visual-ui-auditor

visual-ui-auditor is a skill for Claude Code, Codex from roedyrustam/vibes-plug. It costs 89 tokens per session (2,313 once invoked), scanned A, original, MIT.

A visual user-interface review guide that examines screenshots and source code with image-aware AI models and code checks. It looks at layout, visual hierarchy, contrast, borders, corner shapes, number alignment, decorative effects, and interaction states against accessibility and design rules.

In plain words
What is it for?
Use it to audit web pages, UI components, and screenshots for visual consistency, WCAG 2.2 AA accessibility concerns, and specified interaction states.
Why use it?
Text-only code checks cannot reliably judge how an interface looks or whether visual contrast and spacing work in practice. It helps identify visual and accessibility problems before release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit web pages, UI components, and screenshots for visual consistency, WCAG 2.2 AA accessibility concerns, and specified interaction states.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roedyrustam/vibes-plug/visual-ui-auditor
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.

Any agent
npx skills add roedyrustam/vibes-plug --skill visual-ui-auditor
Clone the repo
git clone --depth 1 https://github.com/roedyrustam/vibes-plug

Made for: Claude Code, Codex.

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-ui-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/visual-ui-auditor/github.svg)](https://agentmods.dev/skills/roedyrustam/vibes-plug/visual-ui-auditor)
Your own site
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/visual-ui-auditor"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/visual-ui-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for visual-ui-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/visual-ui-auditor"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/visual-ui-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,313 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 $0.00089 $0.02313
Opus 5.5 $0.00036 $0.00925
Sonnet 5.5 $0.00018 $0.00463
Haiku 4.5 $0.00009 $0.00231

Measured yesterday against content hash 2f9f91808106, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

visual-ui-auditor 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 yesterday.

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.

skills/visual-ui-auditor/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual UI Auditor & Vision Quality Gate (Anti-Slop Pillar 7)

English | Bahasa Indonesia


English

Description

Production guide for automated visual quality auditing using multimodal vision frontier models (Gemini 4 Pro/Flash Vision, Claude 3.7/5.1 Sonnet Vision, GPT-5 Vision). Standard text-based AST linters cannot evaluate spatial breathing room, perceived elevation, optical alignment, or contrast degradation under dynamic lighting. This skill combines automated regex/AST scanners with multimodal vision evaluation to audit UI code and rendered screenshots against the strict Anti-Slop Pillar 7 visual standard: 1px crisp borders, structured 3-tier radius scales, tabular numerals, eradication of generic neon radial glow orbs, and mandatory 5-state interactive contracts.

Trigger Conditions

  • Reviewing UI components, web pages, or application screenshots prior to release (Phase 5/6).
  • Converting Figma designs or mockup screenshots into code (screenshot-to-code-expert).
  • Auditing codebases for AI slop visual clichés (e.g., bg-gradient-to-r from-blue-500 to-purple-600 or rounded-full on standard rectangular buttons).
  • Enforcing WCAG 2.2 Level AA accessibility color contrast and keyboard focus indicators.

The 20-Point Visual Quality Rubric

SCREENSHOT OR UI CODE
          │
          ▼
┌───────────────────────────────┐
│ 1. STATIC AST / REGEX SCAN    │  Bans `rounded-full` on buttons, generic blue-purple gradients
└──────────────┬────────────────┘
               │
               ▼
┌───────────────────────────────┐
│ 2. MULTIMODAL VISION SAMPLING │  Evaluates optical balance, elevation, visual hierarchy
└──────────────┬────────────────┘
               │
               ▼
┌───────────────────────────────┐
│ 3. STRUCTURED SCORECARD       │  Score (0-100), Verdict, Pixel-Level Fixes
└───────────────────────────────┘
The 6 Core Visual Laws (Pillar 7)
  1. Rejection of Pill-Button Addiction: Standard rectangular action buttons must use structured radius (rounded-md 6px or rounded-lg 8px). rounded-full is strictly prohibited on non-circular/non-badge elements.
  2. 1px Crisp Borders: Elevated surfaces (dialogs, cards, dropdowns) must use crisp 1px borders (border border-slate-200 dark:border-slate-800 or rgba(255,255,255,0.08)) to ground geometry rather than heavy floating drop-shadows.
  3. Anti-Generic Gradients: Generic AI blue-to-purple gradients (from-blue-500 to-purple-600) and blurred neon radial backdrops are banned in favor of curated brand palettes.
  4. Tabular Numerals (tabular-nums): Monetary sums and data table counts must specify font tabular figures to prevent horizontal character shifting during live updates.
  5. 5-State Interactive Affordance: Buttons and controls must provide clear visual states for default, hover, focus-visible, active (pressed), and disabled.
  6. Anti-Decorative Emojis: Prohibits rocket (🚀), sparkles (✨), and fire (🔥) clutter in enterprise titles and badges.

Read the full file on GitHub · 158 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. yesterday Changed · +71 lines 2f9f91808106
  2. 2d ago First seen · 87 lines · 89 tokens per session scan A c30fd22c8027

Subscribe to this mod's changes

visual-ui-auditor is a skill published in the GitHub repository roedyrustam/vibes-plug (78 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,313 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-17.

Related

Other skills, from other repositories

frontend-ui-engineering

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

addyosmani/agent-skills · 58 tokens

frontend-blueprint

AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the…

tech-leads-club/agent-skills · 170 tokens

bootstrap

Expert Bootstrap 5 assistance covering 12-column grid system, flexbox utilities, components, and responsive breakpoints. Use when rapidly prototyping responsive, mobile-first web layouts.

G1Joshi/Agent-Skills · 37 tokens

shadcnui

Expert shadcn/ui assistance covering Radix UI primitives, Tailwind CSS styling, copy-paste architecture, and accessibility. Use when building modern React component systems and accessible design systems.

G1Joshi/Agent-Skills · 42 tokens

tailwindcss

Expert Tailwind CSS assistance covering utility classes, responsive variants, arbitrary values, and configuration. Use when styling modern web applications with speed and consistency.

G1Joshi/Agent-Skills · 33 tokens

frontend-ui-engineering

Front-load UI construction decisions — component boundary and prop API, state placement, required states, responsiveness, accessibility. Use when creating or refactoring a component, page, or design-system primitive. Don't use for pure logic (/tdd), throwaway exploration (/prototype), or auditing finished UI…

helderberto/agent-skills · 69 tokens