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.
git clone --depth 1 https://github.com/ayalaphiscan/web-security-guardWrote 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/ayalaphiscan/web-security-guard/proteggi-sito)<a href="https://agentmods.dev/commands/ayalaphiscan/web-security-guard/proteggi-sito"><img src="https://agentmods.dev/badge/commands/ayalaphiscan/web-security-guard/proteggi-sito/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/ayalaphiscan/web-security-guard/proteggi-sito"><img src="https://agentmods.dev/badge/commands/ayalaphiscan/web-security-guard/proteggi-sito.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 | $0.00053 | $0.00572 |
| Opus 5 | $0.00026 | $0.00286 |
| Sonnet 5 | $0.00011 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
proteggi-sito 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 9d 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.
What it actually says
Installa le protezioni di sicurezza nel progetto della cartella di lavoro corrente (se non c'è una cartella connessa, chiedila con request_cowork_directory). Prima rileva lo stack (Node/Express, Python, PHP, sito statico) guardando i file del progetto. Rispondi nella lingua dell'utente.
Applica nell'ordine:
- Agente anti-attacco (skill difesa-attacchi): copia e adatta
guardian-express.jsinsecurity/guardian.jse integralo nell'entry point dell'app. Per stack non-Node, riscrivi la stessa logica nel linguaggio del progetto. ConfiguraskipPathsper eventuali webhook di pagamento. - Security headers e hardening (skill hardening-siti): aggiungi helmet/headers, correggi cookie, CORS e gestione errori dove necessario.
- File GitHub (skill sicurezza-github): crea
.github/workflows/security.ymle.github/dependabot.ymladattati al linguaggio del progetto; verifica.gitignore. - Verifiche pagamenti e autenticazione: se il progetto gestisce pagamenti o login, controlla i punti critici delle skill privacy-pagamenti e autenticazione-sicura e correggi ciò che è automatizzabile; segnala il resto.
Non rimuovere funzionalità esistenti; se una modifica rischia di rompere qualcosa, chiedi prima conferma all'utente con AskUserQuestion.
Alla fine presenta un riepilogo: cosa è stato installato, cosa deve fare l'utente sul suo hosting/GitHub (attivare secret scanning, push protection, WAF/CDN), e come si attiva/disattiva manualmente il lockdown (file flag LOCKDOWN).
English: install the security protections in the current working folder's project (detect the stack first, reply in the user's language). Apply in order: 1) guardian anti-attack middleware (difesa-attacchi skill), 2) security headers and hardening (hardening-siti skill), 3) GitHub security files (sicurezza-github skill), 4) payments/authentication checks (privacy-pagamenti, autenticazione-sicura skills). Never remove existing functionality; ask before risky changes. End with a summary of what was installed, what the user must enable on their hosting/GitHub, and how to toggle the LOCKDOWN flag file.
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.
- 9d ago First seen · 21 lines · 53 tokens per session scan A adb155bd335a
proteggi-sito is a command published in the GitHub repository ayalaphiscan/web-security-guard (4 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 572 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 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
adr-supersede
Create a new ADR that supersedes an existing one.