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 mezmo/aura --skill incident-triagegit clone --depth 1 https://github.com/mezmo/auraWrote 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/mezmo/aura/incident-triage)<a href="https://agentmods.dev/skills/mezmo/aura/incident-triage"><img src="https://agentmods.dev/badge/skills/mezmo/aura/incident-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/mezmo/aura/incident-triage"><img src="https://agentmods.dev/badge/skills/mezmo/aura/incident-triage.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 | $0.00041 | $0.00380 |
| Opus 5 | $0.00020 | $0.00190 |
| Sonnet 5 | $0.00008 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
incident-triage 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 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.
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.
What it actually says
Incident triage
Follow these steps in order. Do not skip ahead to a fix.
1. Establish scope
- Identify the namespace and workload named in the request. If none is given, list namespaces and ask which one before continuing.
- Record the time the problem was first noticed.
2. Check workload state
- List pods for the workload and note any that are not
Running/Ready. - For each unhealthy pod, note restart count, last termination reason, and the age of the current container.
3. Read recent events
- List events for the namespace, most recent first.
- Look for:
OOMKilled,CrashLoopBackOff,FailedScheduling,ImagePullBackOff, probe failures, node pressure.
4. Read logs — narrowly
- Fetch logs only for the unhealthy pods, only the tail (last 200 lines).
- Search for stack traces, connection refused/timeouts, and the first error after the last successful startup line.
5. Report
Use exactly this structure:
Impact: <what is broken, for whom>
Since: <timestamp, from events or first error>
Cause: <best current hypothesis, with the evidence line that supports it>
Evidence: <pod names, event reasons, log excerpts — quoted, not paraphrased>
Next step: <one action, read-only unless the user asked for a fix>
If the evidence does not support a single cause, say so and list the two most likely candidates with what would distinguish them.
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 · 47 lines · 41 tokens per session scan A a0bf25cae090
incident-triage is a skill published in the GitHub repository mezmo/aura (353 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 380 once invoked, about $0.0002 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
cluster-events
Analyze cluster-wide Kubernetes events to identify issues and patterns. Aggregates Warning events, detects high-frequency patterns, and correlates related events.
quota-debug
Diagnose Kubernetes native ResourceQuota and LimitRange admission rejections (exceeded quota, forbidden by LimitRange, FailedCreate). Checks namespace quotas, current usage, LimitRange constraints, and ReplicaSet events to identify why pods cannot be created. Not applicable to Volcano Queue — use…
volcano-diagnose-pod
Diagnose Volcano-managed Pod scheduling issues. Checks Pod status, PodGroup, events, and Queue to identify scheduling failures.
volcano-job-diagnose
Diagnose Volcano Job status and issues. Check Job phases, task statuses, PodGroup associations, and overall job health.
volcano-queue-diagnose
Diagnose Volcano Queue status and resource allocation. Check queue weights, deserved resources, allocated resources, and identify queue-related scheduling bottlenecks.
volcano-scheduler-config
View Volcano scheduler configuration. Check scheduler ConfigMap, actions, plugins, and tier settings.