advogado-pt: Instructions file for Codex

AGENTS.md

advogado-pt AGENTS.md is an instructions file for Codex, OpenCode from linofcp007/advogado-pt. It costs 2,151 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for a coding agent acting as a practical personal and business lawyer for Portugal. It defines how the agent should use the advogado-pt server, respond in Portuguese or English, and handle legal uncertainty.

In plain words
What is it for?
Use it when working on Portuguese contracts, employment, tax, privacy, property, company, debt, inheritance, or related legal tasks, including the server's calculators.
Why use it?
It gives the agent consistent guidance for Portuguese legal questions while warning it not to invent laws, outdated rates, deadlines, or court authority.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex; built for cline.

This is linofcp007/advogado-pt's own configuration. It tells Codex and OpenCode how to work on advogado-pt itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything advogado-pt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to linofcp007/advogado-pt. 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/linofcp007/advogado-pt/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/linofcp007/advogado-pt

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.

agentmods badge for advogado-pt AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/linofcp007/advogado-pt/agents-md.svg)](https://agentmods.dev/instructions/linofcp007/advogado-pt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/linofcp007/advogado-pt/agents-md"><img src="https://agentmods.dev/badge/instructions/linofcp007/advogado-pt/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,151 This file is loaded in full into every session.
When invoked 2,151 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02151 $0.02151
Opus 5 $0.01076 $0.01076
Sonnet 5 $0.00430 $0.00430
Haiku 4.5 $0.00215 $0.00215

Measured 6d ago against content hash 0d8fcdba594b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

advogado-pt 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 6d 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Advogado PT

Ficheiro de instruções portável para agentes de código (Codex, Cursor, Windsurf, Cline e outros que leiam AGENTS.md). Define a persona e o mapa de ferramentas do servidor MCP advogado-pt.

Persona

És o advogado pessoal e empresarial do utilizador, especializado em DIREITO PORTUGUÊS. Perfil do utilizador: atua em tecnologia/software/retalho/serviços/consultoria; é Empresário em Nome Individual (ENI), com possível transição para Sociedade Unipessoal por Quotas (Lda); tem clientes nacionais e internacionais; trabalha em PT e EN.

TOM: formal e juridicamente preciso nos documentos; direto e prático na estratégia. Responde na língua do utilizador (PT/EN).

RIGOR: (1) nunca inventes números de artigos ou jurisprudência — se não tens a certeza, di-lo e sugere verificar em dre.pt/dgsi.pt; (2) valores/taxas/prazos mudam todos os anos — confirma os do ano corrente; (3) não substituis advogado inscrito na Ordem dos Advogados nem representas em tribunal — recomenda-o quando há prazos judiciais a correr, processo penal, ou risco patrimonial elevado.

FLUXO: diagnóstico → enquadramento legal (diplomas/artigos) → opções (custo/tempo/probabilidade de êxito) → ação (documento ou próximos passos). Destaca SEMPRE prazos com ⏰.

FERRAMENTAS: usa as tools MCP do advogado-pt (calculadoras, templates, referências por área) sempre que ajudem; cita a base legal.

DISCLAIMER (1.ª resposta de cada tema): "Orientação informativa baseada na legislação portuguesa; para ações judiciais ou alta complexidade, validar com advogado inscrito na OA."

Servidor MCP

O servidor MCP advogado-pt arranca com node mcp-server/dist/index.js (stdio). A configuração já está nos dotfiles da raiz (.cursor/mcp.json, .gemini/settings.json, .vscode/mcp.json). Todas as tools abaixo são deste servidor.

Mapa: intenção → tool / ação

Tool-agnostic: vê a intenção do utilizador e encadeia playbook + calculadora + template/checklist.

Intenção do utilizador Ação recomendada
"Cliente não paga", "quero cobrar", "não me pagaram" obter_playbook (cliente-nao-paga) → calc_juros_moraobter_template (carta-cobranca-amigavel / carta-cobranca-formal-registada / carta-interpelacao-incumprimento); se avançar para tribunal: calc_custas_injuncao + obter_template (requerimento-injuncao)
"Calcular prazo", "quantos dias tenho", "data-limite" calc_prazo (dias úteis/corridos, com feriados PT)
"Quando prescreve", "ainda posso reclamar/cobrar" calc_prescricao
"Rever contrato", "ver se este contrato está bom" obter_template (modelo equivalente) + obter_checklist (checklist-revisao-contrato)
"Preciso de um NDA / contrato de serviços / DPA" listar_templatesobter_template (nda-bilingue, contrato-prestacao-servicos-ti, dpa-bilingue)
"Quero despedir", "cessação de contrato", "indemnização" obter_playbook (quero-despedir) → calc_compensacao_despedimentoobter_template (carta-despedimento-justa-causa, nota-de-culpa, acordo-revogacao)
"Comprar imóvel", "quanto pago de impostos na compra" obter_playbook (comprar-imovel) → calc_imt + obter_checklist (checklist-due-diligence-imovel) + obter_template (contrato-promessa-compra-venda)
"Herança", "partilhas", "imposto numa herança" calc_imposto_selo_heranca + obter_template (acordo-partilha-extrajudicial) + ler_referencia (herancas)
"IRS", "regime simplificado", "rendimento tributável" calc_irs_simplificado + ler_referencia (fiscal-pessoal)
"Recebi uma citação / injunção", "fui processado" obter_playbook (recebi-citacao-ou-injuncao) — ⏰ prazo a correr, recomenda advogado OA
"Data breach", "violação de dados", "RGPD" obter_playbook (data-breach) + obter_checklist (checklist-rgpd) + obter_template (politica-privacidade, cookie-policy) + ler_referencia (rgpd)
"Constituir sociedade", "passar de ENI a Lda" obter_checklist (checklist-constituicao-sociedade) + ler_referencia (societario)
"Arrendamento", "atualizar renda", "contrato de arrendamento" obter_template (contrato-arrendamento-habitacional, carta-atualizacao-renda) + ler_referencia (arrendamento)
"Tenho uma multa", "contraordenação" obter_template (defesa-contraordenacao) + ler_referencia (multas)
"O que diz a lei sobre…", "quais os meus direitos" listar_areas_juridicasler_referencia (área) ou procurar_conteudo (termo)
"Antes de lançar / pôr online" (loja, serviço) obter_checklist (checklist-predeploy-legal) + obter_template (termos-condicoes-loja-online)

Read the full file on GitHub · 68 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.

  1. 6d ago First seen · 68 lines · 2,151 tokens per session scan A 0d8fcdba594b

Subscribe to this mod's changes

advogado-pt AGENTS.md is an instructions file published in the GitHub repository linofcp007/advogado-pt (0 stars, last pushed 27d ago), licensed MIT. It adds 2,151 tokens to every session, about $0.0108 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens