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-customizegit 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-customize)<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-customize"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-customize/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-customize"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-customize.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 | $0.00159 | $0.03865 |
| Opus 5 | $0.00079 | $0.01932 |
| Sonnet 5 | $0.00032 | $0.00773 |
| Haiku 4.5 | $0.00016 | $0.00386 |
Grade A, and why
nemotron-customize 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 10d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nemotron-customize
IMPORTANT: Read this file before answering any nemotron-customize,
Nemotron customization, Curator curation, translation, SFT, PEFT, RL,
conversion, optimization, checkpoint or existing/hosted-endpoint evaluation, or
multi-step pipeline request. This applies whether the user names one step or
asks you to compose several steps into a pipeline.
Evaluation requests count even when no training is involved: "evaluate",
"benchmark", "smoke test", or "score" an existing/hosted endpoint, an API/model
ID, or a deployed model all route to eval/model_eval. Read this skill for
those too.
Purpose
Turn a model-customization request into a repo-native Nemotron step pipeline. Plan the DAG, validate artifact wiring, and create only the YAML/config files needed to run existing steps.
Use this skill only for inspecting, configuring, validating, running, or submitting existing Nemotron steps or multi-step training/customization pipelines. For frontend, dashboard, visualization, generic ML advice, billing/access, or unrelated coding tasks, stop with a short scope note and do not inspect the step catalog or edit files in that turn.
Prerequisites
- A checkout of the Nemotron repo with
src/nemotron/steps/present; run from the repo root. uvavailable to invokeuv run nemotron steps ....- For remote execution: an env profile TOML (
NEMOTRON_ENV_FILEorenv*.toml) with a section matching the selected step. - For hosted services (translation, hosted eval): the auth environment variable
expected by the step (for example
NVIDIA_API_KEY), exported in the environment — never inlined or committed. - User-provided concrete values (model/checkpoint, data paths, output dir, hardware/GPU count) before any command is presented as runnable.
Limitations
- Does not invent new catalog steps. When no existing step, runner, recipe, CLI, or config can satisfy the request, it names the gap (Explorer mode) instead of fabricating a step.
- Produces YAML/config for existing steps; new Python/shell is out of scope except in Explorer mode after the gap is approved.
- Not for deployment-only/serving, frontend, dashboards, generic ML advice, or non-Nemotron tasks.
- Does not guess concrete values (paths, model IDs, GPU counts, profiles); it
asks or returns
Blockedwhen they are missing.
What ships with it
34 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.
- .claude-plugin/plugin.json 639 B
- BENCHMARK.md 3.7 KB
- evals/evals.json 9.7 KB
- references/act/PROJECT.md 7.2 KB
- references/act/STAGE.md 8.9 KB
- references/ARTIFACTS.md 4.8 KB
- references/CATALOG.md 13 KB
- references/COMMANDS.md 9.3 KB
- references/context/automodel-launcher-executor-modes.txt 2.4 KB
- references/context/automodel-pretrain.txt 6.0 KB
- references/context/automodel-sft-peft-core.txt 2.1 KB
- references/context/byob-benchmark-curator-translation.txt 4.9 KB
- references/context/checkpoint-conversion.txt 1.8 KB
- references/context/curator-data-acquisition.txt 2.3 KB
- references/context/curator-processing-language-quality.txt 1.7 KB
- references/context/curator-translation-faith.txt 4.8 KB
- references/context/data-designer-sdg.txt 4.6 KB
- references/context/eval-deploy-formats.txt 1.7 KB
- references/context/eval-sovereign-benchmarks.txt 2.0 KB
- references/context/eval-standard-nlu.txt 1.7 KB
- references/context/index.toml 7.4 KB
- references/context/mbridge-parallelism-performance.txt 2.0 KB
- references/context/mbridge-pretrain.txt 1.8 KB
- references/context/mbridge-sft.txt 1.8 KB
- references/context/modelopt-optimization.txt 8.3 KB
- references/context/nemo-rl-alignment.txt 5.7 KB
- references/context/nemotron-data-prep.txt 6.1 KB
- references/context/README.md 1.6 KB
- references/examples/CALIBRATION.md 2.5 KB
- references/HARDWARE.md 3.1 KB
- references/PATTERNS.md 4.0 KB
- references/WORKFLOW.md 5.2 KB
- skill-card.md 4.1 KB
- skill.oms.sig 12 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.
- 10d ago First seen · 323 lines · 159 tokens per session scan A 985a97bb839e
nemotron-customize is a skill published in the GitHub repository NVIDIA-NeMo/Nemotron (2,034 stars, last pushed 2d ago), licensed Apache-2.0. It adds 159 tokens to every session and 3,865 once invoked, about $0.0008 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.
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.
model_finetuning
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.