mcp-browser: Skill for Claude Code

.claude/skills/browser-mcp-validacao-e-qa/SKILL.md

browser-mcp-validacao-e-qa is a skill for Claude Code from flpccabral/mcp-browser. It costs 177 tokens per session (4,256 once invoked), scanned A, original, MIT.

A testing and quality guide for a browser MCP server. It explains the real test suite, its commands, and what evidence is needed before claiming that behavior works.

In plain words
What is it for?
Running the smoke, tool, and agent tests; adding tests; and understanding browser, network, asynchronous-test, lint, and CI requirements.
Why use it?
It prevents vague or unverified claims by requiring a named passing test and the exact command that runs it.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is flpccabral/mcp-browser's own configuration. It tells Claude Code how to work on mcp-browser itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-browser configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./.venv/bin/pytest tests/ -q.

Reuse

Borrowing it

Nothing to install: this file belongs to flpccabral/mcp-browser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/flpccabral/mcp-browser/main/.claude/skills/browser-mcp-validacao-e-qa/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/flpccabral/mcp-browser

Made for: Claude Code.

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 browser-mcp-validacao-e-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-validacao-e-qa.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-validacao-e-qa)
Your own site
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-validacao-e-qa"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-validacao-e-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00177 $0.04256
Opus 5 $0.00088 $0.02128
Sonnet 5 $0.00035 $0.00851
Haiku 4.5 $0.00018 $0.00426

Measured 7d ago against content hash 7df249731b1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

browser-mcp-validacao-e-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 7d 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.

Makes network callslowCapability

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

`httpbin.org`. `curl https://httpbin.org/get` responde `200` em ~1s, mas o
.claude/skills/browser-mcp-validacao-e-qa/SKILL.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validação e QA — MCP Browser Server

Esta skill define a disciplina de aceitação deste repositório: o que conta como prova, qual é a suíte real, como rodá-la, como estendê-la e como o lint/CI se comportam de verdade (não como o README imagina). Público: engenheiro pleno sem contexto prévio. Voz imperativa. Comandos copiáveis.

Antes de dizer que algo "funciona", releia a seção Disciplina de evidência.

Regra-mãe

Uma afirmação de comportamento só é aceita com (1) um teste verde nomeado mais (2) o comando exato que o roda.

Sem esses dois itens, a afirmação é hipótese — trate-a como [[browser-mcp-metodologia-e-prova]] manda.


Anatomia da suíte REAL

A suíte vive em tests/. Config em pyproject.toml ([tool.pytest.ini_options] com asyncio_mode = "auto" — por isso testes async def rodam sem decorador @pytest.mark.asyncio em test_tools.py/test_agent.py). São 3 arquivos, 43 testes coletados (medido 2026-07-18: 43 tests collected).

Arquivo Testes Precisa de browser real? Precisa de rede? O que prova
tests/test_smoke.py 10 (E2E) Sim (Chromium via Playwright) Sim (httpbin.org) Navegação, type, click, screenshot, stealth, overlay, nova aba — fim a fim
tests/test_tools.py 22 (camada MCP) Sim Parcial (usa data: URIs + example.com) Cada tool via app.call_tool(...) retorna o texto esperado
tests/test_agent.py 11 (agente) Parcial (fixture sobe browser; parsing/prune não) Não (MockLLM) Loop do agente SEM LLM real: parsing, prune, max_iterations, erros consecutivos

test_smoke.py — E2E contra browser + páginas reais

  • Fixture browser (scope function, isolamento por teste): importa o singleton browser_manager de browser_mcp.browser_manager, chama await browser_manager.start(), entrega, e para com stop() em try/except.
  • Browser: Chromium headless do Playwright (o mesmo que playwright install chromium baixa). Contexto em [[browser-mcp-build-e-ambiente]].
  • Páginas-alvo: https://httpbin.org/* (get, headers, forms/post, ip) e navegação real. Isso torna os smokes dependentes de rede e sensíveis a latência — o navigate espera networkidle, então httpbin lento faz Page.goto: Timeout 30000ms mesmo com a rede "no ar".
  • Helper _evaluate(page, expr) embrulha page.evaluate(f"({expr})") porque return cru dá SyntaxError no Playwright.

Read the full file on GitHub · 313 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. 7d ago First seen · 313 lines · 177 tokens per session scan A 7df249731b1a

Subscribe to this mod's changes

browser-mcp-validacao-e-qa is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 4,256 once invoked, about $0.0009 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

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

playwright-cli

A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.

UnicomAI/wanwu · 76 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

anthropics/skills · 35 tokens

create-verification-skill

Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".

get-bb/bb · 57 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens