What is architettura-fortezza?

A four-layer server-security design that keeps important data and keys offline, hides the real server and administration access, and places a protective gateway in front of the public website.

Use it to configure a reverse proxy, firewall, WireGuard private network, encrypted backups, and an offline data store. The public website itself cannot be invisible to visitors.

It reduces the number of systems attackers can reach and keeps the most sensitive parts away from the public internet.

architettura-fortezza — Skill for Claude Code by ayalaphiscan

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.

Any agent

npx skills add ayalaphiscan/web-security-guard --skill architettura-fortezza

Clone the repo

git clone --depth 1 https://github.com/ayalaphiscan/web-security-guard

Made for: Claude Code.

Or install web-security-guard, the plugin that ships this one along with the rest of its 6 skills, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ayalaphiscan/web-security-guard/architettura-fortezza/github.svg)](https://agentmods.dev/skills/ayalaphiscan/web-security-guard/architettura-fortezza)

Your own site

<a href="https://agentmods.dev/skills/ayalaphiscan/web-security-guard/architettura-fortezza"><img src="https://agentmods.dev/badge/skills/ayalaphiscan/web-security-guard/architettura-fortezza/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ayalaphiscan/web-security-guard/architettura-fortezza"><img src="https://agentmods.dev/badge/skills/ayalaphiscan/web-security-guard/architettura-fortezza.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,738 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.

Model	Per session	Once invoked
Fable 5.1	$0.00185	$0.01738
Opus 5	$0.00093	$0.00869
Sonnet 5	$0.00037	$0.00348
Haiku 4.5	$0.00018	$0.00174

Measured 11d ago against content hash 7c47ec41bcec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

architettura-fortezza 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 11d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (references/fortezza/cassaforte/backup-cifrato.sh, references/fortezza/cassaforte/genera-chiavi.sh, references/fortezza/cassaforte/pull-su-cassaforte.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/architettura-fortezza/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architettura Fortezza (4 livelli) · Fortress Architecture

🇮🇹 Versione italiana qui sotto · 🇬🇧 English version below

Quando l'utente vuole un sistema "blindato" dove il cuore è staccato e lo scudo è invisibile, proporre e installare questa architettura. I file template completi (proxy guardian, Caddy, docker-compose, firewall, WireGuard, backup cifrati) sono in references/fortezza/ dentro questa skill; questa skill spiega come adattarli.

Premessa onesta da dare SEMPRE all'utente

La porta web pubblica non può essere invisibile: se i visitatori la raggiungono, la raggiunge anche chi attacca. Invisibili possono diventare invece SSH, l'amministrazione, il server reale e la cassaforte. E i DDoS volumetrici enormi restano gestibili solo con un CDN/WAF esterno (es. Cloudflare free) davanti allo scudo. Non promettere "non attaccabile": promettere "superficie ridotta al minimo, cuore irraggiungibile, dati sempre recuperabili".

I quattro livelli

Scudo invisibile — unica macchina pubblica. Caddy (HTTPS + rimozione impronte) → proxy guardian (WAF, rate limit, blocklist silenziosa, lockdown, honeypot). Firewall stealth: solo 80/443 visibili, resto in DROP, niente ping.
Server origine nascosto — sito + DB, nessuna porta pubblica, accetta solo lo scudo via VPN. L'app ascolta sull'IP VPN, mai esposta dal provider.
WireGuard — rete privata cifrata tra scudo, origine e admin. Non risponde senza chiave valida → invisibile agli scanner. Solo gli AllowedIPs passano.
Cassaforte offline — air-gapped, custodisce la chiave privata. Backup cifrati con chiave pubblica (il server cifra ma non può decifrare). La cassaforte va a prendere i backup (sola andata); il server non la conosce.

Principi di progettazione da rispettare

Minima superficie: ogni livello espone solo ciò che serve al livello accanto.
Conoscenza parziale: ogni macchina conosce solo il vicino, mai l'intera catena.
One-way verso il cuore: nessun percorso che parta dal server e arrivi alla cassaforte.
Cifratura asimmetrica: chi può essere compromesso (il server) ha solo la chiave pubblica.
Silenzio: agli attaccanti non si risponde (stealth), per non dare impronte né feedback.
Difesa in profondità: questa architettura si SOMMA alle altre skill del plugin (hardening-siti, difesa-attacchi, privacy-pagamenti, autenticazione-sicura), non le sostituisce.

Read the full file on GitHub · 107 lines

Files

What ships with it

13 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.

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.

11d ago First seen · 107 lines · 185 tokens per session scan A 7c47ec41bcec

Subscribe to this mod's changes

architettura-fortezza is a skill published in the GitHub repository ayalaphiscan/web-security-guard (4 stars, last pushed 3mo ago), licensed MIT. It adds 185 tokens to every session and 1,738 once invoked, about $0.0009 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 2026-08-31.

Claude Code Cloud DevOps and cloud Security ai-agents claude claude-code-plugin hardening

framework-compliance-triage

Make a cloud account compliant with a security or industry framework using Prowler Cloud.

prowler-cloud/prowler · 24 tokens

deploy-site

Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.

microsoft/power-platform-skills · 50 tokens

activate-site

Activates and provisions a Power Pages website in a Power Platform environment via the Power Platform REST API. Use when the user wants to activate, provision, turn on, or enable a Power Pages website or portal.

microsoft/power-platform-skills · 45 tokens

deploy

Builds and deploys a Power Apps code app to Power Platform. Use when deploying changes, redeploying an existing app, or pushing updates.

microsoft/power-platform-skills · 32 tokens

deploy-to-connect

Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package. Handles interactive apps and dashboards, web APIs, rendered documents, and prepared bundles/manifests. Use whenever the user asks to deploy, publish, or redeploy content to Posit Connect, or mentions…

posit-dev/skills · 81 tokens

telephony-and-conferencing

Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…

cbrock84/headcount · 85 tokens