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/prazos)<a href="https://agentmods.dev/commands/linofcp007/advogado-pt/prazos"><img src="https://agentmods.dev/badge/commands/linofcp007/advogado-pt/prazos/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/prazos"><img src="https://agentmods.dev/badge/commands/linofcp007/advogado-pt/prazos.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 | $0.00040 | $0.00479 |
| Opus 5.5 | $0.00016 | $0.00192 |
| Sonnet 5.5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
prazos 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 23d 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 os prazos em curso: $ARGUMENTS.
- Listar (sem argumentos): usa a tool MCP
listar_prazose destaca com ⏰ os vencidos e os que terminam nos próximos 7 dias. Para cada vencido, avalia logo o que ainda se pode fazer (justo impedimento, multa do art. 139.º CPC, outro meio de defesa). - Registar: se o utilizador ainda não tem a data-limite, calcula-a primeiro com
calc_prazo(dias úteis/corridos, férias judiciais, dilação) e confirma-a com ele; depois grava comregistar_prazo(dataAAAA-MM-DD,descricao,origemcom a norma e o ato que fez correr o prazo). Ficam em.advogado-pt/prazos.md, e o hook avisa no início de cada sessão. - Cumprido: marca com
concluir_prazo(data e descrição como aparecem emlistar_prazos).
Nunca dês um prazo judicial como garantido: indica a regra de contagem usada e recomenda advogado quando o prazo for perentório e estiver próximo.
EN: Activate the advogado-pt skill for running deadlines: $ARGUMENTS. List them with listar_prazos, compute new ones with calc_prazo and save them with registar_prazo; mark them done with concluir_prazo. The session-start hook warns about overdue deadlines and those due within 7 days.
Exemplos · Examples: "/prazos", "/prazos registar 2026-10-20 oposição à execução fiscal (art. 203.º CPPT)", "/prazos cumprido 2026-10-06 audição prévia".
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.
- 23d ago First seen · 17 lines · 40 tokens per session scan A 52b9089ef78d
prazos is a command published in the GitHub repository linofcp007/advogado-pt (0 stars, last pushed 24d ago), licensed MIT. It adds 40 tokens to every session and 479 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
data-act-ryan-malek
EU Data Act skill — classify, draft, lookup, analyze, or audit under Regulation (EU) 2023/2854. Produces lawyer-style Word output.
overtime
Analyze whether to accept an overtime/weekend/extra-scope request. Calculates true economic, health, career, legal, and collective costs against the requester's framing.
gsd:profile-user
Generate developer behavioral profile and create Claude-discoverable artifacts.
gsd:note
Zero-friction idea capture. Append, list, or promote notes to todos.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.