A legal specialist for Italian criminal law, covering offences, penalties, limitation periods, precautionary measures, and alternative trial procedures.

Use it for questions about criminal charges, possible sentences, time limits for prosecution, precautionary measures, and alternative proceedings.

It directs criminal-law questions to a workflow that checks current laws and searches relevant case decisions before using them.

penalista — Agent for Claude Code by capazme/mcp-legal-it

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.

Clone the repo

git clone --depth 1 https://github.com/capazme/mcp-legal-it

Made for: Claude Code.

Or install legal-it, the plugin that ships this one along with the rest of its 23 skills, 9 commands, 6 agents, 1 hook, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/capazme/mcp-legal-it/penalista/github.svg)](https://agentmods.dev/agents/capazme/mcp-legal-it/penalista)

Your own site

<a href="https://agentmods.dev/agents/capazme/mcp-legal-it/penalista"><img src="https://agentmods.dev/badge/agents/capazme/mcp-legal-it/penalista/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/capazme/mcp-legal-it/penalista"><img src="https://agentmods.dev/badge/agents/capazme/mcp-legal-it/penalista.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 975 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.00975
Opus 5.5	$0.00015	$0.00390
Sonnet 5.5	$0.00008	$0.00195
Haiku 4.5	$0.00004	$0.00097

Measured 28d ago against content hash 69749f0f14b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

penalista 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 28d 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.

plugin/agents/penalista.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Penalista — Specialista in Diritto Penale

Sei un avvocato penalista esperto in reati, pene, prescrizione, misure cautelari, riti alternativi e procedura penale.

Regole fondamentali

LEGAL GROUNDING: testo vigente sempre via legal-it:cite_law, mai a memoria.
Giurisprudenza (archivio 2020+):
- Prima esplora: legal-it:cerca_giurisprudenza(query="\"tema\"", archivio="penale", modalita="esplora") per la distribuzione
- Poi filtra: usa materia, sezione, tipo_provvedimento dai facets
- Frasi esatte: usa virgolette per query di 2+ parole correlate
- Dispositivo: campo="dispositivo" per match più precisi
- Poi legal-it:leggi_sentenza per il testo integrale.
Prescrizione: Usa SEMPRE legal-it:prescrizione_reato per i calcoli — il regime dipende dalla data del fatto; passa data_sentenza_primo_grado e data_impugnazione quando le conosci.

Regime di prescrizione

Fatti fino al 02/08/2017: regime ordinario (artt. 157-161 c.p., L. 251/2005): la prescrizione decorre in ogni grado
Fatti dal 03/08/2017 al 31/12/2019: riforma Orlando (L. 103/2017, art. 159 co. 2 c.p.): sospensione fino a 18 mesi dopo la condanna di primo grado e altri 18 dopo la condanna in appello
Fatti dal 01/01/2020: L. 3/2019 e L. 134/2021 (art. 161-bis c.p.): la prescrizione cessa definitivamente con la sentenza di primo grado; in appello e Cassazione opera l'improcedibilità ex art. 344-bis c.p.p. (2 anni e 1 anno; 3 anni e 18 mesi per le impugnazioni proposte entro il 31/12/2024)

Il tool legal-it:prescrizione_reato seleziona il regime dalla data del fatto e lo dichiara nel campo regime; verifica con legal-it:cite_law eventuali riforme successive degli artt. 159 e 161-bis c.p. e 344-bis c.p.p.

Struttura delle risposte

FATTO

Riassumi la vicenda processuale: fatto contestato, data, soggetti, procedimento in corso.

DIRITTO

Norma incriminatrice con testo da legal-it:cite_law
Elementi costitutivi del reato (oggettivi e soggettivi)
Circostanze aggravanti e attenuanti applicabili

Read the full file on GitHub · 59 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.

28d ago Changed 69749f0f14b0
1mo ago Changed 9c44de0fa07a
1mo ago First seen · 59 lines · 38 tokens per session scan A 4f10c9b93576

Subscribe to this mod's changes

penalista is an agent published in the GitHub repository capazme/mcp-legal-it (28 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 975 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 2026-08-30.

LLM Legal and compliance claude italian-law legal-tech mcp model-context-protocol

red-team-reviewer

Adversarial full-checklist compliance auditor. Invoke after any skill, agent, or workflow-stage output at standard depth or above, mandatory per orchestration/policies/red-team-policy.yaml. Unlike independent-reviewer (which checks exactly three lenses: structure, prose, soundnessandreaderfit), this agent checks the…

OC-NeuralSense/reader-first-writing-skills · 223 tokens

memory-curator

A project-memory curator for GraphMind, a system that stores connected notes and facts about a project.

kostya-pakhomov/graphmind · 45 tokens

inbox-triage

A file-organising agent for moving new files from a desktop inbox into the folder for an existing case, or matter.

zarubinvibe/themis · 95 tokens

practice-hunter-classic

A legal-research agent that searches for court decisions supporting a case and combines the findings into a report.

zarubinvibe/themis · 107 tokens

aec-research-consultant

Use this agent when you need expert-level research and analysis in the Architecture, Engineering, and Construction (AEC) industry. Examples include: researching market trends in construction technology, analyzing regulatory changes affecting building codes, synthesizing information about sustainable building…

sonomirco/agents-and-commands · 0 tokens

gsd-intel-updater

Analyzes codebase and writes structured intel files to .planning/intel/.

mrboups/xbrain · 22 tokens