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.
curl -O https://raw.githubusercontent.com/flpccabral/mcp-browser/main/.claude/skills/browser-mcp-validacao-e-qa/SKILL.mdgit clone --depth 1 https://github.com/flpccabral/mcp-browserWrote 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.
[](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-validacao-e-qa)<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>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 | $0.00177 | $0.04256 |
| Opus 5 | $0.00088 | $0.02128 |
| Sonnet 5 | $0.00035 | $0.00851 |
| Haiku 4.5 | $0.00018 | $0.00426 |
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 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(scopefunction, isolamento por teste): importa o singletonbrowser_managerdebrowser_mcp.browser_manager, chamaawait browser_manager.start(), entrega, e para comstop()emtry/except. - Browser: Chromium headless do Playwright (o mesmo que
playwright install chromiumbaixa). 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 — onavigateesperanetworkidle, então httpbin lento fazPage.goto: Timeout 30000msmesmo com a rede "no ar". - Helper
_evaluate(page, expr)embrulhapage.evaluate(f"({expr})")porquereturncru dáSyntaxErrorno Playwright.
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.
- 7d ago First seen · 313 lines · 177 tokens per session scan A 7df249731b1a
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.
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).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
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.
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".
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.
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…