What is browser-mcp-controle-de-mudancas?

Change-management instructions for a browser MCP server. They explain how to classify code changes and what testing, linting, and documentation are required before merging them.

Use them when adding MCP tools, changing agent behavior or browser extensions, updating documentation, or preparing a change for publication.

They help developers follow the repository's review rules and avoid repeating known incidents or missing required checks.

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-controle-de-mudancas/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-controle-de-mudancas/github.svg)](https://agentmods.dev/skills/flpccabral/mcp-browser/browser-mcp-controle-de-mudancas)

Your own site

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

Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,792 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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	$0.00183	$0.03792
Opus 5	$0.00092	$0.01896
Sonnet 5	$0.00037	$0.00758
Haiku 4.5	$0.00018	$0.00379

Measured 10d ago against content hash 12651c85f7f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

browser-mcp-controle-de-mudancas scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist/

.claude/skills/browser-mcp-controle-de-mudancas/SKILL.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Controle de Mudanças — browser MCP server

Como mudanças são classificadas, condicionadas e revisadas neste repositório; os inegociáveis (com racional e incidente histórico); o estilo da casa para docs; e o processo de publicação. Fatos voláteis estão datados de 2026-07-18 — re-verifique com os comandos da última seção.

Definições usadas uma vez, valendo para o documento inteiro:

Tool MCP — função registrada com decorator @app.tool(...) em src/browser_mcp/tools.py.
Gate de CI — .github/workflows/ci.yml (jobs lint, test).
README na convenção da casa — ver seção "Estilo da casa para docs".

Quando NÃO usar esta skill

Sua pergunta é sobre...	Use a irmã
Design, invariantes de arquitetura, onde uma feature deve viver	`browser-mcp-contrato-de-arquitetura`
Instalar, criar venv, `playwright install`, dependências	`browser-mcp-build-e-ambiente`
Subir o servidor, operar em produção	`browser-mcp-executar-e-operar`
Variáveis de ambiente e flags	`browser-mcp-config-e-flags`
Depurar uma falha em andamento	`browser-mcp-playbook-de-depuracao`
A crônica completa dos incidentes (aqui só há o resumo por inegociável)	`browser-mcp-arqueologia-de-falhas`
O que conta como evidência de que algo funciona	`browser-mcp-validacao-e-qa`
Confiabilidade do agente autônomo	`browser-mcp-campanha-confiabilidade-do-agente`
Referência de automação de browser em geral	`browser-automacao-referencia`

Esta skill responde uma pergunta só: "o que precisa ser verdade antes de esta mudança entrar em main ou virar release?"

1. Classes de mudança e o que é obrigatório antes de mergear

Toda mudança cai em exatamente uma classe primária (a mais restritiva que se aplique). Requisitos são cumulativos com a linha "Todas".

Classe	Exemplos	Obrigatório antes de mergear
Todas	—	`ruff check src/browser_mcp tests` e `ruff format --check src/browser_mcp tests` limpos localmente (o CI NÃO vai pegar na branch — ver seção 3); commit convencional (`feat:`/`fix:`/`docs:`/`ci:`/`chore:`)
Nova tool MCP	novo `@app.tool(...)` em `tools.py`	Teste cobrindo a tool em `tests/test_tools.py`; atualizar a tabela de tools do README e a contagem declarada (README cita a contagem em 4 lugares — linhas 4, 8, 116 e 211 hoje); se a tool for exposta ao agente, atualizar o catálogo no system prompt de `src/browser_mcp/agent.py`
Mudança no agente	loop, system prompt, dispatch em `agent.py`	Teste em `tests/test_agent.py`; se mexer no system prompt, preservar a regra do `isTrusted` (inegociável 2); rodar a suíte completa `pytest tests/` local (o job `test` do CI roda `test_tools` + `test_agent`; `test_smoke` fica fora por depender de httpbin.org)
Mudança na extensão	`extension/background.js`, `injected.js`, `manifest.json`	Não há suíte automatizada para `extension/` (`tests/` só cobre Python) — evidência manual obrigatória seguindo `browser-mcp-validacao-e-qa`; JAMAIS commitar `.pem`/`.crx` (inegociável 1); se mudar comportamento visível, atualizar seção da extensão no README
Docs	README, PUBLISH.md, docs/	Toda alegação nova com referência `arquivo:linha` conferida; contagens re-conferidas contra o código (ver seção 4 — há divergência aberta hoje)

Read the full file on GitHub · 271 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.

10d ago First seen · 271 lines · 183 tokens per session scan C 12651c85f7f3

Subscribe to this mod's changes

browser-mcp-controle-de-mudancas is a skill published in the GitHub repository flpccabral/mcp-browser (0 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 3,792 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens

mcp-browser: Skill for Claude Code