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 Aidas-dev/k8s-agent-skills --skill kserve-operatorgit clone --depth 1 https://github.com/Aidas-dev/k8s-agent-skillsWrote 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/aidas-dev/k8s-agent-skills/kserve-operator)<a href="https://agentmods.dev/skills/aidas-dev/k8s-agent-skills/kserve-operator"><img src="https://agentmods.dev/badge/skills/aidas-dev/k8s-agent-skills/kserve-operator/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/aidas-dev/k8s-agent-skills/kserve-operator"><img src="https://agentmods.dev/badge/skills/aidas-dev/k8s-agent-skills/kserve-operator.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 | $0.00047 | $0.05941 |
| Opus 5 | $0.00023 | $0.02971 |
| Sonnet 5 | $0.00009 | $0.01188 |
| Haiku 4.5 | $0.00005 | $0.00594 |
Grade A, and why
kserve-operator 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 769 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KServe — Operator CRDs & Configuration
Repository: github.com/kserve/kserve
Latest release: v0.18.0 (Apr 29, 2026) — v0.19.0-rc0 available
CNCF: Incubating (Jan 2025)
License: Apache 2.0
Stars: 10k+
Architecture
RawPredictOp → Preprocess → Predict → [Explain] → Postprocess → ExplainOp
(Transformer) (Predictor) (Transformer)
InferenceService (CRD) ──► KServe Controller ──► Deployment + Service + HPA + Istio/Knative
│
Storage: S3/GCS/Azure/HF/PVC/HTTP/HDFS
│
Modelcar (OCI) or PVC or storage init container
Deployment Modes
| Mode | Networking | Use Case |
|---|---|---|
| Standard | Istio VirtualService | Enterprise, stable, full traffic control |
| Knative | Knative + Istio (Kourier optional) | Auto-scaling to zero, serverless |
| Raw | Direct Service + Ingress/Gateway | Simple, lightweight, no service mesh |
Annotations Control
| Annotation | Effect |
|---|---|
serving.kserve.io/deploymentMode |
Serverless (Knative, default), RawDeployment, ModelMesh |
serving.tempaltes.kserve.io/default |
Template rendering default |
sidecar.istio.io/inject |
true to inject Istio sidecar |
CRDs (22 total — primary 9 covered here)
All under serving.kserve.io:
| CRD | API Version | Scope | Short Name | Description |
|---|---|---|---|---|
| InferenceService | v1beta1 / v1alpha1 |
Namespaced | isvc |
Core serving unit |
| ServingRuntime | v1alpha1 |
Namespaced | sr |
Runtime template (ModelMesh) |
| ClusterServingRuntime | v1alpha1 |
Cluster | csr |
Cluster-scoped runtime template |
| InferenceGraph | v1alpha1 |
Namespaced | ig |
Router graph (ensemble/switch/splitter) |
| TrainedModel | v1alpha1 |
Namespaced | tm |
Model-scoped config for ServingRuntime |
| LLMInferenceService | v1alpha1 |
Namespaced | — | LLM-specific (disaggregated prefill/decode) |
| LocalModelCache | v1alpha1 |
Namespaced | lm |
Node-level model cache for LocalModelNode |
| LocalModelNode | v1alpha1 |
Cluster | lmn |
Node DaemonSet for model loading |
| ClusterStorageContainer | v1alpha1 |
Cluster | csc |
Default storage container template |
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.
- 9d ago First seen · 769 lines · 47 tokens per session scan A 646dd256d778
kserve-operator is a skill published in the GitHub repository Aidas-dev/k8s-agent-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 47 tokens to every session and 5,941 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.
Other skills, from other repositories
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…