NVIDIA Cloud Functions is a platform for deploying, managing, and running GPU-based workloads such as inference, streaming, and batch processing, while routing requests to GPU worker clusters. Its monorepo contains the service code, deployment materials, documentation, examples, command-line tools, agent skills, and validation tools used to build and operate the platform.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVIDIA/nvcfnpx agentmods add skills/nvidia/nvcf/nvca-self-managed-installWrote 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/nvidia/nvcf/nvca-self-managed-install)<a href="https://agentmods.dev/skills/nvidia/nvcf/nvca-self-managed-install"><img src="https://agentmods.dev/badge/skills/nvidia/nvcf/nvca-self-managed-install/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/nvidia/nvcf/nvca-self-managed-install"><img src="https://agentmods.dev/badge/skills/nvidia/nvcf/nvca-self-managed-install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 69 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.00847 |
| Opus 5.5 | $0.00022 | $0.00339 |
| Sonnet 5.5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
nvca-self-managed-install 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 6d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NVCA Self-Managed Install
Use deploy/helm/nvca-operator as the install surface for NVCA Operator chart
validation. Do not add NVCA back into the stack Helmfile just to test this
chart.
Source of Truth
- Control-plane deployment:
deploy/stacks/self-managed - NVCA chart and install workflow:
deploy/helm/nvca-operator - NVCA source images and source chart:
src/compute-plane-services/nvca - Cluster prerequisites: use the public
nvcf-self-managed-prerequisiteskill - Full stack install and teardown: use the public
nvcf-self-managed-installationskill
Instructions
Run from deploy/helm/nvca-operator:
make render-values-from-stack \
stack_env=local \
stack_repo=../../../deploy/stacks/self-managed
Inspect the generated file under bin/, then install or upgrade. The render
also sets the values the control-plane validator role needs from the stack:
clusterValidator.gatewayNames from the wired ingress.gatewayApi.gateways,
clusterValidator.storageClass from global.storageClass, and
clusterValidator.externalComponents from the quorum components the stack
disables. It rewrites them on every render, empty included, so an upgrade does
not keep a stale value from the release. On a registry other than NGC
(nvcr.io or a subdomain) it also sets clusterValidator.nodeToNodeProbeImage
to busybox:1.36 under the stack's repository, so mirror that image there. It
keeps a probe image the release already sets, and sets none when
networkChecks.enforcement.testImage is set:
make install-from-stack \
stack_env=local \
stack_repo=../../../deploy/stacks/self-managed
Optional Inputs
additional_values=override.ymlfor one-off overridesNCA_ID=<value>to set the primary account ID explicitlyCLUSTER_NAME=<value>andCLUSTER_ID=<value>to preserve or pin cluster identityIMAGE_PULL_SECRET_NAME=<secret>to attach a pre-created image pull secretNODE_TO_NODE_PROBE_IMAGE=<image>to pick the node-to-node probe image; it must be pullable without an image pull secret
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.
- 6d ago Changed 7b909be28e88
- 13d ago Changed · +12 lines b476fa2e5917
- 1mo ago First seen · 72 lines · 55 tokens per session scan A 9d9d56afc42c
nvca-self-managed-install is a skill published in the GitHub repository NVIDIA/nvcf (244 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 847 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
obol-stack
Monitor the Kubernetes cluster running the Obol Stack. Use when asked about pod status, logs, events, services, deployments, statefulsets, PVCs, or diagnosing issues — in your own namespace or across the cluster (local Ethereum nodes, DV pods, monitoring). Read-only; Secrets are never readable.
helm
Package Kubernetes applications as Helm charts, configure values and dependencies, and inspect release upgrades or rollbacks.
bazel-k8s-expert
Expert knowledge for deploying Quarkus/Java applications to Kubernetes using Bazel. Covers rulesk8s, Helm, Kustomize, ConfigMaps, Secrets, and health probes.
kubernetes-mesh-provisioner
Kubernetes Mesh Provisioner atomic skill. Stands up an RKE2 cluster (server + agents) with Cilium CNI and the NVIDIA GPU device plugin, the Kubernetes parallel of swarm-mesh-provisioner. Idempotent — re-runnable.
kubernetes-ontology-access
Use this skill whenever a user wants to onboard, deploy, install, or operate kubernetes-ontology; set up its Helm chart, release CLI, daemon, or topology viewer; run Kubernetes topology queries; diagnose Pod or Workload failures with AI-agent workflows; or connect human visual troubleshooting to the CLI and HTTP API.…
Kubernetes Expert
Kubernetes Expert delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.