Borrowing it
Nothing to install: this file belongs to lab-dados/juscraper-mcp. 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/lab-dados/juscraper-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/lab-dados/juscraper-mcpWrote 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/lab-dados/juscraper-mcp/claude-md)<a href="https://agentmods.dev/instructions/lab-dados/juscraper-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lab-dados/juscraper-mcp/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/lab-dados/juscraper-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lab-dados/juscraper-mcp/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 | $0.00670 | $0.00670 |
| Opus 5.5 | $0.00268 | $0.00268 |
| Sonnet 5.5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
juscraper-mcp 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 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Servidor MCP público do juscraper (consultas a tribunais brasileiros sem autenticação),
deployado em Azure Container Apps. Segue os padrões do repo irmão
../escritorio-servicos (ver o CLAUDE.md de lá). O pacote consumido é
../juscraper (instalado via git+https no build).
Comandos
Python é gerido exclusivamente por uv. Nunca pip install. O uv.lock
não é commitado (resolvido no build da imagem).
uv sync
uv run uvicorn main:app --reload --port 8080
uv run pytest
uv run ruff check . && uv run ruff format .
uv run python scripts/smoke_client.py [url] [--real]
Estrutura
main.py— entrypoint ASGI (main:app).juscraper_mcp/server.py— FastMCP (stateless + json_response, obrigatório para scale-to-zero), instructions,/health.juscraper_mcp/tools.py— tools MCP. Regras invioláveis:- toda chamada ao juscraper passa por
_executar(semáforo + thread + timeout); - filtros
Nonenão são repassados (os schemas do juscraper têmextra="forbid"); - erros viram
ToolErrorcom mensagem em português que oriente o modelo a corrigir.
- toda chamada ao juscraper passa por
juscraper_mcp/registry.py— catálogo de tribunais. Para adicionar um tribunal novo, adicione a entrada aqui (e nada mais, se o juscraper já o suporta viajus.scraper(sigla)). Critério de entrada: funciona sem autenticação e sem captcha (TJMG e JusBR ficam fora).juscraper_mcp/serialize.py— DataFrame → JSON truncado (limites emsettings.py).infra/— Terraform que reusa o RG/CAE/ACR do escritorio-servicos. Não criar recursos de custo fixo. Orçamento do projeto: R$ 200/mês (budget alert já configurado);max_replicas=20existe para uso em sala de aula, masmin_replicas=0e 0.25 vCPU são decisões de custo — não aumentar sem discutir.
Testes
Os testes não acessam tribunais: tests/test_tools.py usa sessão MCP em memória
(mcp.shared.memory) com _get_scraper monkeypatchado. Ao corrigir um bug, adicione um
teste que falhe no código antigo. Verificação real contra tribunais: só via
scripts/smoke_client.py --real, manualmente.
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 · 51 lines · 670 tokens per session scan A b4de1f8a1b8c
juscraper-mcp CLAUDE.md is an instructions file published in the GitHub repository lab-dados/juscraper-mcp (8 stars, last pushed 5mo ago), licensed MIT. It adds 670 tokens to every session, about $0.0027 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.
juscraper-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| juscraper-mcp CLAUDE.mdlab-dados/juscraper-mcp | Instructions file | 8 | 5mo ago | MIT | A | 670 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 279k | today | MIT | A | 4,325 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |