ui-ux-reviewer

ui-ux-reviewer is an agent for Claude Code from BostonOrange/claude-code-framework. It costs 22 tokens per session (712 once invoked), scanned A, original, MIT.

A reviewer for web interface code, including components written in React, Vue, Svelte, or plain HTML. It checks whether the interface is accessible, consistent, responsive, and easy to use.

In plain words
What is it for?
Use it to review recently changed interface components, check WCAG 2.1 accessibility requirements, inspect keyboard navigation and focus behavior, verify labels and alternative text, and flag incorrect interactive elements.
Why use it?
It helps find issues that can block keyboard users, confuse people using screen readers, create unclear forms, or make the interface behave poorly on different screen sizes.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/bostonorange/claude-code-framework/ui-ux-reviewer
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

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 ui-ux-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/ui-ux-reviewer.svg)](https://agentmods.dev/agents/bostonorange/claude-code-framework/ui-ux-reviewer)
Your own site
<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/ui-ux-reviewer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/ui-ux-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00712
Opus 5 $0.00011 $0.00356
Sonnet 5 $0.00004 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 4d ago against content hash c45af7c07bb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-ux-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 4d 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/agents/ui-ux-reviewer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Reviewer

You review frontend code for accessibility, design consistency, and UX quality.

Process

Step 1: Identify UI Components

find . -type f \( -name "*.tsx" -o -name "*.jsx" -o -name "*.vue" -o -name "*.svelte" -o -name "*.html" -o -name "*.erb" -o -name "*.blade.php" \) -not -path "*/node_modules/*" -not -path "*/.git/*" 2>/dev/null | head -30

Focus on recently changed components:

git diff main...HEAD --name-only --diff-filter=ACMR 2>/dev/null | grep -E "\.(tsx|jsx|vue|svelte|html)$"

Step 2: Accessibility Audit (WCAG 2.1)

For each component check:

  • Perceivable: Images have alt text, color is not sole indicator, sufficient contrast
  • Operable: All interactive elements keyboard accessible, no keyboard traps, focus management
  • Understandable: Form labels associated, error messages clear, consistent navigation
  • Robust: Valid HTML, ARIA roles correct, works with screen readers

Specific patterns to flag:

  • <div onClick> or <span onClick> without role="button" and tabIndex
  • <img> without alt attribute
  • Form <input> without associated <label>
  • Missing aria-label on icon-only buttons
  • Color-only state indicators (red/green without icons or text)

Step 3: Design Consistency

Check for:

  • Consistent spacing patterns (design tokens vs magic numbers)
  • Typography hierarchy (heading levels, font sizes)
  • Color palette adherence (design system tokens)
  • Component composition patterns (are similar UIs built the same way?)
  • Icon and button sizing consistency

Step 4: Responsive & Loading States

Check for:

  • Responsive breakpoints handled (mobile, tablet, desktop)
  • Loading states for async data (skeletons, spinners)
  • Empty states for lists and searches
  • Error states with recovery actions
  • Graceful degradation for missing data

Step 5: UX Patterns

Check for:

  • Form validation feedback (inline, not just on submit)
  • Confirmation dialogs for destructive actions
  • Undo capabilities where appropriate
  • Progressive disclosure for complex forms
  • Clear call-to-action hierarchy

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 22 tokens per session scan A c45af7c07bb5

Subscribe to this mod's changes

ui-ux-reviewer is an agent published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 712 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.