ux-validator

ux-validator is an agent for Claude Code from smorky850612/Aurakit. It costs 46 tokens per session (1,154 once invoked), scanned A, original, MIT.

An automated reviewer for frontend user experience and accessibility. It checks WCAG 2.1 AA concerns, loading and error states, and responsive behavior after frontend files change.

In plain words
What is it for?
Use it after changes to React, Vue, Svelte, CSS, or SCSS files. It checks accessibility markup, interactive elements, error announcements, loading states, and mobile-friendly layout.
Why use it?
It catches common problems such as missing image descriptions, unlabeled form fields, and clickable non-button elements before they reach users. It skips changes limited to backend files.

Agent for Claude Code

Written for Claude Code: disallowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the aurakit plugin — 3 skills, 23 agents shipped together

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/smorky850612/aurakit/ux-validator
Clone the repo
git clone --depth 1 https://github.com/smorky850612/Aurakit

Made for: Claude Code.

Or install aurakit, the plugin that ships this one along with the rest of its 3 skills, 23 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 ux-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/smorky850612/aurakit/ux-validator.svg)](https://agentmods.dev/agents/smorky850612/aurakit/ux-validator)
Your own site
<a href="https://agentmods.dev/agents/smorky850612/aurakit/ux-validator"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/ux-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,154 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 5.1 $0.00046 $0.01154
Opus 5 $0.00023 $0.00577
Sonnet 5 $0.00009 $0.00231
Haiku 4.5 $0.00005 $0.00115

Measured 6d ago against content hash 80a3413b2f0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ux-validator 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 6d 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/ux-validator.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Validator Agent — User Experience Verification

Absorbed from Autopus-ADK ux-validator agent. Phase 3.5: Runs automatically after Phase 3 when frontend files (.tsx/.vue/*.svelte) were modified. Checks accessibility, loading states, error states, responsive behavior.


Trigger Condition

Auto-activate in Phase 3.5 when implementation included ANY of:

  • *.tsx / *.jsx files
  • *.vue files
  • *.svelte files
  • *.css / *.scss with layout changes

SKIP if only backend files modified.


Check 1 — Accessibility (WCAG 2.1 AA)

# Scan for common accessibility issues
grep -rn "<img" src/ | grep -v "alt="                      # Missing alt
grep -rn "<input\|<textarea\|<select" src/ | grep -v "id=" # Missing ID for label
grep -rn "<label" src/ | grep -v "htmlFor=\|for="          # Label without htmlFor
grep -rn "onClick\|onChange" src/ | grep "div\|span"        # Non-semantic interactives

Issues:

  • <img> without alt → FAIL
  • <input> without associated <label> → FAIL
  • onClick on <div> or <span> without role="button" → FAIL
  • Error messages without role="alert" → WARN
  • Missing aria-label on icon-only buttons → WARN

Focus Management

For modals/dialogs:

// Required: focus moves into dialog on open
useEffect(() => {
  if (isOpen) firstFocusableRef.current?.focus()
}, [isOpen])

// Required: focus returns to trigger on close
useEffect(() => {
  if (!isOpen) triggerRef.current?.focus()  
}, [isOpen])

Check 2 — Loading States

For every component that fetches data:

□ Loading skeleton or spinner shown during fetch
□ Button disabled during form submission (prevents double-submit)
□ Cursor changes to "not-allowed" on disabled elements
□ Progress indication for long operations (> 2 seconds expected)

Detect missing loading states:

grep -rn "useQuery\|useMutation\|fetch\|axios" src/ |
  # For each file, check if isLoading/isPending is used

Check 3 — Error States

□ User-facing error message (not raw Error.message or stack trace)
□ Error displayed near the failing operation
□ Retry option available for network errors
□ Error boundary wraps dynamic content sections
□ Form field errors inline (not just alert at top)

Read the full file on GitHub · 169 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. 6d ago First seen · 169 lines · 46 tokens per session scan A 80a3413b2f0a

Subscribe to this mod's changes

ux-validator is an agent published in the GitHub repository smorky850612/Aurakit (41 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 1,154 once invoked, about $0.0002 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.