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-diagnosticos-e-ferramentas/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-diagnosticos-e-ferramentas)<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-diagnosticos-e-ferramentas"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-diagnosticos-e-ferramentas/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-diagnosticos-e-ferramentas"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-diagnosticos-e-ferramentas.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 | $0.00187 | $0.04869 |
| Opus 5 | $0.00093 | $0.02434 |
| Sonnet 5 | $0.00037 | $0.00974 |
| Haiku 4.5 | $0.00019 | $0.00487 |
Grade A, and why
browser-mcp-diagnosticos-e-ferramentas 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnósticos e Ferramentas — browser-mcp-server
Este projeto tem instrumentos para medir o browser em vez de adivinhar. Esta skill cataloga cada um, mostra o comando exato e — o mais importante — como ler a saída. Todas as referências file:line e contagens foram verificadas em 2026-07-17; re-confira após refactors grandes (veja "Proveniência e manutenção").
Regra de ouro: antes de propor uma causa, produza uma medição que a discrimine. Se a resposta for "olhei e parece que...", pare e escolha um instrumento abaixo.
Quando NÃO usar esta skill
- Algo QUEBROU e você quer triar o sintoma (click não funciona, extensão não conecta, timeout) →
browser-mcp-playbook-de-depuracao(ele usa estes instrumentos na triagem). - Teoria por trás de CDP/CSP/isTrusted/accessibility/MV3 →
browser-automacao-referencia. - Significado/default de cada env var →
browser-mcp-config-e-flags(aqui só damos o scriptcheck_env.pyque mostra o valor efetivo). - A crônica de por que o console/overlay/extensão são assim →
browser-mcp-arqueologia-de-falhas. - Como provar uma alegação com rigor →
browser-mcp-metodologia-e-prova.
Tabela — qual instrumento para qual pergunta
| Pergunta | Ferramenta / script | Comando | Como ler |
|---|---|---|---|
| Que chamada AJAX popula este dropdown? | browser_network_start → interagir → browser_network_list |
network_start, mudar o <select> pai, network_list com filter_method="POST" |
procure o request disparado depois da sua ação; o response_body traz as options |
| Que endpoints a página bate? | browser_get_network_log |
get_network_log com filter_url="/api" |
JSON detalhado com headers + body (truncado em 50000 bytes) |
| Guardar a sessão de rede para análise | browser_export_har |
export_har com path="webbridge_output/x.har" |
HAR 1.2 — abra no DevTools "Import HAR" ou em har-viewer |
| A página deu erro JS? (só modo extensão) | browser_get_console_errors |
get_console_errors com filter_text="GraphQL" |
só captura console.warn/console.error — veja limitação abaixo |
| Que elementos existem e com que ref estável? | browser_accessibility_tree |
accessibility_tree |
lista de {ref:@eN, role, name}; use o @eN depois |
| Visão alternativa dos clicáveis | get_interactive_elements (interno) |
via agente/CDP | tag/id/name/text/selector dos até 50 primeiros visíveis |
| Quais ferramentas existem mesmo? | scripts/dump_tools.py |
python .../dump_tools.py |
39 nomes + descrição (README diz 37 — divergência aberta) |
| Minha env var tem efeito? | scripts/check_env.py |
python .../check_env.py |
valor efetivo + o que o .env.example documenta errado |
| Testar a extensão sem cliente MCP | ws_client.py (raiz) |
python ws_client.py navigate '{"url":"..."}' |
JSON cru da resposta da extensão |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 223 lines · 187 tokens per session scan A 11ce37b5f1bf
browser-mcp-diagnosticos-e-ferramentas is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 4,869 once invoked, about $0.0009 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
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.