Borrowing it
Nothing to install: this file belongs to opastorello/cpf-validador. 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/opastorello/cpf-validador/master/CLAUDE.mdgit clone --depth 1 https://github.com/opastorello/cpf-validadorWrote 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/opastorello/cpf-validador/claude-md)<a href="https://agentmods.dev/instructions/opastorello/cpf-validador/claude-md"><img src="https://agentmods.dev/badge/instructions/opastorello/cpf-validador/claude-md.svg" alt="Measured on agentmods" 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 | $0.02992 | $0.02992 |
| Opus 5 | $0.01496 | $0.01496 |
| Sonnet 5 | $0.00598 | $0.00598 |
| Haiku 4.5 | $0.00299 | $0.00299 |
Grade A, and why
cpf-validador 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 yesterday.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guia para o Claude Code ao trabalhar neste repositório.
Comandos
# Instalar dependências (requirements-trt3.txt inclui o PyTorch da CRNN)
pip install -r requirements-trt3.txt
# Rodar localmente (FastAPI + FastMCP na porta 8000)
uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
# Docker (porta 8002 conforme docker-compose.yaml)
docker compose up --build -d
docker compose down
Testes automatizados (mockam o TRT3, rodam no CI):
pip install -r requirements-dev.txt
ruff check app/
pytest tests/ -v
Testes manuais via:
- Interface web:
http://localhost:8000/ - FastAPI docs (apenas
ENV=development):http://localhost:8000/docs - MCP transport:
http://localhost:8000/mcp(streamable-http)
Arquitetura
FastAPI (app/main.py) com routers REST + FastMCP 3.0 montado em /mcp. A camada services/ não tem dependência de framework.
app/
├── main.py # FastAPI — routers + rate limiter + mcp.http_app() em /mcp
├── config.py # Lê todas as variáveis de ambiente com defaults
├── mcp_server.py # FastMCP("cpf-validador") — 6 tools wrapping services
├── auth.py # TokenMiddleware — autenticação via API_TOKEN + controle prod/dev via ENV
├── rate_limit.py # Limiter compartilhado — main.py e routers/consulta.py precisam do mesmo objeto
├── services/
│ ├── cpf.py # Lógica pura de CPF (zero deps de framework)
│ └── sources/ # Fontes de consulta — a fonte ativa vem de SOURCE no .env
│ ├── base.py # ABC Fonte + contrato do retorno + mascarar_cpf (log)
│ ├── __init__.py # Registro preguiçoso + busca em lote (agnóstica de fonte)
│ ├── trt3.py # TRT3: curl_cffi + CAPTCHA CRNN + pypdf
│ ├── tcu.py # TCU: API JSON + Altcha (PoW PBKDF2), sem pypdf
│ └── exemplo.py # Modelo para novas fontes — fictícia, sem rede e sem CAPTCHA
├── routers/
│ ├── cpf.py # POST /cpf/validate, POST /cpf/variations
│ ├── consulta.py # POST /consulta/cpf, /cpfs, /buscar-por-mascara, /buscar-por-variacoes
│ └── ui.py # GET / — interface web com gate de autenticação
└── captcha/
├── model.py # Arquitetura CRNN (CNN + BiLSTM + CTC Loss)
├── predictor.py # Inferência — carrega captcha_model.pt
├── dataset.py # CaptchaDataset com data augmentation
├── train.py # Loop de treino com early stopping + AMP + registry
├── collector.py # Coleta amostras rotuladas do TRT3 (--workers N)
├── registry.py # Versionamento de modelos (models/vN/model.pt + meta.json)
└── models/ # Histórico de versões treinadas
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.
- yesterday Changed · +91 lines · +1,506 tokens per session b55121730e80
- 6d ago First seen · 102 lines · 1,486 tokens per session scan A aed565b62212
cpf-validador CLAUDE.md is an instructions file published in the GitHub repository opastorello/cpf-validador (22 stars, last pushed 2d ago), licensed MIT. It adds 2,992 tokens to every session, about $0.0150 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 2026-08-30.
Other instructions, from other repositories
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.