pod-crashloop-triage

pod-crashloop-triage is a skill for Claude Code, Codex from agenticdevops/aoh. It costs 47 tokens per session (259 once invoked), scanned A, original, MIT.

A read-only investigation guide for Kubernetes pods that keep crashing, cannot download their container image, or run out of memory. Kubernetes pods are groups of containers managed by a cluster.

In plain words
What is it for?
Investigating CrashLoopBackOff, ImagePullBackOff, ErrImagePull, OOMKilled, and CreateContainerConfigError. It recommends the smallest safe next step and cites the evidence, but does not apply the fix.
Why use it?
It collects pod details, logs, events, and status so the failure can be identified before anyone changes the cluster. It separates common causes such as memory exhaustion, bad image settings, application errors, or missing configuration.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/agenticdevops/aoh/pod-crashloop-triage
Any agent
npx skills add agenticdevops/aoh --skill pod-crashloop-triage
Clone the repo
git clone --depth 1 https://github.com/agenticdevops/aoh

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 pod-crashloop-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/agenticdevops/aoh/pod-crashloop-triage.svg)](https://agentmods.dev/skills/agenticdevops/aoh/pod-crashloop-triage)
Your own site
<a href="https://agentmods.dev/skills/agenticdevops/aoh/pod-crashloop-triage"><img src="https://agentmods.dev/badge/skills/agenticdevops/aoh/pod-crashloop-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00259
Opus 5 $0.00023 $0.00130
Sonnet 5 $0.00009 $0.00052
Haiku 4.5 $0.00005 $0.00026

Measured 3d ago against content hash 7559102dcb1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pod-crashloop-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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/collect_pod_crash_diagnostics.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

collections/core/kubeops/skills/pod-crashloop-triage/SKILL.md · 23 lines

What it actually says

Pod Crashloop Triage

Diagnose crashing pods with read-only inspection. You cannot mutate the cluster — RBAC limits this agent to get/list/watch.

Process

  1. Run scripts/collect_pod_crash_diagnostics.sh (no args) to list crashing pods cluster-wide.
  2. For a specific pod: scripts/collect_pod_crash_diagnostics.sh <namespace> <pod>.
  3. Classify the failure from the output:
    • Exit code 137 / OOMKilled → memory limits vs usage
    • ImagePullBackOff / ErrImagePull → image name, tag, registry auth
    • Exit code 1 + app stack trace in previous logs → application bug or config
    • CreateContainerConfigError → missing ConfigMap/Secret reference
  4. Recommend the smallest safe next action (e.g. "raise memory limit to X", "fix image tag"), with the evidence line that supports it. Do not attempt the fix.
Files

What ships with it

1 file 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.

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. 3d ago First seen · 23 lines · 47 tokens per session scan A 7559102dcb1d

Subscribe to this mod's changes

pod-crashloop-triage is a skill published in the GitHub repository agenticdevops/aoh (5 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 259 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 2026-08-31.

Related

Other skills, from other repositories

container-manager-kubernetes-operations

Full operational Kubernetes surface via the container-manager-mcp MCP server — workloads (pods/rollouts/StatefulSets/DaemonSets/ReplicaSets/Jobs/CronJobs), config (ConfigMaps/Secrets/Namespaces/CRDs/patch), networking (Ingress/native Services/NetworkPolicy/DNS), storage (PV/PVC/StorageClass/snapshots/CSI), RBAC…

Knuckles-Team/container-manager-mcp · 189 tokens

doca-container-deployment

Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet standalone watching a static-pod manifests directory, YAML pod-spec drop, kubelet status / ENTRYPOINT logs / per-service liveness, smoke-before-bulk, and the layered…

NVIDIA/skills · 234 tokens

amc-setup-calibration-stack

Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.

NVIDIA/skills · 67 tokens

agent-substrate-deploy

Stand up Agent Substrate (gVisor-isolated Actors) on a dedicated local kind cluster wired to Orka and validate direct Substrate/MCP plus fixture-backed workspace ACP Task paths. Use when the user asks to install, enable, deploy, configure, validate, demo, or troubleshoot the Orka substrate execution-workspace…

orka-agents/orka · 86 tokens

openclaw-tune

OpenClaw system-level maintenance — cleans sessions/.bak rotation, disk bloat under /.openclaw/, validates model fallback chain, audits cron health, prunes short-term-recall noise. Run after openclaw update or every 1-2 weeks. Different from workspace document tune-up (single-responsibility canonical .md files, token…

KCNyu/clawock · 140 tokens

container-apps-deployment

Container Apps deployment gotchas and SPA frontend patterns for Azure. Supplements the official azure-prepare plugin skill with additional patterns for zone redundancy, azure.yaml configuration, and SPA frontend deployment (VITEAPIURL). USE FOR: Container Apps zone redundancy errors, managed-identity ACR pulls…

DanWahlin/github-azure-agentic-journeys · 124 tokens