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.
npx skills add khalilbenaz/claude-skills-collection --skill cloud-security-guidegit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/skills/khalilbenaz/claude-skills-collection/cloud-security-guide)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/cloud-security-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/cloud-security-guide/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/skills/khalilbenaz/claude-skills-collection/cloud-security-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/cloud-security-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.02408 |
| Opus 5 | $0.00036 | $0.01204 |
| Sonnet 5 | $0.00014 | $0.00482 |
| Haiku 4.5 | $0.00007 | $0.00241 |
Grade A, and why
cloud-security-guide 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Security Guide
Workflow en 8 étapes
1. Auditer et durcir l'IAM
Critère de déclenchement : nouveau compte cloud, audit trimestriel, onboarding d'un service.
# AWS — lister les utilisateurs sans MFA
aws iam generate-credential-report
aws iam get-credential-report --query 'Content' --output text | base64 -d | grep ',false,'
# AWS — trouver les politiques permissives (Action: *)
aws iam list-policies --scope Local --query "Policies[*].Arn" --output text | \
xargs -I{} aws iam get-policy-version --policy-arn {} --version-id v1 \
--query "PolicyVersion.Document" 2>/dev/null | grep -B5 '"Action": "\*"'
# Azure — Access Review via CLI
az ad user list --query "[?accountEnabled==\`true\`].{UPN:userPrincipalName}" --output table
Règles d'or :
- Pas de credentials longue durée sur les machines : utiliser des Instance Profiles / Managed Identities / Workload Identity.
- Séparer les comptes par environnement (dev / staging / prod) avec AWS Organizations SCPs ou Azure Management Groups.
- Imposer MFA via une SCP/Policy bloquant toutes les actions si MFA absent.
// AWS SCP — forcer MFA
{
"Effect": "Deny",
"NotAction": ["iam:CreateVirtualMFADevice","iam:EnableMFADevice","sts:GetSessionToken"],
"Resource": "*",
"Condition": {"BoolIfExists": {"aws:MultiFactorAuthPresent": "false"}}
}
2. Segmenter le réseau
# AWS — VPC avec sous-réseaux isolés (Terraform snippet)
resource "aws_vpc" "main" { cidr_block = "10.0.0.0/16" }
resource "aws_subnet" "public" { cidr_block = "10.0.1.0/24" ... }
resource "aws_subnet" "private" { cidr_block = "10.0.2.0/24" ... }
resource "aws_subnet" "data" { cidr_block = "10.0.3.0/24" ... }
# Activer les VPC Flow Logs
aws ec2 create-flow-logs \
--resource-type VPC --resource-ids vpc-xxx \
--traffic-type ALL --log-destination-type cloud-watch-logs \
--log-group-name /vpc/flowlogs
Décision rapide :
| Ressource | Exposition autorisée |
|---|---|
| Base de données | Jamais publique — Private endpoint obligatoire |
| Application web | Via ALB/WAF uniquement |
| API interne | Via VPN ou Service Mesh |
| Bucket/Blob | Jamais public sauf CDN explicite |
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 · 233 lines · 71 tokens per session scan A dcf27cc43356
cloud-security-guide is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 71 tokens to every session and 2,408 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
docker-devops
Docker/K8s: Dockerfile, multi-stage, compose, manifests, Helm. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod.
rollback
Rolls back git commit, DB migration, or deploy to known-good with safety + health checks. Triggers: rollback, revert deploy, revert migration, rollback commit, git revert.
health
Service/infra health via liveness/readiness checks, resource usage, quick diagnostics. Triggers: health check, services up, system status, infra health, degraded service.
monitoring-alerting
Monitoring and alerting design reviewer for production backend services. ALWAYS use when writing Prometheus alerting rules, designing Grafana dashboards, defining SLI/SLO, configuring alert routing (PagerDuty/OpsGenie/Slack), or reviewing existing monitoring setups. Covers SLI/SLO definition, alert rule quality…
piggyback-hosting
Hosting-Muster, um eine lokal gebaute Anwendung (eigene Datenbank, eigener API-Key, In-Process-State) sicher hostbar zu machen, ohne Nutzerverwaltung zu bauen. Kernzug — der Host speichert nichts, der Browser des Besuchers speichert alles — sodass Pro-Besucher-Accounts, Zugriffsprüfungen und Löschfristen…
cloud-communication-protocols
Dach-Skill für Cloud-gestützte Kommunikationsprotokolle zwischen Agenten auf unterschiedlichen Maschinen (Ping-Pong, agent-beam, Listener und künftige Protokolle). Nutzen, wenn Arbeit über Maschinen hinweg per gemeinsamem Sync-Ordner oder Message-Yard koordiniert wird.