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
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 NVIDIA/nvcf --skill documentation-stylegit clone --depth 1 https://github.com/NVIDIA/nvcfWrote 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/documentation-style)<a href="https://agentmods.dev/skills/nvidia/nvcf/documentation-style"><img src="https://agentmods.dev/badge/skills/nvidia/nvcf/documentation-style/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/documentation-style"><img src="https://agentmods.dev/badge/skills/nvidia/nvcf/documentation-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 129 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00061 | $0.01147 |
| Opus 5.5 | $0.00024 | $0.00459 |
| Sonnet 5.5 | $0.00012 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
documentation-style 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 2mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation and writing style
Purpose
Keep NVCF documentation plain, consistent, and useful for external readers. Write short docs an agent or contributor can act on without private context. Avoid typographic Unicode that breaks grep and diff tools, and avoid emphasis patterns that make docs noisy.
When to use
- Any new or edited public Markdown in this repo.
AGENTS.md,CLAUDE.md,SKILL.md, READMEs, plans, and guides.- GitHub issue bodies, commit messages, and Pull Request descriptions.
- Existing docs you are changing for another reason.
Instructions
-
No markdown bold for emphasis. Do not use
**...**,__...__, raw HTML<b>, or<strong>. Use headings, lists, andbackticksfor paths, commands, env vars, and identifiers. -
No emojis in documentation or user-facing prose.
-
No em-dash (Unicode U+2014) or en-dash (U+2013). Split the thought into two sentences, or use a comma, semicolon, parenthesis, or colon.
-
ASCII only in committed prose. Avoid smart quotes, ellipsis characters, non-breaking spaces, arrows, and other typographic Unicode. Prefer
->over an arrow glyph and...over a single-character ellipsis. Code blocks and quoted fixtures are exempt. -
Be succinct. Prefer short sentences and direct wording. Cut filler and repetition. Keep one idea per sentence when possible.
-
Prefer lists for short, scan-friendly structure. Use bullets for unordered items and numbered lists when sequence, priority, or stable rule references matter. Use tables only when columns make comparison, status, option tradeoffs, or matrix decisions easier. Do not turn a short list into a table.
-
Be easy to understand. Define acronyms on first use if the audience is broad. Prefer concrete examples over abstract jargon.
-
Write for GitHub readers. Use public names, public paths, and public behavior. Replace private evidence with the user-visible reason for the change.
-
Keep agent guidance actionable. Say when to use a skill, what to inspect first, what command to run, and what done means. Do not add temporary branch status, Pull Request queues, merge-order notes, or private routing details.
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.
- 2mo ago First seen · 146 lines · 61 tokens per session scan A ab14d8486219
documentation-style is a skill published in the GitHub repository NVIDIA/nvcf (251 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,147 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
runpod
Use when running GPU compute on RunPod and deciding between Pods (hourly, always-on) and Serverless (per-second, autoscaling) for training, fine-tuning or inference — serverless endpoints, handler workers, worker Docker templates, network volumes, timeout and worker-count tuning, cold starts, and runaway bills. NOT…
vllm
Use when self-hosting an OpenAI-compatible LLM endpoint with vLLM 0.32 — vllm serve, offline LLM.generate / llm.chat, PagedAttention with continuous batching and prefix caching, --tensor-parallel-size / --pipeline-parallel-size, AWQ/GPTQ/FP8 quantization, or wiring LangChain/LlamaIndex clients at…
tao-setup-nvidia-gpu-host
Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes GPU worker hosts. TAO-wide defaults can be overridden by the selected model's runtime profile. The --check-only path…
mineru
Use when turning PDFs, scans, or Office documents into structured Markdown/JSON for RAG or translation pipelines with MinerU 4.0 — mineru parse / mineru-kit parse, quality tiers flash/basic/standard/advanced, DoclibClient Python SDK, V1 HTTP API, or Docker on NVIDIA GPUs; also when magic-pdf commands fail because 4.0…
tao-run-on-kubernetes
Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for multi-node distributed training. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator installed, or when integrating TAO into an existing…
pdf-brain-ingest
Ingest PDF/Markdown/TXT files into joelclaw's docs memory pipeline with Inngest durability, durable NAS artifacts, and OTEL verification. Use when adding docs, running batch reindex, reconciling coverage, or recovering stuck runs. Triggers on: 'ingest pdf', 'ingest markdown', 'docs add', 'pdf-brain ingest', 'backfill…