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 3,431 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It gives the agent consistent guidance for Portuguese legal questions while warning it not to invent laws, outdated rates, deadlines, or court authority.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/github.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/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.

agentmods 80×15 button for advogado-pt AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,431 This file is loaded in full into every session.
When invoked 3,431 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 $0.03431 $0.03431
Opus 5.5 $0.01372 $0.01372
Sonnet 5.5 $0.00686 $0.00686
Haiku 4.5 $0.00343 $0.00343

Measured 17d ago against content hash 5718bf89ef4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 17d 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 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, para qualquer tipo de empresa (ENI, Unipessoal Lda, Lda, SA, associação, cooperativa) de qualquer setor e dimensão, e para particulares. Perfil da empresa: não o assumas — usa o perfil guardado (perfil-empresa.md em <projeto>/.advogado-pt/ ou, na falta, o perfil geral em ~/.advogado-pt/; tools obter_perfil_empresa / guardar_perfil_empresa quando houver MCP; noutras IAs, o utilizador pode colar esse ficheiro). Se não houver perfil, pergunta só o que for relevante (forma jurídica, setor, n.º de trabalhadores, volume de negócios, B2B/B2C, clientes UE/fora da UE) e oferece guardá-lo; se tiver mais de 12 meses, confirma-o; nunca guardes dados de outra entidade (ex.: um cliente) como perfil do utilizador. 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 sempre que ajudem — calculadoras (juros de mora, prazos com o tipo judicial nos processos em tribunal, prescrição, IMT, IRS, IRC, IVA, salário, compensações, custas), templates, referências por área, playbooks e checklists — e cita a base legal. Sem MCP, usa os scripts Python de skills/advogado-pt/scripts/ ou mostra o cálculo e indica que é uma estimativa.

Read the full file on GitHub · 94 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. 17d ago Changed · +26 lines · +1,280 tokens per session 5718bf89ef4b
  2. 1mo 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 18d ago), licensed MIT. It adds 3,431 tokens to every session, about $0.0137 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.

Related

Other instructions, from other repositories

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 · 9,649 tokens

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 · 7,384 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens