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 agentmods add skills/nvidia/nvcf/codegennpx skills add NVIDIA/nvcf --skill codegengit clone --depth 1 https://github.com/NVIDIA/nvcfWhat 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 | $0.00059 | $0.00746 |
| Opus 5 | $0.00030 | $0.00373 |
| Sonnet 5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
codegen 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Generation Pipeline
task generate runs Orval, which reads the three OpenAPI specs in spec/
directly and generates React Query hooks, TypeScript models, and MSW handler
factories into ui/src/generated/. It then adds Apache license headers to the
output. There is no bundling step (no Redocly, no openapi.yaml).
Specs:
spec/control-plane-openapi.yaml— the UI shim/BFF APIspec/nvcf-openapi.yaml— NVCF Cloud Functions (v2) APIspec/sis-openapi.yaml— cluster API
Gotchas
- Edit the specs in
spec/— never edit anything inui/src/generated/(regenerated output). ui/src/generated/is committed and enforced by the Codegen Check CI job: if you change a spec, runtask generateand commit the regenerated output, or CI fails on the diff.- Orval config is in
ui/orval.config.ts(one sharedoutputblock spread across all three specs). Customize generation there, not in the generated files. - Generated hook names follow Orval's convention:
useGetFunctions,useGetFunctionsSuspense,getGetFunctionsQueryOptions. The double "Get" is expected — don't rename them.
What Gets Generated
- React Query hooks —
useGetFunctions,useGetFunctionsSuspense, etc. (suspense variants are generated globally). - Query options factories —
getGetFunctionsQueryOptionsfor use in route loaders. - TypeScript models — plain
interface/typefiles inui/src/generated/model/(no runtime validation). Zod generation is intentionally off; re-add it as a separateclient: "zod"Orval target if runtime validation is ever needed. - MSW handler factories — per-endpoint mock handlers plus per-response mock generators (
getGetFunctionVersionResponseMock, etc.).
Mocks and Scenarios
The default mock baseline is a seeded in-memory store (ui/src/mocks/store/), not the raw generated handlers. The store builds a stable dataset once (keyed by account ncaId) using the generated response-mock generators, so list and detail views stay consistent and their IDs line up.
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.
- 2d ago First seen · 52 lines · 59 tokens per session scan A e8f57dad7fad
codegen is a skill published in the GitHub repository NVIDIA/nvcf (202 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 746 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
vmware-privateai
Use this skill whenever the user needs the GPU / AI-infrastructure layer of VMware Private AI Foundation with NVIDIA (PAIF-N) on vSphere 9.x / VCF 9.1: inventory GPU hosts and physical GPU devices, see which VMs consume a vGPU and the profile each holds, read real-time GPU utilization, list the vGPU and DirectPath…
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.
accelerated-computing-cudf
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
llm-torch-profiler-analysis
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed. Use it to inspect an existing trace.json(.gz) or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.
cookbook-review-pr
Review a pull request against the SGLang Cookbook (docs/, Mintlify) contribution checklist — the config-driven format (per-model config + benchmarks JSX consumed by the shared deployment.jsx / playground.jsx engines). Run with /cookbook-review-pr .
speculative-naming
Naming conventions for SGLang speculative decoding identifiers. Use when adding, renaming, or reviewing identifiers in speculative decoding code — anything under python/sglang/srt/speculative/, related attention backends, scheduler accumulators, IPC fields, observability metrics, or CLI flags.