penalista-verifica

penalista-verifica is a skill for Claude Code from Synthos-Logic/penalista-italia. It costs 150 tokens per session (1,481 once invoked), scanned A, original, MIT.

A final quality check for an Italian criminal-law document before it is filed with the court or another authority. It independently reviews citations, deadlines, consistency, and support from the case file.

In plain words
What is it for?
Checking a legal brief or memorandum before filing, verifying cited decisions and deadlines, comparing claims with the case materials, and reporting issues that need correction.
Why use it?
It helps catch incorrect case references, missed time limits, contradictions, and unsupported statements before submission. The review is separate from the drafting process when a separate reviewer is available.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

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

Good fit Checking a legal brief or memorandum before filing, verifying cited decisions and deadlines, comparing claims with the case materials, and reporting issues that need correction.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthos-logic/penalista-italia/penalista-verifica"><img src="https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-verifica.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,481 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 $0.00150 $0.01481
Opus 5 $0.00075 $0.00740
Sonnet 5 $0.00030 $0.00296
Haiku 4.5 $0.00015 $0.00148

Measured 12d ago against content hash 1b3046668e6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

penalista-verifica 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 12d 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-verifica/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill — Verifica pre-deposito

Questa skill è il controllo qualità dello studio: un riesame indipendente e sistematico dell'atto prima che esca. Il suo principio: l'atto si difende da solo solo se ogni affermazione regge alla verifica.

Quando attivarla

  • Su richiesta esplicita dell'avvocato.
  • D'ufficio: al termine della redazione di ogni atto destinato al deposito, proporre: "Vuole che esegua la verifica pre-deposito? Controllo citazioni, termini e coerenza con il fascicolo."

Metodo: verifica indipendente

Se l'ambiente consente di lanciare un agente di verifica separato (subagente), usarlo: il verificatore non deve essere influenzato dal contesto di chi ha scritto l'atto. Istruirlo a leggere SOLO l'atto, il fascicolo e la Knowledge Base — non la conversazione di redazione. Se il subagente non è disponibile, eseguire la checklist direttamente, dichiarandolo.

CHECKLIST DI VERIFICA (eseguire tutta, nell'ordine)

1. Citazioni giurisprudenziali — la verifica più importante

Per OGNI sentenza citata nell'atto:

Esito Criterio Azione
✅ VERIFICATA Presente nell'indice della KB — registro citazionale di KNOWLEDGE_BASE/_INDICE/INDICE.md (o FASCICOLI/<caso>/_INDICE/) — con riscontro testuale della massima alla pagina indicata (PROTOCOLLO_GROUNDING) Nessuna
⚠️ NON IN KB Non presente nell'indice della KB (non riscontrabile nei registri) La citazione va resa testuale dall'indice oppure dichiarata "non presente in KB"; suggerire verifica su Italgiure / DeJure / Portale del Massimario
❌ SOSPETTA Estremi incoerenti (sezione/anno/numero non plausibili), massima che non corrisponde alla fonte Segnalare in rosso: NON depositare senza verifica umana

Mai declassare una citazione a "verificata" per somiglianza. La verifica richiede riscontro testuale della massima, non solo degli estremi.

2. Termini e date

  • Ricalcolare da zero ogni termine menzionato nell'atto (non fidarsi del calcolo fatto in redazione): regole art. 172 c.p.p., sospensione feriale, giorni festivi.
  • Confrontare con lo SCADENZIARIO del fascicolo: coincidono? Se no, segnalare la divergenza — è un errore in uno dei due posti.
  • Verificare la coerenza interna delle date (notifica, decorrenza, deposito).

Read the full file on GitHub · 84 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. 12d ago First seen · 84 lines · 150 tokens per session scan A 1b3046668e6f

Subscribe to this mod's changes

penalista-verifica is a skill published in the GitHub repository Synthos-Logic/penalista-italia (1 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 1,481 once invoked, about $0.0007 per session on Opus 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.

Related

Other skills, from other repositories

legal-law-research

A legal research tool for finding and checking South Korean laws, court decisions, administrative rules, local ordinances, treaties, and official interpretations. It can also verify whether cited provisions or decisions exist and are still applicable.

modu-ai/moai-cowork · 366 tokens

commerce-ad-claim-compliance-kr

A pre-publication check for Korean advertising and product-page wording. It reviews claims against South Korea's advertising, food-safety, and e-commerce laws.

modu-ai/moai-cowork · 381 tokens

data-court-auction

A read-only lookup for property sale notices and case information from South Korea's official court-auction website. It shows details such as the case number, property use, address, assessed value, minimum sale price, and auction date.

modu-ai/moai-cowork · 272 tokens

legal-contract-review

A tool for reviewing and drafting legal documents such as contracts, terms of service, privacy policies, and service-level agreements (SLAs). An SLA is a contract that defines expected service performance and remedies.

modu-ai/moai-cowork · 101 tokens

legal-legal-risk

A tool for identifying and assessing legal risks in a company’s operations, including contracts, privacy, employment, regulation, and intellectual property (IP). IP means rights such as patents, trademarks, copyrights, and trade secrets.

modu-ai/moai-cowork · 113 tokens

legal-patent-analyzer

A patent analysis tool that turns patent data into technology trends, prior-art reports, freedom-to-operate (FTO) reviews, and draft patent applications. FTO means checking whether a product may infringe existing patent claims.

modu-ai/moai-cowork · 232 tokens