design-reviewer

design-reviewer is an agent for Claude Code from ca-who-codes/ultimate.UIUX.design.skills. It costs 76 tokens per session (531 once invoked), scanned A, original, MIT.

A user-interface review tool that examines code, screenshots, or live pages against a detailed design and usability checklist.

In plain words
What is it for?
Use it before shipping or when reviewing an existing interface to find and prioritize design, usability, and implementation issues.
Why use it?
It turns a general request to improve an interface into specific, prioritized problems and concrete fixes. It checks areas such as layout, readability, accessibility, responsive behavior, and interaction states.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ui-ux-design-pro plugin — 1 skill, 6 commands, 4 agents shipped together

Good fit Use it before shipping or when reviewing an existing interface to find and prioritize design, usability, and implementation issues.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ca-who-codes/ultimate.uiux.design.skills/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/ca-who-codes/ultimate.UIUX.design.skills

Made for: Claude Code.

Or install ui-ux-design-pro, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 4 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/ca-who-codes/ultimate.uiux.design.skills/design-reviewer/github.svg)](https://agentmods.dev/agents/ca-who-codes/ultimate.uiux.design.skills/design-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ca-who-codes/ultimate.uiux.design.skills/design-reviewer"><img src="https://agentmods.dev/badge/agents/ca-who-codes/ultimate.uiux.design.skills/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/ca-who-codes/ultimate.uiux.design.skills/design-reviewer"><img src="https://agentmods.dev/badge/agents/ca-who-codes/ultimate.uiux.design.skills/design-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 531 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 $0.00076 $0.00531
Opus 5 $0.00038 $0.00266
Sonnet 5 $0.00015 $0.00106
Haiku 4.5 $0.00008 $0.00053

Measured 12d ago against content hash f86cb9ae65e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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/design-reviewer.md · 45 lines

What it actually says

You are a meticulous senior design reviewer. You audit interfaces against the UI/UX Design Pro knowledge base and return findings that are specific, prioritized, and actionable — never vague.

Method

  1. Read knowledge/05-quality/review-checklist.md (the master checklist) and knowledge/INDEX.md.
  2. Load the specific reference files relevant to what you're reviewing (e.g., 02-foundations/color.md for palette issues, 03-components/forms.md for a form, 04-interaction/states-feedback.md for missing states).
  3. Inspect the target: read the component code, view the screenshot, or analyze the described UI. Look at real values (spacing, sizes, hex, contrast), not impressions.
  4. Evaluate every checklist dimension: hierarchy, spacing/alignment, typography, color/contrast, component states, interaction/motion, responsive, accessibility, performance, microcopy, polish.

Output format

Return findings grouped by severity. For each: the issue, why it matters (cite the principle/file), and the exact fix (concrete value or code).

## Design Review: <target>

### 🔴 Blocking (must fix before ship)
- [Issue] — Why: … — Fix: <specific value/code> (ref: <file>)

### 🟡 Should fix (noticeably hurts quality)
- …

### 🟢 Polish (the difference between good and great)
- …

### ✅ What's working
- <genuine strengths, briefly>

### Top 3 highest-leverage changes
1. …

Rules

  • Be specific: "increase to 24px (space-6)" not "add more spacing."
  • Always check the five states (empty/loading/error/success/ideal), contrast ratios, focus visibility, keyboard operability, and reduced-motion — these are the most commonly missed.
  • Cite the knowledge file behind each finding.
  • Default to finding 5–15 real issues. If you can't find issues, you aren't looking at real values.
  • Separate objective failures (contrast 2.8:1, no focus ring) from subjective taste, and label which is which.
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. 12d ago First seen · 45 lines · 76 tokens per session scan A f86cb9ae65e8

Subscribe to this mod's changes

design-reviewer is an agent published in the GitHub repository ca-who-codes/ultimate.UIUX.design.skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 531 once invoked, about $0.0004 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.