difendi

difendi is a command for Claude Code from mario-montanari/italiano-scrittura-anti-ai. It costs 52 tokens per session (2,567 once invoked), scanned A, original, MIT.

A command that builds an argument for an Italian text flagged by an automated AI detector. It takes the disputed text from a file and uses the writing procedure's supporting materials when available.

In plain words
What is it for?
Use it to create a defence for a specific Italian document by running the command with its file path.
Why use it?
It helps explain why a detector result may be a false positive and presents the author's evidence in an organised form.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the italiano-scrittura-anti-ai plugin — 1 skill, 2 commands shipped together

Good fit Use it to create a defence for a specific Italian document by running the command with its file path.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mario-montanari/italiano-scrittura-anti-ai
Claude Code
/plugin install italiano-scrittura-anti-ai

Made for: Claude Code.

Or install italiano-scrittura-anti-ai, the plugin that ships this one along with the rest of its 1 skill, 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 difendi

README.md
[![agentmods](https://agentmods.dev/badge/commands/mario-montanari/italiano-scrittura-anti-ai/difendi/github.svg)](https://agentmods.dev/commands/mario-montanari/italiano-scrittura-anti-ai/difendi)
Your own site
<a href="https://agentmods.dev/commands/mario-montanari/italiano-scrittura-anti-ai/difendi"><img src="https://agentmods.dev/badge/commands/mario-montanari/italiano-scrittura-anti-ai/difendi/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 difendi

Your own site · 80×15
<a href="https://agentmods.dev/commands/mario-montanari/italiano-scrittura-anti-ai/difendi"><img src="https://agentmods.dev/badge/commands/mario-montanari/italiano-scrittura-anti-ai/difendi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,567 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 $0.00052 $0.02567
Opus 5 $0.00026 $0.01283
Sonnet 5 $0.00010 $0.00513
Haiku 4.5 $0.00005 $0.00257

Measured 12d ago against content hash 83c3d8af3600, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

difendi 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.

commands/difendi.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Difendi

Comando della skill italiano-scrittura-anti-ai. Il metodo completo, le evidenze pubblicate e i due modelli di documento sono in references/scudo-falsi-positivi.md, che sta in una di queste tre posizioni secondo come la skill è stata installata:

${CLAUDE_PLUGIN_ROOT}/references/scudo-falsi-positivi.md
~/.claude/skills/italiano-scrittura-anti-ai/references/scudo-falsi-positivi.md
.claude/skills/italiano-scrittura-anti-ai/references/scudo-falsi-positivi.md

La prima riga vale quando il comando arriva dal plugin: Claude Code sostituisce il segnaposto con la cartella dove il plugin è installato. Se lo si legge con le parentesi graffe ancora al loro posto, il plugin non c'è e quella riga si salta.

Se il file c'è, leggerlo prima di procedere, e con lui references/voce-personale.md per il passo 4. Se non c'è, il comando è stato copiato da solo in .claude/commands/ senza la skill: la procedura qui sotto si esegue lo stesso, e i rimandi alle sezioni della guida restano un approfondimento, non un requisito. In quel caso le evidenze pubblicate non si citano a memoria: si dichiara che non erano disponibili, oppure si chiede all'utente di recuperarle.

File indicato dall'utente: $ARGUMENTS

Il confine di questo comando

Read the full file on GitHub · 211 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 · 211 lines · 52 tokens per session scan A 83c3d8af3600

Subscribe to this mod's changes

difendi is a command published in the GitHub repository mario-montanari/italiano-scrittura-anti-ai (25 stars, last pushed 12d ago), licensed MIT. It adds 52 tokens to every session and 2,567 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.