visual-qa

visual-qa is a skill for Claude Code, Codex from sauravvarma/garage. It costs 305 tokens per session (5,077 once invoked), scanned A, original, MIT.

A process for checking a running website by taking screenshots at its intended screen sizes and comparing them with the project's design guidance and related pages.

In plain words
What is it for?
Use it after changing frontend layouts or components, when checking responsive breakpoints, or before declaring a visual task complete.
Why use it?
It finds visual problems that code checks may miss, such as broken layouts, spacing, colors, or behavior at different screen widths.

Skill for Claude CodeCodex

Part of the garage plugin — 6 skills, 1 hook 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/sauravvarma/garage/visual-qa
Any agent
npx skills add sauravvarma/garage --skill visual-qa
Clone the repo
git clone --depth 1 https://github.com/sauravvarma/garage

Made for: Claude Code, Codex.

Or install garage, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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/skills/sauravvarma/garage/visual-qa.svg)](https://agentmods.dev/skills/sauravvarma/garage/visual-qa)
Your own site
<a href="https://agentmods.dev/skills/sauravvarma/garage/visual-qa"><img src="https://agentmods.dev/badge/skills/sauravvarma/garage/visual-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 305 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00305 $0.05077
Opus 5 $0.00152 $0.02538
Sonnet 5 $0.00061 $0.01015
Haiku 4.5 $0.00030 $0.00508

Measured 5d ago against content hash 0b518e7dcec5, 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 scanned grade A with 1 finding 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/capture.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Not running →** *do not silently spawn a long-running process.* Surface to the user: *"Dev server doesn't appear to be running at `[base URL]`. Want me to start it with `[discovered command]`, or will you start it ma
skills/visual-qa/SKILL.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual QA

Automated visual verification loop for frontend projects. Takes screenshots of the running app at defined breakpoints, reads them (multimodal), and checks against the project's own spec — not hardcoded assumptions.

When to use

  • After making layout or component changes
  • User asks "does this look right", "check breakpoints", "visual QA"
  • Before reporting a layout task as complete
  • When you can't verify a visual QA checklist item from code alone

Spec preflight

Before capturing anything, verify what's available. Visual-qa is graceful — it can run with minimal context and still do useful work — but tell the user what's missing so they understand which checks will and won't fire.

Required:

  • A way to run the app — discovered from CLAUDE.md "Commands" section or package.json scripts (Phase 0a). If neither yields a dev/start command, ask the user.
  • Playwright — auto-installed in Phase 1 if missing.

Recommended (enables project-specific checks):

  • docs/DESIGN-TOKENS.md — without it, no token/color/typography checks
  • docs/DESIGN-LANGUAGE.md — without it, no semantic role checks (rest vs interaction, etc.)

Optional (enables design ↔ code comparison):

  • docs/DESIGN-TAXONOMY.md with rows marked Final and Synced — without it, only spec-vs-code comparison runs; design-vs-code is skipped

If recommended docs are missing, tell the user: "Project-specific design checks won't run — only universal checks (no horizontal overflow, fonts loaded, touch target sizes, etc.). Run /spec-first-project-setup to scaffold the docs and fill them in, or proceed with universal-only checks."


Phase 0: Learn the Project

Before capturing anything, build a project profile by reading project configuration. This is what makes the skill work across any frontend project.

0a. Discover dev server

Read these sources in order (stop at first match):

  1. CLAUDE.md — look for a "Commands" section with dev / start / run commands. Treated as authoritative.
  2. README.md — look for a "Getting started" / "Development" / "Run locally" section that names the command. Confirm the extracted command with the user before treating it as authoritative (prose-derived; easier to mis-parse than CLAUDE.md).
  3. Ask the user directly.

Read the full file on GitHub · 319 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 319 lines · 305 tokens per session scan A 0b518e7dcec5

Subscribe to this mod's changes

visual-qa is a skill published in the GitHub repository sauravvarma/garage (3 stars, last pushed 1mo ago), licensed MIT. It adds 305 tokens to every session and 5,077 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

testing-and-quality

Use throughout the build and before claiming any phase or the project "done", to run the four mandatory quality gates and verify them with evidence. Covers the test pyramid, Playwright + Chrome DevTools browser verification, WCAG AA, and the commit/finish gate wiring.

martian56/claude-engineer · 58 tokens

testing-strategy

Use when defining a project's test approach, when choosing what gets tested at unit vs integration vs e2e level, when setting per-component coverage targets, when reviewing test quality, or when CI is slow / flaky and tests need a strategy reset.

aneja5/forge-skills · 53 tokens

test-native-extension

Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…

microsoft/power-platform-skills · 211 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens