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-arqueologia-de-falhas/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-arqueologia-de-falhas)<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.
<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>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 | $0.00088 | $0.02060 |
| Sonnet 5 | $0.00035 | $0.00824 |
| Haiku 4.5 | $0.00017 | $0.00412 |
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 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 — 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 viagit show cbc8e28:<arquivo>. Isso é intencional: o commit raizcbc8e28é 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:
@erefs 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@erefs embrowser_click/browser_typee 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/detailde primeira classe, em vez de interceptors manuais.
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 · 213 lines · 0 tokens per session scan A 706737602a85
browser-mcp-arqueologia-de-falhas is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 175 tokens to every session and 4,120 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…