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 kyleoliveiro/sg-gov-skills --skill network-securitygit clone --depth 1 https://github.com/kyleoliveiro/sg-gov-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/kyleoliveiro/sg-gov-skills/network-security)<a href="https://agentmods.dev/skills/kyleoliveiro/sg-gov-skills/network-security"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/network-security/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/kyleoliveiro/sg-gov-skills/network-security"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/network-security.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 | $0.00227 | $0.02790 |
| Opus 5 | $0.00113 | $0.01395 |
| Sonnet 5 | $0.00045 | $0.00558 |
| Haiku 4.5 | $0.00023 | $0.00279 |
Grade A, and why
network-security 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
network-security: NS controls for SG government systems
You are designing or auditing the network boundaries of a Singapore government system against the ICT&SS Policy Reform Network Security family (NS-1..NS-11). The family's scope is securing the network boundaries of a system — how the network is segmented, what may talk to what, how the edge is filtered, how services and sites connect privately, and how changes and intrusions are detected. Almost all of it is cloud/IaC configuration — security groups, endpoints, certificates, alert rules — cheap to get right on day one and exactly what a VAPT or CSPM scan walks through first.
Two facts anchor the family:
- Deny by default is the posture, not a control. NS-3 states it, but NS-1
segmentation, NS-2 resource policies, NS-9 private connectivity, and CS-9's private
cluster API are all the same idea applied at different interfaces. An audit that
finds one
0.0.0.0/0rule should immediately ask where else the default was left open — including egress, which teams forget. - The internet is never the transport between trusted parts. Private-to-private (NS-4), service-to-service (NS-7), and cloud-to-on-prem (NS-8) traffic all must move over private, authenticated, encrypted paths. "It's HTTPS anyway" does not satisfy the private-routing half.
Source and currency
Control text in this skill and references/ns-controls.md is embedded from
info.standards.tech.gov.sg as of 2026-07-23 (NS family page last updated 5 March
2026). The standards iterate actively. For any compliance-critical decision, verify
against the live page:
Reference files
references/ns-controls.md— full text of NS-1..NS-11 (statement, recommendations, risk statement) plus cross-family notes. Read it when you need exact wording for an audit response or SSP documentation.references/implementation-recipes.md— concrete config per control: subnet tiering, resource policies, deny-by-default rules, PrivateLink/peering/TGW choices, WAF/CDN setup, certificate automation, mTLS options, hybrid connectivity, IPS/IDS, remote access hardening, and firewall-change alert wiring, with AWS/Azure/GCP specifics. Read it when actually building or fixing.
What ships with it
6 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.
- 9d ago First seen · 191 lines · 227 tokens per session scan A ff2fa84bb2e2
network-security is a skill published in the GitHub repository kyleoliveiro/sg-gov-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 227 tokens to every session and 2,790 once invoked, about $0.0011 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-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…
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).
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…