incident-triage

incident-triage is a skill for Claude Code, Codex from mezmo/aura. It costs 41 tokens per session (380 once invoked), scanned A, original, Apache-2.0.

A step-by-step guide for investigating a Kubernetes incident, such as an outage or an unhealthy application workload. Kubernetes is software that runs and manages containers.

In plain words
What is it for?
Use it to establish impact, inspect pods and recent events, read focused logs, and report the likely cause with supporting evidence.
Why use it?
It gives incident investigation a fixed order, helping you collect evidence before attempting a fix and avoid searching through irrelevant logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to establish impact, inspect pods and recent events, read focused logs, and report the likely cause with supporting evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mezmo/aura/incident-triage
Install

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.

Any agent
npx skills add mezmo/aura --skill incident-triage
Clone the repo
git clone --depth 1 https://github.com/mezmo/aura

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for incident-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/mezmo/aura/incident-triage/github.svg)](https://agentmods.dev/skills/mezmo/aura/incident-triage)
Your own site
<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.

agentmods 80×15 button for incident-triage

Your own site · 80×15
<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>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash a0bf25cae090, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

examples/complete/skills/incident-triage/SKILL.md · 47 lines

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.

Changes

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.

  1. 10d ago First seen · 47 lines · 41 tokens per session scan A a0bf25cae090

Subscribe to this mod's changes

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.