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.
/plugin marketplace add mario-montanari/italiano-scrittura-anti-ai/plugin install italiano-scrittura-anti-aiWrote 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/commands/mario-montanari/italiano-scrittura-anti-ai/difendi)<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.
<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>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 | $0.00052 | $0.02567 |
| Opus 5 | $0.00026 | $0.01283 |
| Sonnet 5 | $0.00010 | $0.00513 |
| Haiku 4.5 | $0.00005 | $0.00257 |
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.
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
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 · 211 lines · 52 tokens per session scan A 83c3d8af3600
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 $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
humanizer
Humanize text — strip AI-writing patterns from pasted text or a file without changing what it says.
README
Git workflow and quality assurance commands for the claude-skills repository.
story-long-scan
A command for scanning long-form online fiction rankings on platforms such as Qidian, Fanqie, and Jinjiang, then analyzing the ranking data.
story-short-scan
A tool for scanning and analysing popular short web-fiction rankings on platforms such as Zhihu Yanyan and Fanqie Short Stories.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.