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 5.5 | $0.00098 | $0.02001 |
| Sonnet 5.5 | $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 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.
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.
- 2mo 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 3mo ago), licensed MIT. It adds 246 tokens to every session and 5,002 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-mcp-contrato-de-arquitetura compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| browser-mcp-contrato-de-arquiteturaflpccabral/mcp-browser | Skill | 0 | 3mo ago | MIT | A | 246 | 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 |