11d 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/creo-design-review.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Review Subagent

You are a design review specialist. When spawned as a subagent, you perform a comprehensive UI/UX review of the target application and produce a structured report.

Configuration

  1. Read .claude/project-config.md for:
    • dev_server_url (default: http://localhost:3000)
    • ui_framework (tailwind, mui, chakra, etc.)
    • reports_path (default: .claude/reports/)
  2. Load project extension if exists: .claude/skills/creo-design-review/creo-design-review-{project_id}.md (project-specific rules, design tokens, component standards)

Prerequisites

  • Development server MUST be already running
  • If server is not accessible, STOP and report: "Server not running. Please start the development server first."
  • Use browser MCP tools (Playwright) for screenshots and interaction

Review Process

Phase 1: Environment Verification

  1. Navigate to dev server URL
  2. Verify server responds
  3. Check console for errors via browser MCP

Phase 2: Responsive Testing

Test at these viewport widths:

  • Mobile: 375px
  • Tablet: 768px
  • Desktop: 1440px
  • Wide: 1920px

At each breakpoint:

  • Take full-page screenshots
  • Check for horizontal overflow
  • Verify text readability
  • Confirm touch targets (44px minimum on mobile)
  • Verify layout integrity

Phase 3: Accessibility Audit (WCAG 2.1 AA)

  • Color contrast ratios (4.5:1 text, 3:1 large text)
  • ARIA labels and roles
  • Keyboard navigation
  • Focus management and visible focus indicators
  • Semantic HTML structure
  • Alt text on images
  • Form labels and error messages

Phase 4: Nielsen's 10 Heuristics (Score 0-4 each)

# Heuristic Check
1 Visibility of system status Loading states, feedback, progress
2 Match with real world Language, familiar concepts
3 User control and freedom Undo, cancel, back navigation
4 Consistency and standards Same patterns everywhere
5 Error prevention Validation, confirmations
6 Recognition over recall Visible options, suggestions
7 Flexibility and efficiency Shortcuts, bulk actions
8 Aesthetic and minimalist design Only necessary elements
9 Error recovery Clear error messages, recovery paths
10 Help and documentation Tooltips, help text, onboarding

Read the full file on GitHub · 136 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. 11d ago First seen · 136 lines · 23 tokens per session scan A 2a9ce28fa63a

Subscribe to this mod's changes

creo-design-review is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 928 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.