Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/linofcp007/advogado-ptWrote 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/commands/linofcp007/advogado-pt/irc)<a href="https://agentmods.dev/commands/linofcp007/advogado-pt/irc"><img src="https://agentmods.dev/badge/commands/linofcp007/advogado-pt/irc/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/commands/linofcp007/advogado-pt/irc"><img src="https://agentmods.dev/badge/commands/linofcp007/advogado-pt/irc.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 | $0.00045 | $0.00504 |
| Opus 5.5 | $0.00018 | $0.00202 |
| Sonnet 5.5 | $0.00009 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
irc 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.
What it actually says
Ativa a skill advogado-pt para o IRC: $ARGUMENTS.
- Confirma no perfil (
obter_perfil_empresa) que é uma sociedade e se é PME (certificação IAPMEI). Pede o que faltar: lucro tributável (ou prejuízo), prejuízos de anos anteriores, taxa da derrama do município, viaturas (custo de aquisição, tipo e encargos anuais), despesas de representação, ajudas de custo. - Calcula com a tool MCP
calc_irce explica cada parcela (IRC, derrama municipal, derrama estadual, tributação autónoma) com a base legal (CIRC arts. 52.º, 87.º, 87.º-A e 88.º; Lei 64/2025 para as taxas de 2026-2028). - Quando houver viaturas, compara o impacto de combustão, plug-in e elétrico (limiares de 37.500 €, 45.000 € e 62.500 €). Lembra o agravamento de 10 p.p. com prejuízo e as exceções.
- Para os prazos (Modelo 22, pagamentos por conta, IES), usa
calendario_obrigacoes. Para faturação ao estrangeiro, usacalc_iva_operacaoe a referênciaiva-internacional. Fundamenta comler_referenciafiscale os valores devalores-2026.
EN: Activate the advogado-pt skill for corporate income tax: $ARGUMENTS. Check the profile, compute with the calc_irc MCP tool and explain each component (CIT, municipal and state surcharges, autonomous taxation). Use calendario_obrigacoes for the filing and payment deadlines.
Exemplos · Examples: "/irc lucro 120.000 € PME Lisboa", "/irc quanto pago de tributação autónoma num carro de 40.000 €", "/irc tivemos prejuízo de 30.000 €".
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.
- 17d ago First seen · 16 lines · 45 tokens per session scan A e97a69f6390c
irc is a command published in the GitHub repository linofcp007/advogado-pt (0 stars, last pushed 18d ago), licensed MIT. It adds 45 tokens to every session and 504 once invoked, about $0.0002 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 2026-10-05.
Other commands, from other repositories
aposentadoria
Slash command /aposentadoria — calcula imediatamente quando o usuário pode se aposentar e qual regra é mais vantajosa. Ativa quando o usuário digita /aposentadoria, "quando posso me aposentar", "planejamento INSS", "quantos anos faltam para aposentadoria", "planejamento previdenciário".
clt-pj
Slash command /clt-pj — compara imediatamente uma oferta CLT com uma oferta PJ. Ativa quando o usuário digita /clt-pj, "CLT ou PJ", "vale mais a pena CLT ou PJ", "comparar proposta CLT PJ", "quanto preciso ganhar como PJ".
rescisao
Slash command /rescisao — calcula imediatamente as verbas rescisórias CLT. Ativa quando o usuário digita /rescisao, "calcular rescisão", "quanto recebo se for demitido", "verbas rescisórias".
simples
Slash command /simples — calcula imediatamente o DAS do Simples Nacional e compara regimes tributários. Ativa quando o usuário digita /simples, "calcular DAS", "quanto pago de Simples Nacional", "regime tributário empresa".
irpf
Slash command /irpf — inicia imediatamente o fluxo guiado de declaração do Imposto de Renda Pessoa Física 2026. Ativa quando o usuário digita /irpf, com ou sem argumentos adicionais.
gsd:debug
Systematic debugging with persistent state across context resets.