What is browser-mcp-metodologia-e-prova?

A Portuguese-language guide for testing claims about the browser MCP server with evidence. MCP is a standard way for AI agents to use external tools, and this guide focuses on proving that a claim is true.

Use it when investigating hypotheses, deciding what can safely be stated, or designing experiments and evidence for the browser MCP server.

It helps prevent conclusions based only on intuition by requiring a mechanism that explains the observations and survives a planned attempt to disprove it.

How flpccabral/mcp-browser configures Claude Code

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-metodologia-e-prova/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-metodologia-e-prova/github.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-metodologia-e-prova)

Your own site

<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-metodologia-e-prova"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-metodologia-e-prova/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/flpccabral/mcp-browser/browser-mcp-metodologia-e-prova"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-metodologia-e-prova.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 240 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,896 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	$0.00240	$0.05896
Opus 5.5	$0.00096	$0.02358
Sonnet 5.5	$0.00048	$0.01179
Haiku 4.5	$0.00024	$0.00590

Measured 2mo ago against content hash 7a0bfbe5b539, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-mcp-metodologia-e-prova 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 2mo 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.

.claude/skills/browser-mcp-metodologia-e-prova/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metodologia e Prova — como transformar intuição em resultado aceito NESTE repo

Esta skill define a barra de evidência do projeto e fornece seis receitas de prova, cada uma com um exemplo resolvido extraído da história real deste repositório. A regra da casa em uma frase: prove, não apenas instale.

Público: engenheiro sem contexto prévio. Todos os comandos de verificação rodam a partir da raiz do repo. Comandos git show referem-se ao commit histórico cbc8e28 ("feat: 4 P0 fixes", 2026-07-10), que contém os relatórios de investigação removidos do working tree atual.

Quando NÃO usar esta skill

Triagem rápida de um bug em produção — use browser-mcp-playbook-de-depuracao (esta skill é o rigor por trás da triagem, não a triagem em si).
Passar pelo gate formal de merge (testes obrigatórios, lint, README) — use browser-mcp-controle-de-mudancas.
Escolher o instrumento de medição (network log, HAR, screenshot, accessibility tree) — use browser-mcp-diagnosticos-e-ferramentas.
Consultar uma ideia já aposentada — o registro vive em browser-mcp-arqueologia-de-falhas.
Rodar a suíte de testes formal / evidência de QA — use browser-mcp-validacao-e-qa.

Parte A — Barra de evidência

A.1 Um mecanismo deve explicar TODAS as observações

Um mecanismo proposto só é aceito se explicar todas as observações, inclusive as negativas (o que NÃO aconteceu), e sobreviver a uma refutação adversarial designada (receita B.6).

Regras práticas:

Liste as observações numeradas ANTES de propor o mecanismo — positivas e negativas ("o click falha em X" E "o click funciona em Y").
Para cada observação, escreva como o mecanismo a explica. Uma observação sem explicação = mecanismo incompleto ou errado.
Um mecanismo que explica só as observações convenientes é uma racionalização, não uma explicação.

Exemplo do padrão neste repo: os testes do agente cobrem tanto o caminho feliz (test_execute_task_simple) quanto os negativos — teto de iterações (test_max_iterations) e erros consecutivos (test_consecutive_errors) em tests/test_agent.py. Um mecanismo de loop testado só no caminho de sucesso poderia estar ignorando silenciosamente as condições de parada.

Read the full file on GitHub · 387 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.

2mo ago First seen · 387 lines · 240 tokens per session scan A 7a0bfbe5b539

Subscribe to this mod's changes

browser-mcp-metodologia-e-prova is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 3mo ago), licensed MIT. It adds 240 tokens to every session and 5,896 once invoked, about $0.0010 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 Research

browser-mcp-metodologia-e-prova next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
browser-mcp-metodologia-e-provaflpccabral/mcp-browser	Skill	0	3mo ago	MIT	A	240	Claude Code
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code

mcp-browser: Skill for Claude Code