mcp-browser: Skill for Claude Code

.claude/skills/browser-mcp-campanha-confiabilidade-do-agente/SKILL.md

browser-mcp-campanha-confiabilidade-do-agente is a skill for Claude Code from flpccabral/mcp-browser. It costs 278 tokens per session (6,418 once invoked), scanned A, original, MIT.

A Portuguese-language testing and improvement guide for the AI agent inside a browser MCP server. It uses an observe, think, check, act, and record cycle to measure how reliably the agent completes browser tasks.

In plain words
What is it for?
Benchmarking browser-agent success, investigating parsing or provider problems, adding reliability improvements such as retries and backoff, and deciding whether changes are ready to promote.
Why use it?
It replaces subjective judgments with before-and-after benchmark results and distinguishes agent problems from issues caused by slow or rate-limited AI providers.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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-campanha-confiabilidade-do-agente/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-campanha-confiabilidade-do-agente

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-campanha-confiabilidade-do-agente"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-campanha-confiabilidade-do-agente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 278 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,418 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 $0.00278 $0.06418
Opus 5 $0.00139 $0.03209
Sonnet 5 $0.00056 $0.01284
Haiku 4.5 $0.00028 $0.00642

Measured 11d ago against content hash 43e0052bb637, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

browser-mcp-campanha-confiabilidade-do-agente 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/benchmark_agent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-campanha-confiabilidade-do-agente/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Campanha: confiabilidade do agente LLM

Este é o problema mais difícil em aberto do repositório. O dono declarou: a CONFIABILIDADE do agente (src/browser_mcp/agent.py, classe BrowserAgent, loop execute_task OBSERVE→THINK→CHECK→ACT→RECORD) é o alvo. O SOTA público (browser-use, 104k stars) reporta 87.4% em 200 tarefas do benchmark Odysseys (dado externo, 2026-07-13). Toda esta campanha existe para trocar "acho que melhorou" por um número.

Linha de base estabelecida em 2026-07-18 (ver baseline-2026-07-18.md): com provedor rápido e sem rate limit (gemma4:31b-cloud), 7/7 (100%) estável no conjunto offline, 0 incidentes de parse. A "não-confiabilidade" dos runs anteriores (Ollama lento, NVIDIA free rate-limited) era confound de provedor, não defeito do agente. Fase 1 desnecessária; Fase 2 (retry/backoff) implementada e validada como upside puro; o conjunto de 7 tarefas está saturado — a próxima alavanca é ampliar o benchmark com tarefas mais difíceis para achar o teto real.

Regra de ouro (leia antes de qualquer coisa)

Nenhuma mudança no agente é promovida sem número de benchmark ANTES e DEPOIS. Sucesso é MENSURÁVEL, nunca a olho. Prompt-tweaking sem benchmark é caminho cercado (ver seção "Caminhos cercados").

Toda promoção passa pelo gate de [[browser-mcp-controle-de-mudancas]] e não pode introduzir NOVAS regressões. Contagem verificada 2026-07-17: .venv/bin/python -m pytest tests/ --collect-only -q lista os testes coletados; algumas suítes de smoke são flaky por timeout de rede (httpbin/networkidle). O critério é: sem novas regressões além dessa flakiness conhecida de rede, não "tudo verde cegamente".

Quando NÃO usar esta skill

  • Um bug pontual quebrou em runtime (click não funciona, extensão não conecta, timeout esperando elemento) → [[browser-mcp-playbook-de-depuracao]] (triagem sintoma→causa). Esta skill é campanha sistemática, não triagem.
  • Você quer entender POR QUE o agente é assim (isTrusted, @e refs, histórico de design) → [[browser-mcp-arqueologia-de-falhas]] e [[browser-automacao-referencia]].
  • Você vai só rodar o servidor / conectar extensão[[browser-mcp-executar-e-operar]].
  • Você quer comparar com concorrentes ou escrever claim público[[browser-mcp-fronteira-e-posicionamento]].
  • A mudança não toca o agente (nova tool, config) → outras skills.

Read the full file on GitHub · 377 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 · 377 lines · 278 tokens per session scan A 43e0052bb637

Subscribe to this mod's changes

browser-mcp-campanha-confiabilidade-do-agente is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 278 tokens to every session and 6,418 once invoked, about $0.0014 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

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

playwright-cli

A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.

UnicomAI/wanwu · 76 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

anthropics/skills · 35 tokens

create-verification-skill

Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".

get-bb/bb · 57 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens