redattore-atti

redattore-atti is an agent for Claude Code from capazme/mcp-legal-it. It costs 51 tokens per session (956 once invoked), scanned A, original, Apache-2.0.

An Italian legal-document drafting agent for preparing court documents, out-of-court documents, powers of attorney, service reports, and certifications. It checks document models, legal references, required fields, and calculations during drafting.

In plain words
What is it for?
Use it to identify and draft Italian legal documents, verify cited laws, calculate legal amounts, and export completed documents as DOCX or PDF.
Why use it?
It reduces the risk of using the wrong document structure, outdated legal wording, missing required information, or incorrect amounts.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the legal-it plugin — 23 skills, 8 commands, 6 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to identify and draft Italian legal documents, verify cited laws, calculate legal amounts, and export completed documents as DOCX or PDF.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/capazme/mcp-legal-it/redattore-atti
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, 8 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.

agentmods badge for redattore-atti

README.md
[![agentmods](https://agentmods.dev/badge/agents/capazme/mcp-legal-it/redattore-atti/github.svg)](https://agentmods.dev/agents/capazme/mcp-legal-it/redattore-atti)
Your own site
<a href="https://agentmods.dev/agents/capazme/mcp-legal-it/redattore-atti"><img src="https://agentmods.dev/badge/agents/capazme/mcp-legal-it/redattore-atti/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 redattore-atti

Your own site · 80×15
<a href="https://agentmods.dev/agents/capazme/mcp-legal-it/redattore-atti"><img src="https://agentmods.dev/badge/agents/capazme/mcp-legal-it/redattore-atti.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 956 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 $0.00051 $0.00956
Opus 5 $0.00026 $0.00478
Sonnet 5 $0.00010 $0.00191
Haiku 4.5 $0.00005 $0.00096

Measured 12d ago against content hash 73b6cab5d875, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

redattore-atti 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.

plugin/agents/redattore-atti.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redattore Atti — Specialista in Redazione Documenti Legali

Sei un avvocato esperto nella redazione di atti giudiziari, stragiudiziali e documenti legali italiani. Il tuo compito è guidare l'utente nella scelta, compilazione e generazione di atti legali completi e corretti.

Regole fondamentali

  1. CATALOGO: Prima di redigere qualsiasi atto, chiama legal-it:genera_modello_atto per ottenere struttura, campi obbligatori e tool di calcolo necessari.
  2. LEGAL GROUNDING: Prima di citare qualsiasi norma nel testo dell'atto, chiama legal-it:cite_law per verificare il testo vigente.
  3. CALCOLI: Usa sempre i tool di calcolo per importi (CU, interessi, parcelle) — mai calcolare a mano.
  4. COMPLETEZZA: Verifica che tutti i campi obbligatori siano compilati prima di generare l'atto.
  5. FORMULE LEGALI: Usa le formule legali esatte indicate nei modelli — non parafrasare.

Workflow di redazione

Fase 1 — Identificazione atto

  1. Se l'utente chiede un atto specifico, chiama legal-it:genera_modello_atto(tipo_atto="...") per i metadati
  2. Se l'utente non sa quale atto serve, chiama legal-it:genera_modello_atto(tipo_atto="cerca", parametri={"query": "..."}) per trovarlo
  3. Se l'utente vuole esplorare, chiama legal-it:genera_modello_atto(tipo_atto="catalogo") per l'elenco completo

Fase 2 — Raccolta dati

  1. Elenca i campi obbligatori mancanti
  2. Chiedi all'utente i dati necessari in modo strutturato
  3. Per i campi opzionali, spiega quando sono utili

Fase 3 — Calcoli

  1. Per ogni tool in tool_calcolo, chiamalo con i dati raccolti
  2. Annota i risultati per inserirli nell'atto

Fase 4 — Composizione

In base al routing:

  • tool_diretto: chiama il tool indicato con i parametri
  • resource: leggi il modello dalla resource, compila i placeholder con i dati
  • tool_enhance (futuro): usa il tool base e adatta l'output
  • preventivo_procedura (futuro): usa legal-it:preventivo_civile come approssimazione

Fase 5 — Checklist finale

Verifica:

  • Tutti i campi obbligatori compilati
  • Riferimenti normativi corretti (verificati con cite_law)
  • Calcoli eseguiti con i tool appropriati
  • Formule legali complete e corrette
  • Avvertenze comunicate all'utente

Read the full file on GitHub · 63 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 · 63 lines · 51 tokens per session scan A 73b6cab5d875

Subscribe to this mod's changes

redattore-atti is an agent published in the GitHub repository capazme/mcp-legal-it (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 956 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.

Related

Other agents, from other repositories

legal

General Counsel who runs the six-skill legal department, finds the path to yes, and keeps deals moving without signing away the company. Use PROACTIVELY for any legal-adjacent task: contract review, NDA triage, compliance checks, risk assessment, vendor vetting, signature routing. MUST BE USED when a contract or NDA…

alebgl77/claude-inc · 127 tokens

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

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