mcp-browser: Skill for Claude Code

.claude/skills/browser-mcp-playbook-de-depuracao/SKILL.md

browser-mcp-playbook-de-depuracao is a skill for Claude Code from flpccabral/mcp-browser. It costs 142 tokens per session (5,371 once invoked), scanned A, original, MIT.

A troubleshooting playbook for a browser MCP server. It maps symptoms such as failed clicks, connection errors, and element timeouts to checks and likely causes.

In plain words
What is it for?
Use it to diagnose browser automation issues, extension and WebSocket connections, missing dropdown data, overlays, and related runtime problems.
Why use it?
It gives developers a structured way to investigate real runtime failures instead of guessing where the problem is.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Gemini CLI.

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-playbook-de-depuracao/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-playbook-de-depuracao

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-playbook-de-depuracao"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-playbook-de-depuracao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,371 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.05371
Opus 5 $0.00071 $0.02686
Sonnet 5 $0.00028 $0.01074
Haiku 4.5 $0.00014 $0.00537

Measured 11d ago against content hash cb6b78475e3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

browser-mcp-playbook-de-depuracao 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.

.claude/skills/browser-mcp-playbook-de-depuracao/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playbook de Depuração — browser-mcp-server

Runbook sintoma → causa → experimento para os modos de falha REAIS deste projeto, construído lendo o código (mensagens de erro, guards, timeouts) e os documentos históricos recuperáveis via git show cbc8e28:<doc>.md. Linhas verificadas em 2026-07-17 — re-confira após refactors grandes.

Quando NÃO usar esta skill

  • Setup/instalação quebrada (dependências, playwright install, venv) → browser-mcp-build-e-ambiente.
  • Como rodar/operar o servidor (comandos de start, modos) → browser-mcp-executar-e-operar.
  • Significado de cada flag/env varbrowser-mcp-config-e-flags.
  • A crônica completa dos incidentesbrowser-mcp-arqueologia-de-falhas (este playbook referencia as histórias, não as reconta).
  • Catálogo das ferramentas de medição (network log, HAR, console) → browser-mcp-diagnosticos-e-ferramentas.
  • Teoria por trás de isTrusted/CSP/MV3browser-automacao-referencia.
  • Escrever/alterar códigobrowser-mcp-contrato-de-arquitetura e browser-mcp-controle-de-mudancas.

Pré-triagem universal: torne o stderr visível

Todos os logs vão para stderr com prefixos [SERVER], [WS-SERVER], [EXTENSION-BRIDGE], [TOOLS] (verificado em server.py:68, websocket_server.py:91, extension_bridge.py:55, tools.py:98). Rodando sob um cliente MCP, o stderr costuma ser engolido. Antes de qualquer triagem:

cd /caminho/do/repo/mcp_browser
.venv/bin/python -m browser_mcp.server 2> /tmp/mcp_stderr.log &   # ou: browser-mcp-server (console script)
tail -f /tmp/mcp_stderr.log

Duas armadilhas de "engolimento" tornam isso obrigatório — ver sintomas 7 e 8.

Mapa rápido sintoma → seção

Sintoma Seção
Click não faz nada / evento ignorado 1
Extensão Chrome não conecta ao WebSocket 2
Timeout esperando elemento / dropdown vazio 3
Overlay/indicador visual não aparece 4
Agente em loop / repete ação / estoura iterações 5
ERROR: [Server] - ... genérico sem stack 6
Startup "funciona" mas browser não iniciou 7

Read the full file on GitHub · 246 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. 11d ago First seen · 246 lines · 142 tokens per session scan A cb6b78475e3f

Subscribe to this mod's changes

browser-mcp-playbook-de-depuracao is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 5,371 once invoked, about $0.0007 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.

Related

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.

ChromeDevTools/chrome-devtools-mcp · 31 tokens

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.

ChromeDevTools/chrome-devtools-mcp · 50 tokens

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).

ChromeDevTools/chrome-devtools-mcp · 55 tokens

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).…

chromium/chromium · 119 tokens

nullaway

Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.

chromium/chromium · 43 tokens

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.

chromium/chromium · 52 tokens