Azure Skills Plugin is an agent plugin that packages Azure-specific guidance with MCP server configurations for carrying out Azure work. Coding agents use it to plan, deploy, troubleshoot, monitor, govern, and optimize Azure applications and services. The catalogue entries are the plugin's skills, instructions, and execution integrations.
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/azure-skills --skill aks-network-capturegit clone --depth 1 https://github.com/microsoft/azure-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/microsoft/azure-skills/aks-network-capture)<a href="https://agentmods.dev/skills/microsoft/azure-skills/aks-network-capture"><img src="https://agentmods.dev/badge/skills/microsoft/azure-skills/aks-network-capture/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/azure-skills/aks-network-capture"><img src="https://agentmods.dev/badge/skills/microsoft/azure-skills/aks-network-capture.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 | $0.00075 | $0.00661 |
| Opus 5.5 | $0.00030 | $0.00264 |
| Sonnet 5.5 | $0.00015 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
aks-network-capture 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 6d 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.
This is a copy
100% identical to aks-network-capture — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AKS Network Capture
Quick Reference
| Use | Requires | Safety |
|---|---|---|
| AKS pcap evidence | kubectl; az for Azure evidence |
Bounded, pinned, least privilege |
When to Use This Skill
Use for explicit packet capture after read-only checks, not generic connectivity failures.
MCP Tools
Azure MCP's AKS area provides cluster and node-pool metadata, not Kubernetes command execution or packet capture.
Host Capability Gate
Before executing the workflow, confirm that the host permits the required
Bash or PowerShell execution, kubectl access to the bound cluster, az for
Azure evidence, access to the bundled scripts, and an approved artifact
destination. A governed Azure CLI tool alone does not establish that shell,
Kubernetes commands, or artifact operations are supported.
If a required capability is unavailable or prohibited, state that capture
execution is unavailable in this host. Analyze supplied, appropriately
redacted evidence or give the operator a target-bound collection/capture plan;
do not claim to have run it. Never route kubectl through Azure MCP, add an
unapproved execution path, or bypass host policy. Host support does not replace
the mutation and sensitive-data approvals below.
Run bundled scripts from the skill root only after this gate is satisfied.
Workflow/Steps
- Check host capabilities, then complete authorization and target binding. Capture intent is not mutation consent. Stop for separate approval before any debug-container fallback.
- Install Bash / PowerShell.
- Capture nodes or pods with Bash / PowerShell.
- Generate traffic if approved with Bash / PowerShell.
- Retrieve the exact run with Bash / PowerShell.
- Gather Azure evidence with Bash / PowerShell.
What ships with it
12 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.
- references/capture-authorization.md 1.4 KB
- scripts/collect-azure-network-info.ps1 7.9 KB runs code
- scripts/collect-azure-network-info.sh 7.0 KB runs code
- scripts/create-capture.ps1 12 KB runs code
- scripts/create-capture.sh 12 KB runs code
- scripts/generate-test-traffic.ps1 5.4 KB runs code
- scripts/generate-test-traffic.sh 6.1 KB runs code
- scripts/retrieve-captures.ps1 9.4 KB runs code
- scripts/retrieve-captures.sh 8.1 KB runs code
- scripts/run-capture.sh 2.4 KB runs code
- scripts/setup-capture-configmap.ps1 1.7 KB runs code
- scripts/setup-capture-configmap.sh 1.2 KB runs code
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.
- 6d ago First seen · 64 lines · 75 tokens per session scan A afa6c749b8a5
aks-network-capture is a skill published in the GitHub repository microsoft/azure-skills (1,572 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 661 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to aks-network-capture, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-workload-scaling-troubleshooting
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as , FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter…
gke-ai-troubleshooting-tpu-mxla-hang
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale HANGDETECTED logs and hang monitored events) using the ML Diagnostics Megascale XLA (MXLA) Hang Analyzer (gcloud alpha mldiagnostics monitored-events) and 1-minute Cloud Monitoring multi-slice latency metrics (kubernetes.io/container/multislice/).…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-node-unresponsive-timeout
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for…