agentmods.dev

penalista-giurisprudenza

penalista-giurisprudenza is a skill for Claude Code from Synthos-Logic/penalista-italia. It costs 214 tokens per session (3,661 once invoked), scanned A, original, MIT.

An Italian-language research workflow for criminal-law case decisions, including rulings and legal positions from Italy's Supreme Court and other courts.

In plain words
What is it for?
Use it to find decisions relevant to a criminal defense, check how courts interpret an issue, and organize authorities for a legal document.
Why use it?
It helps a lawyer search with a precise legal question and distinguish established positions, specific holdings, and disagreements between courts.

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 changed 13d ago A scan 214 tokens original MIT

Good fit Use it to find decisions relevant to a criminal defense, check how courts interpret an issue, and organize authorities for a legal document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthos-logic/penalista-italia/penalista-giurisprudenza
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-giurisprudenza
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-giurisprudenza

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthos-logic/penalista-italia/penalista-giurisprudenza"><img src="https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-giurisprudenza.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 214 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,661 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 $0.00214 $0.03661
Opus 5.5 $0.00086 $0.01464
Sonnet 5.5 $0.00043 $0.00732
Haiku 4.5 $0.00021 $0.00366

Measured 13d ago against content hash 0618a9517ee1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

penalista-giurisprudenza 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 13d 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-giurisprudenza/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill — Ricerca Giurisprudenziale Penale

Questa skill supporta la ricerca e l'organizzazione della giurisprudenza penale per costruire argomenti difensivi solidi. La giurisprudenza non è un ornamento — è l'ossatura di ogni atto che conta.

Prima di iniziare

Se la richiesta non è già precisa, chiedi in un'unica domanda:

  • L'argomento giuridico specifico (non "corruzione" ma "elemento soggettivo della corruzione per la funzione" o "distinzione corruzione/istigazione alla corruzione")
  • L'obiettivo (trovare orientamenti favorevoli alla difesa / verificare un principio / identificare un contrasto tra sezioni / costruire una citazione per un atto)
  • Il livello di certezza richiesto (orientamento consolidato / massima specifica / contrasto da segnalare)

MODULO 0 — FRESCHEZZA DELLE FONTI (sempre, prima di ogni ricerca)

La KB contiene due binari di giurisprudenza:

  1. Massimari annuali (stock consolidato, citazioni con numero Rv) — sezioni 1 e 2 dell'INDICE.
  2. Pronunce segnalate dall'Ufficio del Massimario (flusso settimanale, repo giurisprudenza-db) — sezione 3 dell'INDICE ("Registro segnalate").

Check di freschezza obbligatorio: leggi la data di generazione in testa a KNOWLEDGE_BASE/_INDICE/INDICE.md. Se più vecchia di 7 giorni — o se la cartella 02_GIURISPRUDENZA/SEGNALATE/ manca — proponi all'avvocato l'aggiornamento: python3 skills/penalista-archivio/scripts/sincronizza_segnalate.py KNOWLEDGE_BASE (repo pubblico, nessun account richiesto; la pipeline centrale aggiorna ogni lunedì).

Come si cita una segnalata (quote-then-claim, sempre): apri la scheda indicata dal registro → incolla la massima testuale → cita così: Cass. pen., Sez. III, n. 23006 del 2026 (dep. 22/06/2026) — massima ufficiale segnalata dall'Ufficio del Massimario (scheda in KB; PDF ufficiale: <url_pdf dalla scheda>). Il link al PDF autentico VA SEMPRE riportato: è la fonte verificabile con un clic.

Questioni SU pendenti: non sono precedenti. Si usano SOLO come segnalazione del contrasto rimesso alle Sezioni Unite (con data d'udienza) — preziose per istanze di rinvio, motivi in subordine, strategia. Mai citarle come autorità.

Read the full file on GitHub · 207 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago Changed · +9 lines · -72 tokens per session 0618a9517ee1
  2. 2mo ago First seen · 198 lines · 286 tokens per session scan A 28d26c523cb5

Subscribe to this mod's changes

penalista-giurisprudenza is a skill published in the GitHub repository Synthos-Logic/penalista-italia (1 stars, last pushed 14d ago), licensed MIT. It adds 214 tokens to every session and 3,661 once invoked, about $0.0009 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 complianceResearchai-agentsanthropiccassazioneclaude-code-skillsclaude-plugins
Related

penalista-giurisprudenza compared with skills from other repositories

penalista-giurisprudenza next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
penalista-giurisprudenzaSynthos-Logic/penalista-italiaSkill114d agoMITA214Claude 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