What is cpf-validador AGENTS.md?

A repository instruction guide for coding agents working on a Brazilian CPF lookup service. It explains the service's REST, MCP, and web interfaces, its code layout, and rules such as not storing real people's data.

Use it before editing the project, running commands, adding tests or examples, or changing its APIs and user interface.

It gives an agent the project context and prevents changes that break important data-handling or implementation rules.

How opastorello/cpf-validador configures Codex and OpenCode

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/opastorello/cpf-validador/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/opastorello/cpf-validador

Made for: Codex, OpenCode.

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/instructions/opastorello/cpf-validador/agents-md/github.svg)](https://agentmods.dev/instructions/opastorello/cpf-validador/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/opastorello/cpf-validador/agents-md"><img src="https://agentmods.dev/badge/instructions/opastorello/cpf-validador/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/opastorello/cpf-validador/agents-md"><img src="https://agentmods.dev/badge/instructions/opastorello/cpf-validador/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,349 This file is loaded in full into every session.

When invoked 4,349 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.04349	$0.04349
Opus 5.5	$0.01740	$0.01740
Sonnet 5.5	$0.00870	$0.00870
Haiku 4.5	$0.00435	$0.00435

Measured 1mo ago against content hash c55a4353fde8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cpf-validador AGENTS.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 1mo 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.

AGENTS.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guia para qualquer agente de código (Codex, Cursor, Claude Code, Copilot…) que for trabalhar neste repositório. Explica o que o projeto faz, como cada parte funciona e as regras que não podem ser quebradas. O CLAUDE.md tem o mesmo conteúdo em formato de referência rápida; se os dois divergirem, o código manda e os dois devem ser corrigidos.

O que é

Serviço que responde "a quem pertence este CPF?" consultando bases públicas, e que recupera um CPF incompleto ou digitado errado. Expõe a mesma lógica por três portas:

REST (FastAPI) — app/routers/
MCP (FastMCP 3.0, streamable-http em /mcp) — app/mcp_server.py, 6 tools
Interface web em / — uma página única servida por app/routers/ui.py

Nada é persistido no servidor: o histórico da interface vive no localStorage do navegador.

Regras que não se quebram

Dado real nunca entra no repositório. Ele é público. CPF, nome ou certidão de pessoa real não vão para teste, fixture, exemplo de API, README, CHANGELOG nem mensagem de commit — inclusive o CPF que alguém informou para reproduzir um bug e a versão "corrigida" dele. Use o CPF de exemplo do projeto, 151.879.820-95, e derive dele os casos inválidos (151.879.820-98, 151.979.820-95). Nome de exemplo: FULANO DE TAL. Antes de commitar, git grep pelo dado usado na reprodução.
CPF nunca sai inteiro no log. Use sources/base.py::mascarar_cpf() (111.***.***-35). Nome de certidão só em DEBUG. tests/test_logging.py trava as duas.
services/ não importa FastAPI nem FastMCP. É Python puro.
Routers e tools MCP nunca importam uma fonte concreta — só services.sources.consultar e consultar_multiplos.
Uma fonte nunca levanta exceção para quem chama: falha vira {"cpf": ..., "encontrado": None, "erro": "..."}.
Um commit por mudança, em português (fix:, fix(ui):, build:, ci:, chore:), sem Co-Authored-By nem assinatura de ferramenta.
Toda mudança é documentada no README (no padrão existente) e no CHANGELOG.md.
Subir a versão e dar push no master publica uma release (ver "CI e release").

Read the full file on GitHub · 278 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.

1mo ago First seen · 278 lines · 4,349 tokens per session scan A c55a4353fde8

Subscribe to this mod's changes

cpf-validador AGENTS.md is an instructions file published in the GitHub repository opastorello/cpf-validador (23 stars, last pushed 1mo ago), licensed MIT. It adds 4,349 tokens to every session, about $0.0174 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 2026-09-19.

Project management Writing and docs captcha cpf crnn fastapi fastmcp mcp

cpf-validador AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cpf-validador AGENTS.mdopastorello/cpf-validador	Instructions file	23	1mo ago	MIT	A	4,349	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cpf-validador: Instructions file for Codex