agentmods.dev

penalista-cautelare

penalista-cautelare is a skill for Claude Code from Synthos-Logic/penalista-italia. It costs 196 tokens per session (3,656 once invoked), scanned A, original, MIT.

An Italian-language legal workflow for personal precautionary measures in criminal proceedings, such as pre-trial detention or restrictions on liberty.

In plain words
What is it for?
Use it to analyse the grounds for a measure, calculate custody deadlines, and prepare or review requests for reconsideration, cancellation, replacement, or release.
Why use it?
These cases involve strict legal conditions and deadlines, so missed requirements can affect a person's freedom.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the penalista-italia plugin — 9 skills, 2 commands shipped together

not rated 1repo 14d ago A scan 196 tokens original MIT

Good fit Use it to analyse the grounds for a measure, calculate custody deadlines, and prepare or review requests for reconsideration, cancellation, replacement, or release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthos-logic/penalista-italia/penalista-cautelare
View source ↗ Synthos-Logic/penalista-italia synthos-logic.github.io
Install

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.

Any agent
npx skills add Synthos-Logic/penalista-italia --skill penalista-cautelare
Clone the repo
git clone --depth 1 https://github.com/Synthos-Logic/penalista-italia

Made for: Claude Code.

Or install penalista-italia, the plugin that ships this one along with the rest of its 9 skills, 2 commands.

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 penalista-cautelare

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-cautelare/github.svg)](https://agentmods.dev/skills/synthos-logic/penalista-italia/penalista-cautelare)
Your own site
<a href="https://agentmods.dev/skills/synthos-logic/penalista-italia/penalista-cautelare"><img src="https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-cautelare/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 penalista-cautelare

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthos-logic/penalista-italia/penalista-cautelare"><img src="https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-cautelare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,656 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00196 $0.03656
Opus 5.5 $0.00078 $0.01462
Sonnet 5.5 $0.00039 $0.00731
Haiku 4.5 $0.00020 $0.00366

Measured 2mo ago against content hash e2ddf0e88631, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

penalista-cautelare 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 2mo 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.

skills/penalista-cautelare/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill — Misure Cautelari Personali

Questa skill gestisce l'intero ciclo difensivo delle misure cautelari personali: dall'analisi dei presupposti al riesame, dalla revoca alla verifica dei termini di fase. I termini cautelari sono tra i più critici del processo penale — un errore può tenere un innocente in carcere oltre i termini legali.

⚠️ Quadro normativo vigente (verificato giugno 2026)

Due novità della Riforma Nordio (L. 114/2024) incidono direttamente su questa skill:

1. Interrogatorio preventivo (art. 291 co. 1-bis c.p.p.) — IN VIGORE. Salvo i casi eccettuati (esigenze cautelari incompatibili con il preavviso, reati di maggiore gravità, pericolo attuale di fuga o inquinamento), il giudice deve interrogare la persona prima di applicare la misura, con registrazione audio/video integrale. Per la difesa è un'occasione nuova: preparare il cliente, valutare il silenzio, depositare documentazione sulle esigenze cautelari prima che la misura sia disposta. L'omissione dell'interrogatorio fuori dai casi consentiti è motivo di impugnazione — verificarla sempre nell'analisi dell'ordinanza (Modulo 2).

2. GIP collegiale per la custodia in carcere (art. 328 co. 1-quinquies c.p.p.) — NON ANCORA IN VIGORE. L'entrata in vigore, originariamente fissata al 25 agosto 2026, è stata differita a fine febbraio 2027 (decreto-legge approvato dal CdM il 4 giugno 2026) [VERIFICARE estremi G.U.]. Fino ad allora decide il GIP monocratico. Dettagli in [[AGGIORNAMENTO_NORMATIVO_2025-2026]].

Prima di procedere

Identifica la situazione cautelare. Chiedi in un'unica domanda le informazioni mancanti:

  • Tipo di misura vigente (custodia cautelare in carcere / arresti domiciliari / altra)
  • Data di esecuzione della misura
  • Reato contestato (per determinare il regime dei termini di fase)
  • Fase processuale (indagini / UP / primo grado / appello / Cassazione)
  • Cosa serve fare (riesame / revoca / verifica termini / analisi presupposti / udienza convalida)

Read the full file on GitHub · 251 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. 2mo ago First seen · 251 lines · 196 tokens per session scan A e2ddf0e88631

Subscribe to this mod's changes

penalista-cautelare is a skill published in the GitHub repository Synthos-Logic/penalista-italia (1 stars, last pushed 14d ago), licensed MIT. It adds 196 tokens to every session and 3,656 once invoked, about $0.0008 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.

Claude CodeLegal and complianceai-agentsanthropiccassazioneclaude-code-skillsclaude-plugins
Related

penalista-cautelare compared with skills from other repositories

penalista-cautelare next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
penalista-cautelareSynthos-Logic/penalista-italiaSkill114d agoMITA196Claude Code
commerce-ad-claim-compliance-krmodu-ai/moai-coworkSkill31528d agoApache-2.0A381Claude Code
data-court-auctionmodu-ai/moai-coworkSkill31528d agoApache-2.0A272Claude Code
hr-draft-offermodu-ai/moai-coworkSkill31528d agoApache-2.0A108Claude Code
hr-resume-screenermodu-ai/moai-coworkSkill31528d agoApache-2.0A309Claude Code
commerce-influencer-collabmodu-ai/moai-coworkSkill31528d agoApache-2.0A217Claude Code
legal-ip-search-reportmodu-ai/moai-coworkSkill31528d agoApache-2.0A269Claude Code