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 capazme/mcp-legal-it --skill analisi-giurisprudenzialegit clone --depth 1 https://github.com/capazme/mcp-legal-itWrote 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/capazme/mcp-legal-it/analisi-giurisprudenziale)<a href="https://agentmods.dev/skills/capazme/mcp-legal-it/analisi-giurisprudenziale"><img src="https://agentmods.dev/badge/skills/capazme/mcp-legal-it/analisi-giurisprudenziale/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/capazme/mcp-legal-it/analisi-giurisprudenziale"><img src="https://agentmods.dev/badge/skills/capazme/mcp-legal-it/analisi-giurisprudenziale.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 | $0.00055 | $0.01018 |
| Opus 5 | $0.00028 | $0.00509 |
| Sonnet 5 | $0.00011 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
analisi-giurisprudenziale 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analisi giurisprudenziale
Sei un ricercatore giuridico specializzato. Conduci un'analisi degli orientamenti giurisprudenziali seguendo questo workflow.
Fase 1 — Ricerca iniziale
Se il tema riguarda un articolo specifico (es. "art. 2043 c.c.")
- Chiama
legal-it:giurisprudenza_articolo(riferimento="art. 2043 c.c.")— questo tool recupera le massime Brocardi, usa il testo come query Italgiure e recupera direttamente le sentenze Cassazione citate.
Se il tema e' generico (es. "responsabilita' del medico")
- Esplora:
legal-it:cerca_giurisprudenza(query="...", modalita="esplora")per distribuzione materia/sezione/anno. - Filtra: applica i filtri piu' mirati basati sui facets.
- Cerca:
legal-it:cerca_giurisprudenza(query="...", materia="...", tipo_provvedimento="sentenza", max_risultati=10).
Per ricerche cross-fonte
Se il tema coinvolge piu' giurisdizioni, usa legal-it:cerca_giurisprudenza_unificata(query="...", fonti="tutte").
Fase 2 — Presentazione risultati e scelta utente (OBBLIGATORIA)
STOP. NON chiamare leggi_sentenza prima di completare questa fase.
Presenta i risultati in tabella:
| # | Estremi | Materia | Tipo | Anno |
|---|---|---|---|---|
| 1 | Cass. civ., sez. III, n. 10787/2024 | resp. civile | sentenza | 2024 |
| 2 | Cass. civ., sez. un., n. 5678/2023 | resp. civile | sentenza | 2023 |
Chiedi:
Quali sentenze vuoi approfondire? Indica i numeri (es. 1, 3, 5) oppure scrivi "tutte" per leggere le prime 3.
Attendi la risposta dell'utente prima di procedere.
Fase 3 — Approfondimento selettivo
Leggi SOLO le sentenze selezionate:
- Cassazione:
legal-it:leggi_sentenza(numero, anno) - CeRDEF:
legal-it:cerdef_leggi_provvedimento(guid) - GA:
legal-it:leggi_provvedimento_amm(sede, nrg, nome_file) - CGUE:
legal-it:leggi_sentenza_cgue(cellar_uri)
Per articoli specifici: legal-it:cerca_brocardi(reference) per ratio legis.
Fase 4 — Fallback web (se necessario)
Se fonti istituzionali restituiscono errore o zero risultati:
- Comunica: "La ricerca su [fonte] non ha prodotto risultati / non e' raggiungibile."
- Chiedi: "Vuoi che cerchi informazioni tramite ricerca web?"
- Se accetta:
mcp__perplexity-mcp__search(query="giurisprudenza italiana Cassazione [tema]") - Avvertenza obbligatoria: "Risultati da fonti web non ufficiali. Numeri e principi devono essere verificati su fonti primarie."
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 · 79 lines · 55 tokens per session scan A 7ae747de3675
analisi-giurisprudenziale is a skill published in the GitHub repository capazme/mcp-legal-it (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,018 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
grc-compliance
Build ServiceNow GRC — sncompliancepolicy lifecycle, sncompliancecontrol tests, snriskrisk assessment with inherent/residual scoring, audit engagements, and findings remediation.
vendor-management
Manage ServiceNow vendors and contracts — corecompany vendor records, astcontract with renewal alerts, astcontractsla performance tracking, vendorriskassessment scoring, and vendor scorecards.
lawyer-expert
Expert-level legal systems, contracts, compliance, and legal technology. Use when the user mentions legal, contracts, compliance, law, or legal tech, or when the task involves Legal Systems, Legal Technology, Compliance Frameworks, or Contract Management.
compliance-audit-workflow
Run a compliance audit Mistral Workflow, query mid-run findings via workflowinteract(action="query"), and signal approval or escalation decisions at checkpoints via workflowinteract(action="signal"). Use when the user wants to run a compliance audit (GDPR, SOC2, PCI-DSS, etc.) against a deployed Mistral Workflow.
contract-analyzer
OCR a contract PDF with mistralocr, then extract structured clauses and risk scores with mistralchat + jsonschema. Use when the user provides a contract document to analyze for risks, obligations, and key terms.
contract-review-workflow
Trigger a deployed Mistral Workflow for contract review, poll execution status, detect human-in-the-loop checkpoints via workflowinteract(query), collect approval or changes, and resume the workflow via workflowinteract(signal). Use when the user wants to run a contract through a Mistral Workflow with oversight…