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 procure-quotazionigit 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/procure-quotazioni)<a href="https://agentmods.dev/skills/capazme/mcp-legal-it/procure-quotazioni"><img src="https://agentmods.dev/badge/skills/capazme/mcp-legal-it/procure-quotazioni/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/procure-quotazioni"><img src="https://agentmods.dev/badge/skills/capazme/mcp-legal-it/procure-quotazioni.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 | $0.00181 | $0.01343 |
| Opus 5.5 | $0.00072 | $0.00537 |
| Sonnet 5.5 | $0.00036 | $0.00269 |
| Haiku 4.5 | $0.00018 | $0.00134 |
Grade A, and why
procure-quotazioni 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Procure e Quotazioni — recupero crediti seriale
Produce, per ogni posizione, due DOCX pronti-firma: la procura alle liti e la lettera di quotazione con blocco di accettazione del cliente. Il calcolo e l'impaginazione sono deterministici (tool server); questa skill governa la parte critica: leggere le posizioni, capire la fase, non inventare dati.
Workflow
1. Config studio (dati fissi)
Cerca un file studio.json con i dati ricorrenti (mandante, firmatario, difensori, domicilio, PEC): prima nella cartella di lavoro, poi in ~/.claude/legal-it/studio.json. Formato in references/studio.esempio.json. Se manca, chiedi i dati una volta sola e proponi di salvarli in ~/.claude/legal-it/studio.json per le prossime esecuzioni. I dati reali dello studio restano locali: mai inserirli nel repository del plugin.
Se il firmatario del mandante è cambiato (es. firma il presidente del CdA invece del consigliere), verifica su visura camerale che abbia la rappresentanza legale anche in giudizio prima di intestargli le procure, e riporta in firmatario_qualifica la carica reale.
2. Leggere le posizioni
Da Excel (leggilo con il Python di sistema; se manca openpyxl chiedi un export CSV) o dai dati nel prompt. Per ogni posizione servono: debitore, valore del credito, azione, stato (esecutorietà/note).
Normalizza gli importi prima di usarli: separatori svizzeri (3'513.60), apostrofi tipografici (3’513.60), stringhe con spazi. Una cella che si legge come data/durata (datetime, timedelta) è un importo corrotto: non usarla — recupera l'importo dal ricorso o dalle fatture in fascicolo, o chiedi all'utente. Segnala sempre nel report i valori recuperati da fonte diversa dall'Excel.
3. Determinare la fase di ogni posizione
La quotazione dipende dalla fase processuale, non solo dal valore: quotare il monitorio a una posizione già esecutiva o opposta produce un preventivo sbagliato. Leggi references/rilevamento-fase.md e classifica ogni posizione: monitorio, esecuzione o opposizione. In caso di dubbio chiedi, non tirare a indovinare.
What ships with it
2 files 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.
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.
- 1mo ago First seen · 56 lines · 181 tokens per session scan A 027b1e7e5471
procure-quotazioni is a skill published in the GitHub repository capazme/mcp-legal-it (28 stars, last pushed today), licensed Apache-2.0. It adds 181 tokens to every session and 1,343 once invoked, about $0.0007 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.
Other skills, from other repositories
redact-pii
Redact personal data from a document through the connected Superlinked MCP edge before working with the content. Use when the user asks to redact, anonymize, scrub, de-identify, or remove PII/sensitive data from a document.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
korean-law
A legal research connection to South Korea's official law information service. It can retrieve statutes, court decisions, administrative rules, local ordinances, treaties, and legal interpretations, then check cited provisions against the source.
legal-analysis
Analyze legal contracts, extract clauses, and perform legal research with structured frameworks.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…
lumen-clause-extraction
How to answer review-table columns - formats, normalization, "not found" rules and the commercial preset columns.