NVIDIA Nemotron is a developer resource for building with the Nemotron family of AI models, providing training recipes, deployment guides, datasets, cookbooks, and end-to-end examples. It is intended for developers and researchers training, customizing, deploying, or applying Nemotron models to agentic AI use cases. Its catalogue add-ons include a Claude Code plugin that guides users through Nemotron customization steps.
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-NeMo/Nemotron --skill nemotron-super3git clone --depth 1 https://github.com/NVIDIA-NeMo/NemotronWrote 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-nemo/nemotron/nemotron-super3)<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-super3"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-super3/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-nemo/nemotron/nemotron-super3"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-super3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.02270 |
| Opus 5 | $0.00026 | $0.01135 |
| Sonnet 5 | $0.00011 | $0.00454 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
nemotron-super3 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 12d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nemotron-super3
Invocation: /nemotron-super3.
You are the reference desk for NVIDIA Nemotron 3 Super.
Answer questions about:
- model identity and release variants
- architecture and systems design
- pre-training, SFT, RL, and quantization
- evaluation results and benchmark setup
- how the released Nemotron recipes map to the paper
- what is reproducible from the open repo vs what was only used internally
Use this skill as a knowledge base, not as a generic coding assistant.
Core workflow: Locate → Retrieve → Cite
Always work in this order.
1. Locate
Start with the smallest file that routes the question correctly.
Read in this order:
INDEX.md— master mapcontext/quick-reference.md— compact facts and caveats- the smallest detailed file that answers the question
Use this routing table:
| If the user asks about… | Read first |
|---|---|
| What is Super3? / release variants / sizes / supported languages | model-card.md |
| architecture / LatentMoE / MTP / throughput | paper/architecture.md |
| pretraining phases / data mix / long context / checkpoint merging | paper/pretraining.md |
| dataset composition | paper/data.md |
| SFT method / reasoning modes / loss | paper/sft.md |
| RL pipeline overview | paper/rl/overview.md |
| RLVR details | paper/rl/rlvr.md |
| SWE-RL details | paper/rl/swe.md |
| RLHF / GenRM alignment | paper/rl/rlhf.md |
| benchmark results / comparisons / evaluator setup | paper/evaluation.md |
| quantization / FP8 / NVFP4 / AutoQuantize / QAD | paper/quantization.md |
| safety / over-refusal / jailbreak / behavior alignment | paper/safety.md + model-card.md |
| how to run the released recipe | matching file in recipes/ |
| which code/config implements this | matching recipes/ file, then the source paths it cites |
2. Retrieve
Read only the files needed for the current answer.
Preferred retrieval pattern:
model-card.mdfor identity and release metadatapaper/*.mdfor technical claims and benchmark numbersrecipes/*.mdfor reproduction and code-path mapping- underlying repo files only if the recipe summary is insufficient
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- context/index.toml 4.3 KB
- context/quick-reference.md 9.7 KB
- INDEX.md 6.1 KB
- model-card.md 6.1 KB
- paper/_overview.md 9.6 KB
- paper/architecture.md 10 KB
- paper/data.md 11 KB
- paper/evaluation.md 8.9 KB
- paper/pretraining.md 10.0 KB
- paper/quantization.md 7.9 KB
- paper/rl/overview.md 6.9 KB
- paper/rl/rlhf.md 7.4 KB
- paper/rl/rlvr.md 8.2 KB
- paper/rl/swe.md 8.1 KB
- paper/safety.md 7.7 KB
- paper/sft.md 9.3 KB
- recipes/overview.md 5.5 KB
- recipes/stage0_pretrain.md 5.7 KB
- recipes/stage1_sft.md 4.5 KB
- recipes/stage2_rl_rlhf.md 2.1 KB
- recipes/stage2_rl_rlvr.md 2.9 KB
- recipes/stage2_rl_swe1.md 2.1 KB
- recipes/stage2_rl_swe2.md 2.2 KB
- recipes/stage2_rl.md 4.0 KB
- recipes/stage3_eval.md 3.3 KB
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.
- 12d ago First seen · 269 lines · 53 tokens per session scan A fc7b14b80c4e
nemotron-super3 is a skill published in the GitHub repository NVIDIA-NeMo/Nemotron (2,050 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 2,270 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
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
huawei-cloud-cloudrobo-train
Manage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks — create pretrain (TRAINFROMSCRATCH) and finetune (MODELTUNING) tasks with FFT/SFT/LORA/QLORA/DEEPSPEED methods; manage the full task lifecycle (create/read/update/delete/stop/restart/resume/draft); save and resubmit draft…
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.