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 jonathan-vella/apex-accelerator --skill apex-azure-diagnosticsgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/jonathan-vella/apex-accelerator/apex-azure-diagnostics)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-azure-diagnostics"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-diagnostics/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/jonathan-vella/apex-accelerator/apex-azure-diagnostics"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-diagnostics.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 | $0.00119 | $0.01800 |
| Opus 5.5 | $0.00048 | $0.00720 |
| Sonnet 5.5 | $0.00024 | $0.00360 |
| Haiku 4.5 | $0.00012 | $0.00180 |
Grade C, and why
apex-azure-diagnostics scanned grade C with 1 finding 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 22d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
not a healthy result. Do not dump credentials or app settings into reports. How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Diagnostics
AUTHORITATIVE GUIDANCE — MANDATORY COMPLIANCE
This document is the official source for debugging and troubleshooting Azure production issues. Follow these instructions to diagnose and resolve common Azure service problems systematically.
Triggers
Activate this skill when user wants to:
- Debug or troubleshoot production issues
- Diagnose errors in Azure services
- Analyze application logs or metrics
- Fix image pull, cold start, or health probe issues
- Investigate why Azure resources are failing
- Find root cause of application errors
- Troubleshoot Azure Function Apps (invocation failures, timeouts, binding errors)
- Find the App Insights or Log Analytics workspace linked to a Function App
- Troubleshoot App Service issues (high CPU, deployment failures, crashes, slow responses, TLS/custom domains)
- Troubleshoot AKS clusters, nodes, pods, ingress, DNS or upgrades
- Troubleshoot Azure VM connectivity (RDP/SSH failures, NSG or firewall blocks, VM agent issues)
- Troubleshoot Event Hubs and Service Bus SDK errors (AMQP failures, lock lost, connectivity)
Rules
- Start with systematic diagnosis flow
- Use AppLens (MCP) for AI-powered diagnostics when available
- Check resource health before deep-diving into logs
- Select appropriate troubleshooting guide based on service type
- Document findings and attempted remediation steps
- Diagnose only the approved scope; obtain separate approval before remediation
- Default to read-only. Restarts, redeploys,
run-command, credential resets, NSG changes, cordon/drain and node debug pods (run-igwith--approve) each need explicit approval - Never print secret values: list app setting names only, and never pass passwords through chat
Prerequisites
- Confirm resource IDs, subscription, incident window and read access.
- Use available Azure CLI or MCP capabilities; unavailable telemetry is a gap, not a healthy result. Do not dump credentials or app settings into reports.
What ships with it
52 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/aks/aks-troubleshooting.md 6.2 KB
- references/aks/general-diagnostics.md 2.0 KB
- references/aks/load-balancer-and-ingress.md 3.6 KB
- references/aks/network-policy.md 832 B
- references/aks/networking.md 5.5 KB
- references/aks/node-issues.md 4.7 KB
- references/aks/pod-failures.md 7.6 KB
- references/aks/references/aks-mcp.md 1.5 KB
- references/aks/references/command-flows.md 4.0 KB
- references/aks/references/inspektor-gadget.md 7.9 KB
- references/aks/references/structured-input-modes.md 1.5 KB
- references/aks/spot-and-zone-issues.md 2.5 KB
- references/aks/upgrade-operations.md 2.2 KB
- references/app-service/README.md 7.2 KB
- references/azure-resource-graph.md 2.2 KB
- references/compute/references/cannot-connect-to-vm.md 3.1 KB
- references/compute/references/credential-auth-errors.md 2.5 KB
- references/compute/references/firewall-blocking.md 2.3 KB
- references/compute/references/network-connectivity.md 2.5 KB
- references/compute/references/rdp-connectivity.md 2.8 KB
- references/compute/references/rdp-service-config.md 3.2 KB
- references/compute/references/ssh-connectivity.md 2.2 KB
- references/compute/references/vm-agent-not-responding.md 3.7 KB
- references/compute/vm-troubleshooting.md 3.3 KB
- references/container-apps/README.md 3.1 KB
- references/functions/README.md 3.8 KB
- references/infraops-health-checks.md 5.0 KB
- references/infraops-kql-templates.md 1.9 KB
- references/infraops-remediation-playbooks.md 3.5 KB
- references/kql-queries.md 1.3 KB
- references/messaging/azure-eventhubs-dotnet.md 3.5 KB
- references/messaging/azure-eventhubs-java.md 3.3 KB
- references/messaging/azure-eventhubs-js.md 2.8 KB
- references/messaging/azure-eventhubs-py.md 4.4 KB
- references/messaging/azure-servicebus-dotnet.md 2.5 KB
- references/messaging/azure-servicebus-java.md 2.2 KB
- references/messaging/azure-servicebus-js.md 2.4 KB
- references/messaging/azure-servicebus-py.md 2.3 KB
- references/messaging/README.md 1.6 KB
- references/messaging/service-troubleshooting.md 5.1 KB
- scripts/aks-baseline.ps1 7.0 KB runs code
- scripts/aks-baseline.sh 6.7 KB runs code
- scripts/appservice-diagnostics.ps1 2.3 KB runs code
- scripts/appservice-diagnostics.sh 2.9 KB runs code
- scripts/containerapp-diagnostics.ps1 2.1 KB runs code
- scripts/containerapp-diagnostics.sh 2.7 KB runs code
- scripts/pod-evidence.ps1 6.6 KB runs code
- scripts/pod-evidence.sh 7.1 KB runs code
- scripts/run-ig.ps1 6.1 KB runs code
- scripts/run-ig.sh 7.1 KB runs code
- scripts/test-messaging-connectivity.ps1 6.3 KB runs code
- scripts/test-messaging-connectivity.sh 6.8 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.
- 22d ago Changed · +31 lines · +19 tokens per session 3f9ac0daeeee
- 23d ago First seen · 148 lines · 100 tokens per session scan C 21493bc93690
apex-azure-diagnostics is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,800 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
azure-kubernetes-automatic-readiness
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic…
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
azure-diagnostics
Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function…
extracting-code-structure
Use when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively without loading entire files.
dynamo-troubleshoot
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.
forge-diagnose
Diagnose runtime infrastructure issues — cold starts, timeouts, scaling problems, network failures. Use when asked about "infra is slow", "cold starts", "network issues", "why is this timing out", "scaling problem", "latency spikes", or "service is down".