microsoft/sre-agent is the community repository for Azure SRE Agent, an AI assistant for diagnosing and resolving production problems and reducing routine operations work. It is for teams working on service reliability and includes documentation, discussions, videos, and hands-on labs for using the product. The catalogue skills relate to the agent's official plugins and resources.
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 microsoft/sre-agent --skill nsg-auditgit clone --depth 1 https://github.com/microsoft/sre-agentWrote 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/microsoft/sre-agent/nsg-audit)<a href="https://agentmods.dev/skills/microsoft/sre-agent/nsg-audit"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/nsg-audit/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/microsoft/sre-agent/nsg-audit"><img src="https://agentmods.dev/badge/skills/microsoft/sre-agent/nsg-audit.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 | $0.00100 | $0.01359 |
| Opus 5.5 | $0.00040 | $0.00544 |
| Sonnet 5.5 | $0.00020 | $0.00272 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
nsg-audit 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zava Learning — Network Security Group (NSG) & Connectivity-Path Audit
Resource Group: @@RG@@. Read-only audit — never create, modify, or delete an NSG, rule, route, or
firewall. This is a weekly posture review of the lab's network exposure and the integrity of its
connectivity paths, not an incident response.
1. Enumerate the network surface
- List every NSG:
az network nsg list -g @@RG@@. - For each NSG, list its security rules (custom + default):
az network nsg rule list -g @@RG@@ --nsg-name <nsg> --include-default. - Map each NSG to what it protects (
az network nsg show -g @@RG@@ -n <nsg> --query "{subnets:subnets[].id, nics:networkInterfaces[].id}"). An NSG attached to no subnet and no NIC is orphaned — itself a finding.
2. Evaluate every inbound (and risky outbound) rule
Flag, with an impact-based severity (see the zava-audit-report severity model):
- SEV1 — any inbound
Allowfrom*/Internet/0.0.0.0/0to a management port (22 SSH, 3389 RDP); a blanketAllow *:* *(any source, any port, any protocol); or a rule whosedescriptionmarks it temporary / break-glass ("temp", "troubleshooting", "INC-####") that is still present. - SEV2 — inbound
Allowfrom a broad source (large CIDR /Internet) to a data or admin port (e.g. 5432 Postgres, 6379 Redis, 1433, 27017, 8080-808x app-management ports) where the source should be a known subnet / Application Gateway only. - SEV3 — shadowed rules (a higher-priority rule fully masks a lower one so it can never match), unused / legacy rules (deny or allow referencing a decommissioned CIDR/subnet), overlapping / duplicate rules, priority inversions, and orphaned NSGs (attached to nothing). Distinguish the lab's intended exposure (the Application Gateway public lane ports 8081-8087 reaching the lane apps; the AppGw subnet allowing Internet inbound on 80/443 + those lane ports) from genuinely risky exposure — flag only what a real reviewer would. The lane data ports (Postgres, the reporting-VM subnet) should be reachable only from inside the VNet; the reporting VM has no public path and needs no inbound Internet at all.
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.
- 1mo ago First seen · 78 lines · 100 tokens per session scan A a500dccce5c0
nsg-audit is a skill published in the GitHub repository microsoft/sre-agent (179 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 1,359 once invoked, about $0.0004 per session on Opus 5.5. 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 security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
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 generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
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…
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".