debug-maas

debug-maas is a skill for Claude Code, Codex from MichalSteczko/rhoai-agentic-skills. It costs 44 tokens per session (5,193 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide and toolset for Models-as-a-Service, or MaaS, in OpenShift AI. OpenShift AI is a platform for running machine-learning services, and MaaS provides models to applications through that platform.

In plain words
What is it for?
Use it to investigate stuck tenants, startup loops, missing databases, failing pods, resource conditions, and HTTP gateway routing problems.
Why use it?
It helps locate configuration, database, tenant, pod, and gateway failures that can leave model services stuck or unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to investigate stuck tenants, startup loops, missing databases, failing pods, resource conditions, and HTTP gateway routing problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michalsteczko/rhoai-agentic-skills/debug-maas
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 MichalSteczko/rhoai-agentic-skills --skill debug-maas
Clone the repo
git clone --depth 1 https://github.com/MichalSteczko/rhoai-agentic-skills

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 debug-maas

README.md
[![agentmods](https://agentmods.dev/badge/skills/michalsteczko/rhoai-agentic-skills/debug-maas/github.svg)](https://agentmods.dev/skills/michalsteczko/rhoai-agentic-skills/debug-maas)
Your own site
<a href="https://agentmods.dev/skills/michalsteczko/rhoai-agentic-skills/debug-maas"><img src="https://agentmods.dev/badge/skills/michalsteczko/rhoai-agentic-skills/debug-maas/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 debug-maas

Your own site · 80×15
<a href="https://agentmods.dev/skills/michalsteczko/rhoai-agentic-skills/debug-maas"><img src="https://agentmods.dev/badge/skills/michalsteczko/rhoai-agentic-skills/debug-maas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00044 $0.05193
Opus 5 $0.00022 $0.02596
Sonnet 5 $0.00009 $0.01039
Haiku 4.5 $0.00004 $0.00519

Measured 11d ago against content hash 38eab14173a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

debug-maas 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 11d 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.

curl -s "http://${MAAS_HOST}/maas-api/v1/models"
skills/debug-maas/SKILL.md · 518 lines

How it starts

The opening of the file, as written. The whole thing — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MaaS Debugging Skill

Diagnose and resolve common Models-as-a-Service (MaaS) issues in OpenShift AI (RHOAI).

Namespace Reference

Resource Namespace
Tenant CR, MaasTenantConfig models-as-a-service
AITenant ai-tenants
maas-api, maas-postgres, maas-db-config secret redhat-ai-gateway-infra
maas-controller, modelsasservice redhat-ods-applications
Config (cluster-scoped)

Key Resources

  • DataScienceCluster (DSC): default-dsc — top-level; ModelsAsAServiceReady condition gates DSC Ready
  • Config (maas.opendatahub.io/v1alpha1): cluster-scoped default — owned by ModelsAsService; has bootstrap annotation
  • AITenant: models-as-a-service in ai-tenants — finalizer maas.opendatahub.io/aitenant-cleanup
  • MaasTenantConfig: default-tenant in models-as-a-service — reconciled by maas-controller
  • Tenant CR: default-tenant in models-as-a-service — status mirrored from MaasTenantConfig; read by DSC controller
  • maas-api: Deployment in redhat-ai-gateway-infra — requires maas-db-config secret
  • maas-db-config: Secret in redhat-ai-gateway-infra — must have DB_CONNECTION_URL key
  • GatewayClass openshift-default: cluster-scoped — Istio is configured to watch this name (PILOT_GATEWAY_API_DEFAULT_GATEWAYCLASS_NAME), but PILOT_ENABLE_GATEWAY_API_GATEWAYCLASS_CONTROLLER: false means Istio does NOT auto-create it; it must exist manually
  • Gateway maas-default-gateway in openshift-ingress: routes model HTTPRoutes from any namespace to model pods; requires maas-default-gateway-config ConfigMap in openshift-ingress for Istio to provision its Service/Deployment
  • HTTPRoute per model: in the model's namespace (e.g. <model-namespace>), parentRefs the maas-default-gateway
  • maas-controller: Deployment in redhat-ods-applications — label is control-plane=maas-controller (NOT app.kubernetes.io/name); holds a leader election lease; crashes with exit code 1 when it loses the lease

Read the full file on GitHub · 518 lines

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. 11d ago First seen · 518 lines · 44 tokens per session scan A 38eab14173a7

Subscribe to this mod's changes

debug-maas is a skill published in the GitHub repository MichalSteczko/rhoai-agentic-skills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 44 tokens to every session and 5,193 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

system-architecture

Canonical joelclaw topology, Central/Relay vocabulary, and wiring map. Use when reasoning about architecture, Panda/Flagg Central migration, satellites, run capture, tracing event flow, debugging why something ran/didn't run, identifying which worker executes a function, checking what listens on a port, or following…

joelhooks/joelclaw · 73 tokens

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.

opensandbox-group/OpenSandbox · 48 tokens

network-rca

Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…

kubeshark/kubeshark · 163 tokens

routing-calibration

Use when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.

vllm-project/semantic-router · 27 tokens

plano-observability-debugging

Improve Plano tracing and debugging workflows. Use for sampling strategy, span attributes, and trace query-based root-cause analysis.

katanemo/plano · 32 tokens

k8s-service-path

Trace the Kubernetes service path — Service to selector to pods to EndpointSlices to readiness, plus Ingress routing. Use when a service is getting no traffic, an ingress is not routing, or someone asks why a workload is unreachable inside a cluster.

automateyournetwork/netclaw · 55 tokens