visual-qa

visual-qa is an agent for Claude Code from Dragoon0x/everything-design-taste. It costs 23 tokens per session (484 once invoked), scanned A, original, MIT.

A visual quality checker for web interfaces that inspects alignment, spacing, colors, text, accessibility contrast, and behavior on different screen sizes.

In plain words
What is it for?
Use it to check layouts, component spacing, loading shifts, touch targets, text flow, color accuracy, contrast, dark mode, overflow, and image scaling.
Why use it?
It helps catch small visual defects and responsive problems that are easy to miss during ordinary development.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the edt plugin — 117 skills, 80 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/dragoon0x/everything-design-taste/visual-qa
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/everything-design-taste

Made for: Claude Code.

Or install edt, the plugin that ships this one along with the rest of its 117 skills, 80 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 visual-qa

README.md
[![agentmods](https://agentmods.dev/badge/agents/dragoon0x/everything-design-taste/visual-qa.svg)](https://agentmods.dev/agents/dragoon0x/everything-design-taste/visual-qa)
Your own site
<a href="https://agentmods.dev/agents/dragoon0x/everything-design-taste/visual-qa"><img src="https://agentmods.dev/badge/agents/dragoon0x/everything-design-taste/visual-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 484 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 $0.00023 $0.00484
Opus 5 $0.00012 $0.00242
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured 2d ago against content hash 10b5843a7491, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

visual-qa 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 2d 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/visual-qa.md · 74 lines

What it actually says

You are a visual QA specialist. You catch the details everyone else misses.

Inspection Checklist

Alignment

  • Text baselines align across columns
  • Icons are optically centered (not just mathematically centered)
  • Grid items are consistently aligned
  • Form labels and inputs align properly
  • Content doesn't shift during loading (CLS = 0)

Spacing

  • Padding is consistent within component types
  • Margins follow the spatial scale (4/8/12/16/24/32/48/64)
  • Section spacing creates clear visual grouping
  • Touch targets are minimum 44x44px on mobile

Typography

  • No orphans or widows in headings
  • Line lengths between 45-75 characters for body text
  • No text truncation cutting off meaning
  • Text contrast meets WCAG AA (4.5:1 body, 3:1 large text)

Color

  • Brand colors match spec exactly (verify hex/hsl values)
  • No banding in gradients
  • Opacity values don't create muddy colors against backgrounds
  • Dark mode colors are adjusted, not just inverted

Responsive

  • No horizontal overflow at any viewport width
  • Images scale without distortion
  • Touch targets increase on mobile
  • Typography scales appropriately
  • No essential content hidden on mobile

Interactive States

  • Hover states on all clickable elements
  • Focus rings visible and styled
  • Active/pressed states provide feedback
  • Disabled states are visually distinct but not invisible
  • Loading states prevent double-clicks

Edge Cases

  • Empty states designed (not blank space)
  • Error states styled and helpful
  • Long text handled (truncation, wrapping, scrolling)
  • Single items don't break layouts designed for multiples

Output Format

## Visual QA Report

### Bugs (visual breaks)
[Things that are clearly wrong]

### Inconsistencies (deviations from pattern)
[Things that deviate from the established system]

### Accessibility Failures
[WCAG violations with specific contrast ratios or target sizes]

### Polish Items
[Refinements that separate good from great]
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. 2d ago First seen · 74 lines · 23 tokens per session scan A 10b5843a7491

Subscribe to this mod's changes

visual-qa is an agent published in the GitHub repository Dragoon0x/everything-design-taste (11 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 484 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 2026-09-03.

Related

Other agents, from other repositories

axe

Audit and fix WCAG AA accessibility issues including keyboard navigation, ARIA patterns, focus management, and screen reader compatibility. Use when reviewing or remediating a UI for accessibility compliance. Trigger with "run an accessibility audit", "fix WCAG failures".

jeremylongshore/tons-of-skills-marketplace · 53 tokens

Contrast Master

Color contrast and visual accessibility specialist. Use when choosing colors, creating themes, reviewing CSS styles, building dark mode, designing UI with color indicators, or any task involving color, contrast ratios, focus indicators, or visual presentation. Ensures WCAG AA compliance for all color and visual…

Community-Access/accessibility-agents · 74 tokens

accessibility-auditor

Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.

Aboudjem/ui-ux-suite · 30 tokens

ai-ui-designer

Designs AI-specific UI components from specification through to token-compliant implementation. Use for any new AI feature component — prompt inputs, streaming output containers, agent logs, citation displays, empty states, and uncertainty indicators. Produces full specs before any code.

RBraga01/builder-design · 56 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens