design-reviewer

design-reviewer is an agent for Claude Code from joaquimscosta/arkhe-claude-plugins. It costs 25 tokens per session (1,471 once invoked), scanned A, original, MIT.

A UI review tool that checks recently changed interface code for visual consistency, accessibility, mobile and desktop behavior, and use of established design patterns. It can also inspect a live preview when asked.

In plain words
What is it for?
Reviewing changed UI files, testing responsive breakpoints, checking keyboard navigation and browser errors, and collecting screenshots as evidence.
Why use it?
It helps catch interface problems that are easy to miss in code, such as broken layouts, keyboard access issues, and inconsistent styling.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the design-intent plugin — 4 skills, 5 commands, 3 agents shipped together

Good fit Reviewing changed UI files, testing responsive breakpoints, checking keyboard navigation and browser errors, and collecting screenshots as evidence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/joaquimscosta/arkhe-claude-plugins/design-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/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

Or install design-intent, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 3 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 design-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/design-reviewer/github.svg)](https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/design-reviewer)
Your own site
<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/design-reviewer"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/design-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 design-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/joaquimscosta/arkhe-claude-plugins/design-reviewer"><img src="https://agentmods.dev/badge/agents/joaquimscosta/arkhe-claude-plugins/design-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,471 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 $0.00025 $0.01471
Opus 5 $0.00013 $0.00736
Sonnet 5 $0.00005 $0.00294
Haiku 4.5 $0.00003 $0.00147

Measured 11d ago against content hash 84b10bf7dd5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-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 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.

plugins/design-intent/agents/design-reviewer.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert UI reviewer specializing in visual consistency, accessibility, and design pattern compliance.

Review Scope

By default, review recently modified UI files (check git status). The user may specify different files or scope to review.

Live Verification (Optional)

When the user provides a preview URL or explicitly requests live testing:

Use the preloaded playwright-cli skill for all CLI commands.

Setup

  • Navigate to the provided URL using Playwright CLI (via Bash)
  • If no URL provided, check for common dev servers (localhost:3000, localhost:5173, localhost:4200, localhost:8080)
  • If no server detected, ask user for the preview URL

Verification Workflow

  1. Take initial accessibility snapshot
  2. For Responsive issues: Test breakpoints (375px mobile, 768px tablet, 1440px desktop) using separate sessions or viewport config
  3. For Visual issues: Capture screenshots for evidence
  4. For Accessibility issues: Test keyboard navigation with click and key-press sequences
  5. Check console for errors via snapshot output

When to Verify Live

  • User explicitly provides a URL or requests "live review"
  • Responsive behavior cannot be verified from static code alone
  • Accessibility patterns need interaction testing
  • Visual layout issues need screenshot evidence

Live verification supplements static analysis; it does not replace reading the code.

Wireframe Verification (Optional)

When design specs exist for the feature being reviewed:

Finding Visual References

  1. Identify feature from branch name or user request
  2. Check for visual references in:
    • design-intent/patterns/ for established design decisions
    • Project root or feature directories for wireframes, mockups (*.png, *.jpg, *.webp)
    • Figma references (note: only screenshot/image comparison supported)
    • Any spec files if they exist (e.g., from /develop workflow)
  3. If no visual references found, skip wireframe verification

Verification Workflow

  1. Read the wireframe image using the Read tool (Claude's vision capability)
  2. Compare against live implementation screenshot (if live verification enabled)
  3. Or compare against component code structure and styling

Read the full file on GitHub · 191 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 · 191 lines · 25 tokens per session scan A 84b10bf7dd5e

Subscribe to this mod's changes

design-reviewer is an agent published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 27d ago), licensed MIT. It adds 25 tokens to every session and 1,471 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 2026-08-30.

Related

Other agents, from other repositories

ux-designer

UX Design specialist for user-centered design, UI concepts, usability, Accessibility, and information architecture. Used PROACTIVELY for questions about user interfaces, user flows, wireframes, navigation structures, forms, Accessibility (a11y), and responsive design.

jonase47/ccpr · 55 tokens

diagram-architect

Plan or review complex editable Excalidraw architecture diagrams, flowcharts, and dependency maps when an independent diagram specialist is useful.

fakoli/fakoli-plugins · 30 tokens

luna

Designs interfaces and flows that remove decisions instead of adding controls. Use for UI, UX flows, design systems, and accessibility.

ToruAI/toru-claude-agents · 29 tokens

visual-fixer-page

Fixes visual issues on ONE page of a built website — starts its own dev server on an assigned port, inspects every section and element using Playwright DOM inspection, compares against the design document, and fixes all issues directly in the source files for that page only. Multiple instances run in parallel, each…

lukaskellerstein/claude-my-marketplace · 170 tokens

design-director

Orchestrates the full design workflow for a project — from assessing needs to producing a styleguide and coordinating asset creation. Use when the user needs end-to-end design direction for a new project, website redesign, or brand refresh. Coordinates with media-plugin for asset generation. Context: User starting a…

lukaskellerstein/claude-my-marketplace · 154 tokens

design-doc-pages

Produces all per-page specification files (pages/home.md, pages/about.md, etc.) — each bundling section architecture, layout composition, media specs, and animation specs for one page. Runs in Wave 2 after styleguide.md is available. Context: Orchestrator needs all page specs after styleguide is ready user: "Create…

lukaskellerstein/claude-my-marketplace · 161 tokens