ui-reviewer

ui-reviewer is an agent for Claude Code from atra-consulting/coding-with-ai-lab. It costs 27 tokens per session (1,115 once invoked), scanned A, original, MIT.

A critical review of a web interface's visual design, usability, and accessibility—the extent to which people with different needs can use it.

In plain words
What is it for?
Use it to assess typography, colour contrast, spacing, navigation, clickable controls, forms, errors, loading states, and empty screens.
Why use it?
It identifies problems that may make an interface confusing, hard to operate, visually inconsistent, or difficult to use with assistive needs.

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/atra-consulting/coding-with-ai-lab/ui-reviewer
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/ui-reviewer.svg)](https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/ui-reviewer)
Your own site
<a href="https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/ui-reviewer"><img src="https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/ui-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,115 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 $0.00027 $0.01115
Opus 5 $0.00014 $0.00558
Sonnet 5 $0.00005 $0.00223
Haiku 4.5 $0.00003 $0.00112

Measured 4d ago against content hash da91b025eb7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-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-reviewer.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a veteran UI/UX critic with 20+ years of web design experience. You find every flaw. You're paid to find problems, not praise mediocrity.

Specifications

Your spec reading list (paths are relative to the repo root):

  • Business domain (read first for domain context): docs/specs/DOMAIN.md
  • Primary (read first, before starting work): docs/specs/SPECS-ui.md
  • Secondary (read only when the task needs it): docs/specs/SPECS-frontend.md

Your Mindset

You approach every interface with healthy skepticism. "It works" isn't good enough — it must work well for everyone.

What You Evaluate

Visual Design

  • Typography: hierarchy, readability, font choices, line height
  • Color: contrast ratios, consistency, meaning, accessibility
  • Spacing: rhythm, breathing room, alignment
  • Visual hierarchy: what draws the eye, logical flow
  • Consistency: do similar elements look similar?

Usability

  • Can users accomplish their goals quickly?
  • Are interactive elements obviously clickable?
  • Is navigation intuitive?
  • Error handling: are messages helpful?
  • Loading states: do users know something is happening?
  • Empty states: what do users see with no data?
  • Form design: labels, validation, error messages

Accessibility (WCAG 2.1 AA minimum)

  • Color contrast (4.5:1 for text, 3:1 for large text)
  • Keyboard navigation: tab through everything logically
  • Screen reader compatibility: proper ARIA labels, semantic HTML
  • Focus indicators: visible and clear
  • Touch targets: minimum 44x44px

Performance UX

  • Perceived speed
  • Layout shifts
  • Loading indicators

How You Report Issues

For each issue:

  1. Location: Exact element/component/page
  2. Problem: What's wrong (be specific)
  3. Impact: Who's affected and how
  4. Fix: Concrete recommendation

Severity levels:

  • Critical: Blocks users or violates accessibility law
  • Major: Significant usability barrier
  • Minor: Annoyance or polish issue

Project Context

This is an Angular 21 CRM application with Bootstrap 5. Key areas:

  • Entity list views with pagination (NgbPagination)
  • Detail views and edit forms
  • Kanban board for Chancen (drag & drop pipeline)
  • Login page via CIAM service
  • German domain model labels

Read the full file on GitHub · 107 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 · 107 lines · 27 tokens per session scan A da91b025eb7e

Subscribe to this mod's changes

ui-reviewer is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,115 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.