visual-qa-compare

visual-qa-compare is a skill for Claude Code, Codex from atezer/FMCP. It costs 95 tokens per session (2,306 once invoked), scanned A, original, MIT.

A read-only visual comparison between a Figma design and a screenshot of the coded interface. It checks how closely the implemented screen matches the design in appearance.

In plain words
What is it for?
Use it to validate a UI implementation before delivery, compare Figma and browser screenshots, and create a report of spacing, colour, and typography differences.
Why use it?
It helps find visible differences that code or design-token checks may miss, such as altered spacing, colours, or text styling. It reports the differences without changing the Figma file.

Skill for Claude CodeCodex

Part of the figma-mcp-bridge plugin — 28 skills, 11 commands, 4 agents, 1 MCP server 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 skills/atezer/fmcp/visual-qa-compare
Any agent
npx skills add atezer/FMCP --skill visual-qa-compare
Clone the repo
git clone --depth 1 https://github.com/atezer/FMCP

Made for: Claude Code, Codex.

Or install figma-mcp-bridge, the plugin that ships this one along with the rest of its 28 skills, 11 commands, 4 agents, 1 MCP server.

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-compare

README.md
[![agentmods](https://agentmods.dev/badge/skills/atezer/fmcp/visual-qa-compare.svg)](https://agentmods.dev/skills/atezer/fmcp/visual-qa-compare)
Your own site
<a href="https://agentmods.dev/skills/atezer/fmcp/visual-qa-compare"><img src="https://agentmods.dev/badge/skills/atezer/fmcp/visual-qa-compare.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,306 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 $0.00095 $0.02306
Opus 5 $0.00048 $0.01153
Sonnet 5 $0.00019 $0.00461
Haiku 4.5 $0.00010 $0.00231

Measured 4d ago against content hash 6ccc5a8055a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-qa-compare 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 4d 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.

skills/visual-qa-compare/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual QA Compare — Figma vs Kod Görsel Karşılaştırma

Design Token Kuralı: Bu skill'deki kod örneklerinde geçen font adları, renk kodları, piksel boyutları yalnızca FORMAT gösterimidir. Çalışma anında tüm design token değerleri (font, renk, boyut, spacing, radius, gölge) kayıtlı kütüphaneden (figma_get_variables, figma_get_styles) veya kullanıcıdan okunmalıdır. Hardcoded token değeri kullanma. Detay: project-context.md → "Design Token Kuralı".

Overview

Bu skill, Figma tasarımı ile kodlanmış UI arasındaki görsel farkları tespit eder. design-drift-detector token/kod tabanlı çalışırken, bu skill pixel/görsel tabanlı karşılaştırma yapar.

Salt okunur — Figma tuvalinde değişiklik yapmaz.

Fark: visual-qa-compare vs design-drift-detector

Özellik visual-qa-compare design-drift-detector
Odak Görsel/pixel farklar Token/kod değer farkları
Girdi Figma screenshot + kod UI screenshot Figma variable'lar + kod token dosyaları
Çıktı Görsel fark raporu (spacing, renk, tipografi) Drift raporu (değer uyumsuzlukları)
Araç figma_capture_screenshot + figma_get_design_context figma_check_design_parity + figma_get_variables

Prerequisites

  • F-MCP Bridge plugin bağlı olmalı
  • Kodlanmış UI'ın çalışır durumda screenshot'ı alınabilmeli (dev server veya deploy)
  • Hedef Figma ekranın node ID'si bilinmeli

F-MCP skill koordinasyonu

  • Birlikte: design-drift-detector ile token bazlı kontrol (görsel + token = tam QA)
  • Önce (isteğe bağlı): implement-design çıktısı sonrası doğrulama
  • Sonra: Fark varsa fix-figma-design-system-finding (Figma tarafı) veya kod düzeltme

Required Workflow

Step 1: Plugin Bağlantısını Doğrula

figma_get_status()

Step 2: Figma Screenshot Al

figma_capture_screenshot(nodeId="<NODE_ID>", format="PNG", scale=2)

Step 3: Figma Design Context Al

DERİN ANALİZ KURALI: Sadece frame/node isimlerine bakarak sonuç çıkarma. Her node'un içindeki text content (characters), instance prop'ları ve child yapılarını detaylı oku. Bir şeyin "eksik" veya "yok" olduğunu iddia etmeden önce tüm child node'ların içeriğini kontrol et.

Read the full file on GitHub · 208 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. 4d ago First seen · 208 lines · 95 tokens per session scan A 6ccc5a8055a2

Subscribe to this mod's changes

visual-qa-compare is a skill published in the GitHub repository atezer/FMCP (9 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,306 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

system-pitch

Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…

murphytrueman/design-system-ops · 72 tokens

token-audit

Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…

murphytrueman/design-system-ops · 93 tokens

ai-component-description

Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…

murphytrueman/design-system-ops · 132 tokens

context-engine-builder

Generate a context engine — seven structured blueprint files (UX, UI, content, accessibility, ethical, technical, business intelligence) that encode everything an AI agent needs to work with a design system. This produces YAML infrastructure in .ai/context-engine/, NOT a health score or quality assessment. Trigger…

murphytrueman/design-system-ops · 135 tokens

stakeholder-brief

Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…

murphytrueman/design-system-ops · 73 tokens

token-compliance

Check a codebase or implementation for token compliance — finding hardcoded values, wrong-tier token references, and inconsistent token application in consuming code. This checks how tokens are used in code, NOT how the tokens themselves are defined or structured. Trigger when someone says: are we using tokens…

murphytrueman/design-system-ops · 120 tokens