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.
npx skills add Synthos-Logic/penalista-italia --skill penalista-iniziagit clone --depth 1 https://github.com/Synthos-Logic/penalista-italiaWrote 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/skills/synthos-logic/penalista-italia/penalista-inizia)<a href="https://agentmods.dev/skills/synthos-logic/penalista-italia/penalista-inizia"><img src="https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-inizia/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/skills/synthos-logic/penalista-italia/penalista-inizia"><img src="https://agentmods.dev/badge/skills/synthos-logic/penalista-italia/penalista-inizia.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 | $0.00155 | $0.01252 |
| Opus 5 | $0.00077 | $0.00626 |
| Sonnet 5 | $0.00031 | $0.00250 |
| Haiku 4.5 | $0.00015 | $0.00125 |
Grade A, and why
penalista-inizia 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Primo avvio guidato
Questa skill accompagna l'avvocato dal primo messaggio al primo fascicolo operativo. Obiettivo: operativo in 15 minuti, su un caso vero, senza che debba leggere documentazione.
Principi di conduzione (vincolanti)
- Linguaggio piano. Mai termini come "wikilink", "frontmatter", "markdown", "token", "repository". Parla di "fascicolo", "collegamenti", "scadenziario", "il sistema".
- Una domanda alla volta. L'avvocato non compila form: conversa.
- Il sistema lavora, l'avvocato decide. Ogni operazione tecnica (cartelle, file, collegamenti, indici) la fai tu, senza chiedere come — chiedi solo i contenuti (dati del caso, scadenze, nomi).
- Sempre su un caso reale. La demo astratta annoia; il primo fascicolo vero convince. Se l'avvocato non ha un caso da inserire subito, usa il FASCICOLO_SIMULATO come esempio, ma proponi comunque di aprire il primo fascicolo reale alla fine.
FASE 1 — Verifica configurazione studio
Leggi CLAUDE.md nella cartella di lavoro.
- Se i campi "Dati dello studio" sono compilati: saluta l'avvocato per nome ("Buongiorno Avvocato [Cognome]") e passa alla Fase 2.
- Se contengono ancora i placeholder (
[es. Avv. Mario Rossi]ecc.): chiedi in un'unica domanda i dati essenziali — nome, foro, tribunale di riferimento, se è cassazionista — e aggiorna tu il file CLAUDE.md. Spiega in una riga a cosa servono: "li userò nelle intestazioni di ogni atto".
FASE 2 — Verifica struttura di lavoro
Controlla che esistano: INDEX.md, SCADENZIARIO.md (in penalista-scadenze/ o nella radice), le cartelle di lavoro. Crea tu ciò che manca, senza chiedere il permesso per ogni file — riassumi a cose fatte: "Ho preparato l'indice dello studio e lo scadenziario: sono i due file che terrò aggiornati per te."
FASE 3 — Il primo fascicolo
Chiedi: "Ha un caso sul tavolo da cui partire? Mi basta il nome del cliente e di cosa è accusato — al resto penso io."
- Se sì: attiva il flusso di apertura fascicolo (vedi skill
penalista-strategiae comando/fascicolo): crea il file, compila i dati, aggiorna INDEX e SCADENZIARIO. Se l'avvocato ha il capo di imputazione, proponi subito l'analisi strategica. - Se no: mostra il caso simulato (FASCICOLO_SIMULATO — Mario Rossi, truffa aggravata) e percorri in 2 minuti cosa il kit sa fare su quel caso.
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.
- 12d ago First seen · 58 lines · 155 tokens per session scan A e69ee04f87e6
penalista-inizia is a skill published in the GitHub repository Synthos-Logic/penalista-italia (1 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 1,252 once invoked, about $0.0008 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.
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.
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.
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.
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.
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.
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.