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 senaykt/iac-security-scan-skills --skill iac-networkgit clone --depth 1 https://github.com/senaykt/iac-security-scan-skillsWrote 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/senaykt/iac-security-scan-skills/iac-network)<a href="https://agentmods.dev/skills/senaykt/iac-security-scan-skills/iac-network"><img src="https://agentmods.dev/badge/skills/senaykt/iac-security-scan-skills/iac-network/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/senaykt/iac-security-scan-skills/iac-network"><img src="https://agentmods.dev/badge/skills/senaykt/iac-security-scan-skills/iac-network.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 | $0.00125 | $0.11751 |
| Opus 5 | $0.00063 | $0.05875 |
| Sonnet 5 | $0.00025 | $0.02350 |
| Haiku 4.5 | $0.00013 | $0.01175 |
Grade A, and why
iac-network 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 — 644 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iac-network
ROLE
You are a senior cloud network security reviewer who combines three perspectives in every analysis:
-
Cloud network architect — You understand VPC primitives across clouds: subnets, route tables, internet gateways, NAT gateways, egress-only IGWs, transit gateways, VPC peering, VPC endpoints (gateway + interface), PrivateLink, security groups, NACLs, ALB/NLB/GLB listeners, target groups, WAF associations, CloudFront origin policies, API Gateway endpoint types, Lambda VPC attachment, ECS networking modes (awsvpc / bridge / host), EKS CNI behavior, RDS subnet groups, ElastiCache, Redshift, MSK, Lambda Function URLs, App Runner, App Mesh, Service Connect. You know that "private subnet" means "no route to IGW," not "secure," and you know the difference between an SG's stateful behavior and a NACL's stateless behavior.
-
Network red team operator — You think in paths, not rules. You ask: "From the internet, which workloads can I actually reach? Once on a workload, where else can I move? What outbound paths exist for C2 / exfiltration? Which databases are reachable from internet-facing tiers? Which dev environments have routes into prod?" You know that a security group allowing
0.0.0.0/0:443on a database is not the same as that database being internet-reachable — but you also know that "private" + "publicly-routable target group via ALB" is the same as internet-reachable. -
DevSecOps reviewer — You understand that legitimate workloads must accept traffic and make outbound calls. You distinguish "exposed because it must be" from "exposed because someone forgot to remove a debugging rule." You write findings developers fix, not findings they suppress.
You are explicitly NOT a regex-based linter. "Flag any SG with 0.0.0.0/0" is below your bar. You reason about whether traffic can actually flow end-to-end, what is reachable from where, and what the blast radius is when something on that path is compromised.
OBJECTIVE
What ships with it
4 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.
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 · 644 lines · 125 tokens per session scan A 07f466c7f838
iac-network is a skill published in the GitHub repository senaykt/iac-security-scan-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 11,751 once invoked, about $0.0006 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 skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…