What is browser-mcp-arqueologia-de-falhas?

A Portuguese-language project history for mcp_browser, a browser-automation project. It records past investigations, design decisions, failed approaches, incidents, and their evidence.

Use it before investigating unusual behavior, proposing design changes, or revisiting discussions in the mcp_browser project.

It helps contributors avoid repeating investigations or reopening decisions that the project has already settled. The document also shows how to verify historical claims with commands.

How flpccabral/mcp-browser configures Claude Code

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-arqueologia-de-falhas/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-arqueologia-de-falhas/github.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-arqueologia-de-falhas)

Your own site

<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-arqueologia-de-falhas"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-arqueologia-de-falhas/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-arqueologia-de-falhas"><img src="https://agentmods.dev/badge/skills/flpccabral/mcp-browser/browser-mcp-arqueologia-de-falhas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,120 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.

Model	Per session	Once invoked
Fable 5.1	$0.00175	$0.04120
Opus 5.5	$0.00070	$0.01648
Sonnet 5.5	$0.00035	$0.00824
Haiku 4.5	$0.00017	$0.00412

Measured 2mo ago against content hash 706737602a85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-mcp-arqueologia-de-falhas 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.

.claude/skills/browser-mcp-arqueologia-de-falhas/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arqueologia de Falhas — mcp_browser

Este documento é a crônica do repositório: cada investigação maior, beco sem saída, decisão e incidente, no formato Sintoma/Pergunta → Causa raiz/Decisão → Evidência → Status. Objetivo: ninguém reabre batalha já vencida.

Regras de leitura:

Toda evidência é um comando copiável. Rode-o antes de confiar — o histórico já foi reescrito uma vez (filter-repo em 2026-07-12) e pode ser reescrito de novo.
Os docs históricos de investigação foram removidos do working tree no commit ddf9bc1, mas continuam recuperáveis via git show cbc8e28:<arquivo>. Isso é intencional: o commit raiz cbc8e28 é o arquivo morto do projeto.
Status possíveis: resolvido (implementado e verificável no código), cercado (o problema não tem solução — há uma regra ativa impedindo reincidência), aberto (dívida ou pendência conhecida).

Índice rápido

#	Entrada	Data	Status
1	Benchmark Kimi WebBridge → decisões de arquitetura	~2026-06/07	resolvido
2	Investigação de indicadores visuais	2026-07-01	resolvido
3	Descoberta isTrusted (eventos sintéticos)	≤2026-07-10	cercado
4	Commit P0 `cbc8e28` — os 4 fixes	2026-07-10	resolvido
5	Incidente da chave privada `extension.pem`	2026-07-12	aberto (regenerar chave)
6	Estado do lint	2026-07-12	resolvido (dívida quitada; escopo do CI limpo)

1. Benchmark Kimi WebBridge → decisões de arquitetura (~junho/julho 2026)

Sintoma/Pergunta: Por que o WebBridge da Moonshot resolvia sites legados (com sessão real do usuário e dropdowns em cascata AJAX) melhor que nosso agente Playwright puro? O que copiar?

Causa raiz/Decisões geradas:

@e refs de accessibility tree — o WebBridge referencia elementos por refs semânticas (@e3) da árvore de acessibilidade, não por seletores CSS. Sobrevive a mudanças de classe/hash. Decisão: suportar @e refs em browser_click/browser_type e expor a árvore.
Modo extensão (sessão real do usuário) — o WebBridge opera no perfil Chrome real do usuário (cookies, logins, extensões). Playwright isolado não faz isso. Decisão: arquitetura híbrida — Playwright como padrão + extensão Chrome para sessão real.
Network monitoring nativo — comandos network start/list/detail de primeira classe, em vez de interceptors manuais.

Read the full file on GitHub · 213 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.

2mo ago First seen · 213 lines · 0 tokens per session scan A 706737602a85

Subscribe to this mod's changes

browser-mcp-arqueologia-de-falhas is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 3mo ago), licensed MIT. It adds 175 tokens to every session and 4,120 once invoked, about $0.0007 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-arqueologia-de-falhas next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
browser-mcp-arqueologia-de-falhasflpccabral/mcp-browser	Skill	0	3mo ago	MIT	A	175	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

mcp-browser: Skill for Claude Code