Borrowing it
Nothing to install: this file belongs to rodrigopg/mcp-brazil-marketplaces. 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/rodrigopg/mcp-brazil-marketplaces/main/CLAUDE.mdgit clone --depth 1 https://github.com/rodrigopg/mcp-brazil-marketplacesWrote 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/instructions/rodrigopg/mcp-brazil-marketplaces/claude-md)<a href="https://agentmods.dev/instructions/rodrigopg/mcp-brazil-marketplaces/claude-md"><img src="https://agentmods.dev/badge/instructions/rodrigopg/mcp-brazil-marketplaces/claude-md/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/instructions/rodrigopg/mcp-brazil-marketplaces/claude-md"><img src="https://agentmods.dev/badge/instructions/rodrigopg/mcp-brazil-marketplaces/claude-md.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 | $0.00992 | $0.00992 |
| Opus 5 | $0.00496 | $0.00496 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
mcp-brazil-marketplaces CLAUDE.md 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-brazil-marketplaces
MCP server (FastMCP/stdio) que expõe tools para buscar anúncios em marketplaces brasileiros (OLX, Mercado Livre). Python 3.10+, publicado no PyPI.
Carregar contexto antes de trabalhar
Leia o arquivo correspondente à área da tarefa antes de tocar código:
| Área | Arquivo |
|---|---|
Estrutura do server.py, padrões de tool, schema unificado, adicionar marketplace novo |
.claude/context/arquitetura.md |
| Bypass de bloqueios OLX/ML, fallback Jina, perfis browser, micro-landing | .claude/context/anti-bloqueio.md |
| SSRF, ReDoS, OOM, coerce defensivo, correlation IDs, allowlists | .claude/context/seguranca.md |
| Pytest layout, async, monkeypatch env, ruff config, padrões de teste | .claude/context/testes.md |
| Trusted Publishing, branch protection, cortar release, GitHub Actions | .claude/context/release.md |
Env vars MCP_BR_*, logging, rate limit, diagnóstico prod |
.claude/context/operacao.md |
Se a tarefa tocar múltiplas áreas, leia os arquivos em paralelo.
Regras inegociáveis
- Toda mudança = issue + teste + lint verde. Sem exceções, mesmo "ajustinho de 2 linhas". Issue antes do código, PR fecha via
Closes #N. - Nunca push direto em
main. Branch + PR + CI matrix 3.10–3.13 verde + squash merge. - Nunca raise exceção para o caller MCP. Tools sempre retornam
json.dumps(...); erros viram{"erro": "..."}com correlation ID via_handle_http_error. - Nunca aceitar URL externa sem
_validar_url_<m>. SSRF é bloqueador hard. Allowlist por hostname. - Nunca usar
.*?emre.DOTALLsobre input externo. Classes de caracteres explícitas ([^<]+) + cap de tamanho. - Nunca recriar regex em loop.
re.compileno module level. - Toda chamada HTTP via
_RateGate. Sem isso = queima de IP em loop LLM. - Toda resposta tem campo
fonte(olx,olx_jina,ml). LLM precisa saber a origem. - Não usar
selenium/playwrightem runtime do MCP. Pesado demais para stdio.
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.
- 12d ago First seen · 72 lines · 992 tokens per session scan A 03596d2cbd37
mcp-brazil-marketplaces CLAUDE.md is an instructions file published in the GitHub repository rodrigopg/mcp-brazil-marketplaces (0 stars, last pushed 1mo ago), licensed MIT. It adds 992 tokens to every session, about $0.0050 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 instructions, from other repositories
vibetags com-example-service-OrderService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.