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.
git clone --depth 1 https://github.com/openshift-eng/ai-helpersWrote 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/commands/openshift-eng/ai-helpers/cluster-health-check)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/cluster-health-check"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/cluster-health-check/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/commands/openshift-eng/ai-helpers/cluster-health-check"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/cluster-health-check.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 | $0.00011 | $0.06684 |
| Opus 5 | $0.00005 | $0.03342 |
| Sonnet 5 | $0.00002 | $0.01337 |
| Haiku 4.5 | $0.00001 | $0.00668 |
Grade A, and why
cluster-health-check 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cluster-health-check — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 706 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
hcp:cluster-health-check
Synopsis
/hcp:cluster-health-check <cluster-name> [--verbose] [--output-format json|text]
Description
The /hcp:cluster-health-check command performs an extensive diagnostic of a Hosted Control Plane (HCP) cluster to assess its operational health, stability, and performance. It automates the validation of multiple control plane and infrastructure components to ensure the cluster is functioning as expected.
The command runs a comprehensive set of health checks covering control plane pods, etcd, node pools, networking, and infrastructure readiness. It also detects degraded or progressing states, certificate issues, and recent warning events.
Specifically, it performs the following:
- Detects and validates the availability of oc or kubectl CLI tools and verifies cluster connectivity.
- Checks the HostedCluster resource status (Available, Progressing, Degraded) and reports any abnormal conditions with detailed reasons and messages.
- Validates control plane pod health in the management cluster, detecting non-running pods, crash loops, high restart counts, and image pull errors.
- Performs etcd health checks to ensure data consistency and availability.
- Inspects NodePools for replica mismatches, readiness, and auto-scaling configuration accuracy.
- Evaluates infrastructure readiness (including AWS/Azure-specific validations like endpoint services).
- Examines networking and ingress components, including Konnectivity servers and router pods.
- Scans for recent warning events across HostedCluster, NodePool, and control plane namespaces.
- Reviews certificate conditions to identify expiring or invalid certificates.
- Generates a clear, color-coded summary report and optionally exports findings in JSON format for automation or CI integration.
Prerequisites
Before using this command, ensure you have:
- Kubernetes/OpenShift CLI: Either
oc(OpenShift) orkubectl(Kubernetes)- Install
ocfrom: https://mirror.openshift.com/pub/openshift-v4/clients/ocp/ - Or install
kubectlfrom: https://kubernetes.io/docs/tasks/tools/ - Verify with:
oc versionorkubectl version
- Install
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.
- 7d ago First seen · 706 lines · 11 tokens per session scan A e794823c46fc
cluster-health-check is a command published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 6,684 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
System Status
Check overall system health and status.
investigate
Start a deep root-cause investigation on the AWS DevOps Agent and stream progress.
cloudflare-queues:troubleshoot
Quick troubleshooting for common Cloudflare Queues issues.
cloudflare-workers:debug
Interactive debugging workflow for Cloudflare Workers. Diagnoses deployment errors, runtime issues, and performance problems with step-by-step fixes.
cloudflare-workflows:debug
Interactive debugging for failing workflow instances. Use when user reports workflow errors, instances stuck, or deployment failures.
cloud-run-debug
Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers the root cause and proposes a fix. Read-only by default; --apply writes the fix to a branch.