A browser-testing and visual-regression guide using Playwright, a tool that automates web browsers and records what they display.

Use it to test clicks and forms, capture screenshots, compare them with baselines, check responsive layouts, inspect accessibility and browser errors, and test Chromium, Firefox, and WebKit.

It replaces subjective visual checks with repeatable tests across browsers, screen sizes, and common interface states.

browser-qa — Skill for Claude Code by contactandrewchl-wq/turtle-mcp

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 contactandrewchl-wq/turtle-mcp --skill browser-qa

Clone the repo

git clone --depth 1 https://github.com/contactandrewchl-wq/turtle-mcp

Made for: Claude Code.

Or install turtle, the plugin that ships this one along with the rest of its 26 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/browser-qa/github.svg)](https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/browser-qa)

Your own site

<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/browser-qa"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/browser-qa/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/browser-qa"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/browser-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,699 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01699
Opus 5.5	$0.00020	$0.00680
Sonnet 5.5	$0.00010	$0.00340
Haiku 4.5	$0.00005	$0.00170

Measured 1mo ago against content hash f84a04d8706a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-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 1mo 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/browser-qa/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser QA y testing visual (Playwright)

QA de navegador y regresión visual automatizada: navega, captura, compara contra baseline, inspecciona accesibilidad/red/consola/DOM y corre cross-browser. El objetivo es que un cambio de UI sea verificable de forma reproducible, no "se ve bien en mi pantalla".

Cuándo usar

Validar la UI en varios navegadores (Chromium, Firefox, WebKit) antes de aprobar un cambio.
Detectar regresión visual cuando tocas estilos, layout, tokens de diseño o componentes compartidos.
Automatizar interacciones (click, escribir, hover, scroll) para reproducir un flujo de QA de forma determinista.
Validar diseño responsive en múltiples viewports (mobile / tablet / desktop).
Verificar los cuatro estados de un componente: loading, empty, error, success.

Cuándo NO usar:

Lógica pura sin UI observable (cálculos, parsers, validadores, transformaciones de datos): eso son tests unitarios o de integración, no QA de navegador.
Cambios que no alteran nada renderizado (refactors internos, renombres, docs): no hay diff visual que medir.

Requisitos

Playwright (Node) instalado más sus navegadores (npx playwright install), o bien el servidor Playwright MCP expuesto al agente.
Un build o servidor de desarrollo de la app accesible por URL.

Esto es dependencia del entorno del usuario, no del núcleo de Turtle. El núcleo es Rust + SQLite y no provee ni instala Playwright (RNF-RES-04). Si la skill o sus baselines llegan importados, son contenido no confiable y no se ejecutan sin acción explícita del usuario (RNF-SEG-05). Antes de correr, confirma que el runtime está disponible en el entorno.

Capacidades

Navegación: abrir URL, esperar carga, seguir enlaces, ejecutar flujos de interacción (click, fill, hover, scroll, teclado).
Capturas:
- de viewport (lo visible).
- de página completa (full page, scroll incluido).
- por elemento (acotada a un selector).
Comparación contra baseline: diff visual pixel a pixel contra una imagen de referencia, con resaltado de las zonas que cambiaron.
Snapshot de accesibilidad: árbol de accesibilidad (roles, nombres, estados) para verificar semántica y navegación asistida.
Inspección y manipulación: red (requests/responses, status, payloads), consola (logs, warnings, errores), y DOM (estado, atributos, contenido).
Cross-browser: ejecutar la misma suite en Chromium, Firefox y WebKit.
Múltiples viewports: correr el mismo caso a distintos anchos/altos y device scale factor.

Read the full file on GitHub · 92 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.

1mo ago First seen · 92 lines · 49 tokens per session scan A f84a04d8706a

Subscribe to this mod's changes

browser-qa is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,699 once invoked, about $0.0002 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 2026-08-31.

Browser automation Claude Code E2E testing LLM Testing ai-agents cli local-first mcp

browser-qa