mcp-browser: Skill for Claude Code

.claude/skills/browser-mcp-build-e-ambiente/SKILL.md

browser-mcp-build-e-ambiente is a skill for Claude Code from flpccabral/mcp-browser. It costs 153 tokens per session (2,793 once invoked), scanned C, original, MIT.

A Portuguese guide for rebuilding the browser-mcp-server development environment from a fresh checkout. It covers the virtual environment, installation, Chromium setup, and common Python-version differences between local work and continuous-integration tests.

In plain words
What is it for?
Use it for initial setup or when browser tests fail after cloning. It covers pytest checks and points to separate guides for operation, configuration, debugging, architecture, and quality checks.
Why use it?
It helps distinguish a broken setup from known repository problems before debugging the code itself.

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 →

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-build-e-ambiente/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-build-e-ambiente

README.md
[![agentmods](https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-build-e-ambiente/github.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-build-e-ambiente)
Your own site
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-build-e-ambiente"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-build-e-ambiente/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.

agentmods 80×15 button for browser-mcp-build-e-ambiente

Your own site · 80×15
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-build-e-ambiente"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-build-e-ambiente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,793 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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 $0.00153 $0.02793
Opus 5 $0.00077 $0.01396
Sonnet 5 $0.00031 $0.00559
Haiku 4.5 $0.00015 $0.00279

Measured 9d ago against content hash c7af4ad6a77c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

browser-mcp-build-e-ambiente scanned grade C 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist/
.claude/skills/browser-mcp-build-e-ambiente/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build e ambiente do browser-mcp-server

Guia para recriar o ambiente de desenvolvimento do zero e reconhecer os sintomas de ambiente quebrado vs dívida conhecida do repositório.

Termos usados uma vez e reaproveitados:

  • repo raiz — diretório que contém pyproject.toml.
  • suíte completapytest tests/ (43 testes em 3 arquivos).
  • testes de browser — os testes de tests/test_smoke.py, tests/test_tools.py e a maioria de tests/test_agent.py, que iniciam um Chromium real via browser_manager.start().

Quando NÃO usar esta skill

Necessidade Use em vez desta
Rodar/operar o servidor MCP, modos de execução browser-mcp-executar-e-operar
Catálogo completo de variáveis de ambiente e flags browser-mcp-config-e-flags
Depurar comportamento em runtime browser-mcp-playbook-de-depuracao
Entender falha histórica ou regressão browser-mcp-arqueologia-de-falhas
Regras de arquitetura e limites de mudança browser-mcp-contrato-de-arquitetura / browser-mcp-controle-de-mudancas
Validação/QA de uma mudança browser-mcp-validacao-e-qa
Referência das ferramentas de automação browser-automacao-referencia
Diagnóstico com ferramentas embutidas browser-mcp-diagnosticos-e-ferramentas

Requisitos

Item Valor Fonte
Python mínimo >= 3.11 pyproject.toml (requires-python)
Python no CI matriz 3.11 / 3.12 / 3.13 .github/workflows/ci.yml
Python no .venv local 3.14 (verificado em 2026-07-12) .venv/bin/python --version
Build backend hatchling pyproject.toml [build-system]
Pacote src/browser_mcp [tool.hatch.build.targets.wheel]
Entry point CLI browser-mcp-server = browser_mcp.server:main [project.scripts]
Pytest asyncio_mode = "auto", testpaths = ["tests"] [tool.pytest.ini_options]

Diferença local vs CI: o .venv do repo roda Python 3.14, mas o CI só testa 3.11–3.13 e os classifiers do pyproject.toml param em 3.13. Algo que passa localmente pode se comportar diferente nas versões oficialmente suportadas — na dúvida, trate 3.11–3.13 como o alvo de compatibilidade. Confirme sua versão antes de investigar qualquer diferença de comportamento:

Read the full file on GitHub · 244 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. 9d ago First seen · 244 lines · 153 tokens per session scan C c7af4ad6a77c

Subscribe to this mod's changes

browser-mcp-build-e-ambiente is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 153 tokens to every session and 2,793 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens