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 tahirraufkeeyu/software-development-agent-stack--sdas --skill infra-triagegit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/infra-triage)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/infra-triage"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/infra-triage/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/tahirraufkeeyu/software-development-agent-stack--sdas/infra-triage"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/infra-triage.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 | $0.00059 | $0.03284 |
| Opus 5 | $0.00030 | $0.01642 |
| Sonnet 5 | $0.00012 | $0.00657 |
| Haiku 4.5 | $0.00006 | $0.00328 |
Grade A, and why
infra-triage scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `dig`, `nslookup`, `curl`, `openssl`, `mtr` for the network branch. How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- A vague platform alarm has fired ("cluster X is degraded", "half our pods are unhappy", "certs expiring in 3 days").
- On-call has received a user-facing impact report and does not yet know whether the cause is nodes, network, or certs.
- A routine health sweep after a cloud-provider maintenance window or a CNI upgrade.
- Before any large change (Helm upgrade, node-pool recycle), to confirm the cluster baseline is sane.
Do not use for application-level debugging (use the owning service's logs), for cost/FinOps reviews, or for a known-cause incident where direct remediation is obvious — call incident-response or the specific skill directly.
Chained skills
Executed as a decision tree, not a fixed sequence:
cluster-health— always runs first. Producesinfrastructure/findings/cluster-health.jsonwith node conditions, pod lifecycle counts, and a severity-ranked findings ladder.network-diagnostics— runs only ifcluster-healthfindings include any of:DNS failure,service unreachable,NetworkUnavailablenode condition, CoreDNS CrashLoopBackOff, kube-proxy not ready on a node, or ingress controller 5xx surge.ssl-certificate-manager— runs only ifcluster-healthor alerting surfaces: cert-managerCertificateRequestfailures,x509: certificate has expirederrors in pods,IngressTLS secret missing, or a PrometheusCertManagerCertExpirySoonalert.incident-response— runs only if user-facing impact is confirmed (5xx rate > SLO on a public service, customer tickets tied to the symptom, or status-page decision pending). Drives comms and draft postmortem.
Inputs
cluster— kubeconfig context or cluster name (single cluster per run).alert_source— optional: alert payload (PagerDuty/Alertmanager JSON) that kicked off the triage.impact_scope—internal|user-facing|unknown. Controls whether theincident-responsebranch can run.critical_namespaces— e.g.[ingress, payments, kube-system]to weight findings.incident_window_minutes— how far back to scan events and metrics (default 60).remediation_mode—suggest(default, read-only) |act(may restart pods, reapply secrets, rotate certs).actrequires explicit caller consent per run.
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.
- 10d ago First seen · 268 lines · 59 tokens per session scan A d7b4da1930f1
infra-triage is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 3,284 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-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-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-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-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.