ui-audit

ui-audit is a command for Claude Code from nyldn/claude-dolphin. It costs 11 tokens per session (1,079 once invoked), scanned A, original, MIT.

A systematic review of a website or application interface for accessibility, consistency, and ease of use. Accessibility checks include whether people can navigate with a keyboard, read the content, and use forms and controls correctly.

In plain words
What is it for?
Use it to inspect a component, page, file path, or whole codebase for issues such as contrast, focus indicators, touch targets, headings, labels, links, buttons, image descriptions, and keyboard access.
Why use it?
It helps uncover interface problems that make a product confusing, inconsistent, or difficult to use, including for people with disabilities.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect a component, page, file path, or whole codebase for issues such as contrast, focus indicators, touch targets, headings, labels, links, buttons, image descriptions, and keyboard access.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/nyldn/claude-dolphin/ui-audit
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/nyldn/claude-dolphin

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/nyldn/claude-dolphin/ui-audit.svg)](https://agentmods.dev/commands/nyldn/claude-dolphin/ui-audit)
Your own site
<a href="https://agentmods.dev/commands/nyldn/claude-dolphin/ui-audit"><img src="https://agentmods.dev/badge/commands/nyldn/claude-dolphin/ui-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,079 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 $0.00011 $0.01079
Opus 5 $0.00005 $0.00540
Sonnet 5 $0.00002 $0.00216
Haiku 4.5 $0.00001 $0.00108

Measured 7d ago against content hash 8a8efde23dd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ui-audit 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 7d 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.

commands/ui-audit.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Audit Command

Perform a systematic UI audit on the specified scope.

Scope options:

  • File path (e.g., src/components/ui/button.tsx)
  • Component name (e.g., Button)
  • Page path (e.g., src/app/dashboard/page.tsx)
  • system for full codebase audit

Audit Process

Step 1: Scope Identification

Identify all UI-related files in the specified scope:

# Find component files
Glob: **/*.tsx, **/*.jsx in scope directory
# Find style files
Glob: **/*.css, **/*.scss in scope directory
# Find type definitions
Grep: interface.*Props in scope

Step 2: Accessibility Audit (WCAG 2.2 AA)

For each component, check:

Visual Accessibility:

  • Color contrast ratios meet minimums (4.5:1 body, 3:1 large text)
  • Focus states visible (2px+ outline, high contrast)
  • Touch targets >= 44×44px for interactive elements
  • No color-only information conveyance

Semantic Accessibility:

  • Proper heading hierarchy (no skipped levels)
  • Form labels associated with inputs (htmlFor/id match)
  • Button vs link distinction appropriate
  • Alt text on images (empty for decorative)

Interactive Accessibility:

  • Keyboard navigable (tabIndex, handlers)
  • ARIA labels where semantic HTML insufficient
  • Loading/error states announced (aria-live)
  • No keyboard traps

Step 3: Design Consistency Audit

Compare against project design system:

Design Tokens:

# Check for hardcoded colors
Grep: #[0-9a-fA-F]{3,6}|rgb\(|hsl\( in scope
# Check for hardcoded spacing
Grep: \d+px(?!.*var\() in scope
  • Colors from design token palette
  • Spacing from consistent scale (4, 8, 16, 24, 32, 48, 64px)
  • Typography from defined scale
  • Border radius consistent

Component Patterns:

  • Using shadcn components where applicable
  • Consistent button variants and sizes
  • Uniform input/form styling
  • Card/container patterns followed

Step 4: Usability Review

Evaluate user experience quality:

  • Visual hierarchy clear (primary action obvious)
  • Information architecture logical
  • Error states helpful (not just "Error occurred")
  • Loading states present for async operations
  • Empty states designed (not just blank)

Read the full file on GitHub · 167 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. 7d ago First seen · 167 lines · 11 tokens per session scan A 8a8efde23dd6

Subscribe to this mod's changes

ui-audit is a command published in the GitHub repository nyldn/claude-dolphin (9 stars, last pushed 14d ago), licensed MIT. It adds 11 tokens to every session and 1,079 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.