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 frankxai/claude-skills-library --skill partner-nvidiagit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/partner-nvidia)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/partner-nvidia"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/partner-nvidia/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/frankxai/claude-skills-library/partner-nvidia"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/partner-nvidia.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 | $0.00077 | $0.01943 |
| Opus 5.5 | $0.00031 | $0.00777 |
| Sonnet 5.5 | $0.00015 | $0.00389 |
| Haiku 4.5 | $0.00008 | $0.00194 |
Grade A, and why
partner-nvidia 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NVIDIA — Partner Intelligence
Current state (as of 2026-05-17)
NIM microservices (NVIDIA Inference Microservices) are the default inference layer for the NVIDIA AI Enterprise stack — containerized, GPU-optimized, multi-cloud-deployable. NeMo continues to anchor the LLM build + finetune surface. DGX Cloud (managed GPU clusters via cloud partners — Oracle, AWS, Azure, GCP) is the enterprise-tier compute lane. The Oracle × NVIDIA AI accelerator pack wave is moving through EMEA channel right now, with Arrow ECS Germany as a primary distribution surface. NVIDIA Inception (startup program) operates a nominee pathway — entry typically through a corporate or VC nomination (to verify current rev). Munich EBC (Executive Briefing Center) is active for partner-event work.
Product map
- NIM (NVIDIA Inference Microservices) — containerized inference for production LLMs and multimodal models. GPU-optimized, multi-cloud-deployable, OpenAI-compatible API surface.
- NeMo — framework + microservices for LLM build, finetune, retrieval, and guardrails. Includes NeMo Curator, NeMo Customizer, NeMo Evaluator, NeMo Guardrails, NeMo Retriever.
- NVIDIA AI Enterprise — the licensed enterprise stack. NIM + NeMo + AI Workbench + management + support, deployable on certified infrastructure or DGX Cloud.
- DGX Cloud — managed GPU clusters delivered through cloud partners (Oracle, AWS, Azure, GCP).
- AI Workbench — local + cloud GPU development environment.
- NVIDIA Blueprints — opinionated reference architectures (RAG, video search, drug discovery, virtual screening, etc.).
- CUDA / cuDNN / TensorRT / TensorRT-LLM — the silicon-layer SDKs.
- NVIDIA Inception — startup program. Free tier of credits + technical resources + go-to-market visibility. Nominee pathway. (Entry criteria to verify against current program page.)
- Partner Network (NPN) — channel + technology partner tiers for resellers, distributors, OEMs, ISVs.
- Munich EBC — Executive Briefing Center for European partner work.
- Open-source artifacts — NeMo (Apache 2.0), TensorRT-LLM (Apache 2.0), CUDA-Q (Apache 2.0), many reference blueprints.
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.
- 1mo ago First seen · 80 lines · 77 tokens per session scan A 576d4ef7e817
partner-nvidia is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 1,943 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
fetch-llm-apps
Regenerate the ranked GitHub LLM applications pool (section/xllmapps.md) with fetchllmapps.py. USE FOR: refreshing the pool linked from applications.md. DO NOT USE FOR: hand-curating entries in applications.md or adding star badges to the generated file.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Prompt engineering regression test matrix register: baseline outputs, semantic drift thresholds, judge evaluations, and golden dataset.
prompt-refiner
Lints an existing user-supplied prompt for prompt-engineering defects and prompt-injection risks. Produces a diagnostic report with rule IDs, severity, line/column, quoted evidence, rationale, and optional JSON output. Does not rewrite prompts or impose prompt frameworks.
prompt-modeler
Generate structured strategic prompts with diagnostic and multiple options. Triggers on: /modelar-prompt.
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…