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-contrato-de-arquitetura/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-contrato-de-arquitetura)<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-contrato-de-arquitetura"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-contrato-de-arquitetura/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.
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-contrato-de-arquitetura"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-contrato-de-arquitetura.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00246 | $0.05002 |
| Opus 5 | $0.00123 | $0.02501 |
| Sonnet 5 | $0.00049 | $0.01000 |
| Haiku 4.5 | $0.00025 | $0.00500 |
Grade A, and why
browser-mcp-contrato-de-arquitetura 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contrato de arquitetura do browser-mcp-server
Este documento descreve o que o sistema É, por que foi desenhado assim, o que NÃO pode ser quebrado, e o que já está quebrado. Todos os fatos, caminhos e números de linha foram verificados contra o código em 2026-07-18. Re-verifique com os comandos da seção final antes de citar em outro contexto.
Quando NÃO usar esta skill
| Necessidade | Use em vez desta |
|---|---|
| Recriar o ambiente (venv, playwright install) | [[browser-mcp-build-e-ambiente]] |
| Rodar os 3 modos na prática (comandos de operação) | [[browser-mcp-executar-e-operar]] |
| Catálogo completo de variáveis de ambiente | [[browser-mcp-config-e-flags]] |
| Depurar um sintoma específico (triagem) | [[browser-mcp-playbook-de-depuracao]] |
| Histórico de investigações de falhas passadas | [[browser-mcp-arqueologia-de-falhas]] |
| Medir: network log, HAR, console errors | [[browser-mcp-diagnosticos-e-ferramentas]] |
| Rodar a suíte de testes e coletar evidência | [[browser-mcp-validacao-e-qa]] |
| Teoria geral (MCP, CDP, a11y, isTrusted, CSP, MV3) | [[browser-automacao-referencia]] |
| Confiabilidade do agente autônomo (problema #1) | [[browser-mcp-campanha-confiabilidade-do-agente]] |
| Posicionamento vs. browser-use e concorrentes | [[browser-mcp-fronteira-e-posicionamento]] |
| Barra de evidência e metodologia de prova | [[browser-mcp-metodologia-e-prova]] |
| Gates de mudança, estilo de docs, publicação | [[browser-mcp-controle-de-mudancas]] |
Esta skill é o mapa conceitual. As irmãs acima são os runbooks operacionais.
O que é o sistema
Um servidor MCP (Model Context Protocol — protocolo pelo qual um LLM chama
ferramentas via stdio) de automação de browser, em Python (>=3.11), pacote
browser-mcp-server 0.1.0. Dependências de runtime: mcp, playwright,
httpx, python-dotenv (pyproject.toml:39-44). Suíte: 43 testes
(verificado 2026-07-18; a maioria requer playwright install chromium).
Mapa de módulos em src/browser_mcp/ (linhas verificadas 2026-07-18):
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.
- 11d ago First seen · 321 lines · 246 tokens per session scan A ed4afe862a27
browser-mcp-contrato-de-arquitetura is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 246 tokens to every session and 5,002 once invoked, about $0.0012 per session on Opus 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.
Other skills, from other repositories
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…
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.
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.
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.
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.
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…