visual-consistency-tester

visual-consistency-tester is an agent for Claude Code from tan-yong-sheng/ai-vision-mcp. It costs 20 tokens per session (3,273 once invoked), scanned A, original, MIT.

A visual review role that checks whether an interface follows its design tokens—the shared rules for colors, fonts, spacing, corners, and shadows—and whether screenshots show unintended changes.

In plain words
What is it for?
Use it to compare a current interface with a baseline, check design-system compliance, and identify specific visual changes that need correction.
Why use it?
It helps detect visual regressions, inconsistent styling, and responsive-layout problems across screen sizes and interaction states.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; $skill-name invocation.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the design-eval plugin — 5 skills, 5 commands, 4 agents shipped together

Good fit Use it to compare a current interface with a baseline, check design-system compliance, and identify specific visual changes that need correction.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add tan-yong-sheng/ai-vision-mcp
Claude Code
/plugin install design-eval

Made for: Claude Code.

Or install design-eval, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 4 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-consistency-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/tan-yong-sheng/ai-vision-mcp/visual-consistency-tester/github.svg)](https://agentmods.dev/agents/tan-yong-sheng/ai-vision-mcp/visual-consistency-tester)
Your own site
<a href="https://agentmods.dev/agents/tan-yong-sheng/ai-vision-mcp/visual-consistency-tester"><img src="https://agentmods.dev/badge/agents/tan-yong-sheng/ai-vision-mcp/visual-consistency-tester/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-consistency-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/tan-yong-sheng/ai-vision-mcp/visual-consistency-tester"><img src="https://agentmods.dev/badge/agents/tan-yong-sheng/ai-vision-mcp/visual-consistency-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,273 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 $0.00020 $0.03273
Opus 5 $0.00010 $0.01636
Sonnet 5 $0.00004 $0.00655
Haiku 4.5 $0.00002 $0.00327

Measured 12d ago against content hash 71a32e5bbd54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

visual-consistency-tester 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 12d 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.

plugins/design-eval/agents/visual-consistency-tester.md · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Consistency Tester Agent

Expert visual design validator specializing in token compliance checking and visual regression detection. Validates token usage across components, detects visual changes, and ensures alignment with design system specifications across breakpoints and interaction states.

Responsibilities

  • Validates design token usage against design system standards
  • Detects visual regressions by comparing baseline and current screenshots
  • Analyzes visual properties for compliance and changes
  • Identifies token compliance violations and unintended modifications
  • Measures consistency and regression metrics
  • Identifies responsive design issues across breakpoints
  • Provides remediation guidance aligned to design system

Visual Consistency Scope

This agent validates token compliance across multiple dimensions:

Design Token Compliance

  • Color palette usage (primary, secondary, tertiary, neutral, semantic colors)
  • Typography consistency (font families, sizes, weights, line heights, letter spacing)
  • Spacing and layout (padding, margins, gaps, alignment)
  • Shape and border radius (component corners, consistency across UI)
  • Shadows and elevation (depth, layering, visual hierarchy)
  • Motion and animation (transitions, timing, easing functions)

Responsive Design Validation

  • Mobile breakpoint (320px-480px)
  • Tablet breakpoint (768px-1024px)
  • Desktop breakpoint (1024px+)
  • Layout shifts and reflow behavior
  • Touch target sizing and spacing
  • Readable text sizes at all breakpoints

Visual State Coverage

  • Light mode appearance
  • Dark mode appearance
  • High contrast mode
  • Reduced motion preferences
  • Interactive states (hover, focus, active, disabled)
  • Loading and error states

Regression Detection

  • Pixel-perfect baseline comparison
  • Layout shift detection
  • Color and typography changes
  • Spacing deviations
  • Component size changes

For detailed token mapping, violation detection, severity categorization, and remediation patterns, see the visual-consistency-validation skill. IMPORTANT: Use the playwright-cli-automation skill to capture full-page screenshots before invoking analysis commands.

Read the full file on GitHub · 388 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. 12d ago First seen · 388 lines · 20 tokens per session scan A 71a32e5bbd54

Subscribe to this mod's changes

visual-consistency-tester is an agent published in the GitHub repository tan-yong-sheng/ai-vision-mcp (78 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 3,273 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 2026-08-30.

Related

Other agents, from other repositories

ring:qa-frontend

Senior Frontend QA Analyst for React/Next.js. Supports 5 modes — unit (default), accessibility, visual, e2e, performance. Dispatched with mode parameter; loads mode-specific file from qa-frontend-modes/.

LerianStudio/ring · 53 tokens

accessibility_specialist

Accessibility specialist for WCAG compliance auditing, ARIA implementation review, keyboard navigation testing, and inclusive design assessment. Use when the task requires accessibility audits, screen reader compatibility checks, color contrast verification, or ARIA role validation. For example: auditing a web app for…

josstei/maestro-orchestrate · 83 tokens

a11y-write-playwright-tests

Write Playwright accessibility tests for a component or page: axe scan file and keyboard-only variant. Triggers when the user asks to 'add a11y tests', 'write axe test', 'add keyboard test', or 'create accessibility test for X'.

AmadeusITGroup/otter · 59 tokens

visual-qa-agent

Visual QA: screenshot analysis, wireframe comparison, regression detection. Usar PROACTIVELY cuando se detectan cambios en componentes UI o se ejecutan tests E2E.

gonzalezpazmonica/savia · 41 tokens

implementer

Ship production code from approved plans. Tests alongside code. Atomic commits.

rjmurillo/ai-agents · 17 tokens

ia-accessibility-tester

WCAG 2.1/2.2 accessibility audit: keyboard navigation, screen reader, contrast, ARIA, forms, cognitive. Use for accessibility review, WCAG compliance, or inclusive design assessment.

iliaal/whetstone · 48 tokens