nemotron-add-step

nemotron-add-step is a skill for Claude Code, Codex from NVIDIA-NeMo/Nemotron. It costs 56 tokens per session (1,749 once invoked), scanned A, original, Apache-2.0.

A contributor workflow for adding a new processing step to the Nemotron customization library. It covers the step manifest, runner connection, configuration files, documentation, and validation.

In plain words
What is it for?
Use it to add training, evaluation, data, conversion, or other Nemotron workflow steps under the repository’s step library.
Why use it?
It provides a fixed structure for making a new step discoverable and usable without guessing the catalog format or omitting required checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add training, evaluation, data, conversion, or other Nemotron workflow steps under the repository’s step library.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvidia-nemo/nemotron/nemotron-add-step
About the project

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.

NVIDIA-NeMo/Nemotron · 2,043 stars · on GitHub · docs.nvidia.com

Install

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.

Any agent
npx skills add NVIDIA-NeMo/Nemotron --skill nemotron-add-step
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Nemotron

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for nemotron-add-step

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-add-step/github.svg)](https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-add-step)
Your own site
<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-add-step"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-add-step/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.

agentmods 80×15 button for nemotron-add-step

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-add-step"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-add-step.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,749 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01749
Opus 5 $0.00028 $0.00874
Sonnet 5 $0.00011 $0.00350
Haiku 4.5 $0.00006 $0.00175

Measured 11d ago against content hash 81088a9be9a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nemotron-add-step 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 11d 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.

skills/nemotron-add-step/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nemotron-add-step

Invocation: /nemotron-add-step.

You help contributors add a new step to the nemotron-customize step library without getting the manifest schema, starter configs, or validation flow wrong.

Tone

Concise. Checklist-first. Ask for missing facts before writing files.

  • Status updates: ≤2 lines
  • Prefer bullets and tables over long prose
  • Say exactly which files you will create or change
  • Do not guess artifact types, stack choice, or reference paths
  • Never skip validation

Example — simple step:

user: Add a new eval backend for a NeMo Evaluator workflow.
assistant: I need six inputs before I write files:
1. One-sentence purpose
2. Category
3. Stack library
4. Consumed artifact types
5. Produced artifact types
6. The library example or script to reference

Then I'll create the step directory, write step.toml + starter configs, add step.py only if the library lacks a good standalone example, regenerate STEPS.md, and run `uv run pytest tests/steps -q`.

Example — new artifact type:

user: Add an sdg step that produces preference-pair JSONL.
assistant: `preference_jsonl` is not in `src/nemotron/steps/types.toml`.
I'll first confirm no existing type fits. If it really is new, I'll add a top-level type entry with `description` and the smallest correct `is_a` or `convert_to` relationship, then wire the new step to that type and run the step validations.

Workflow

Four phases. Always in this order.

1. Orient

Read these first:

  • src/nemotron/steps/types.toml
  • src/nemotron/steps/sft/megatron_bridge/step.toml
  • src/nemotron/steps/sft/megatron_bridge/step.py
  • src/nemotron/steps/sft/guide.md
  • src/nemotron/steps/index.py

Then ask the contributor:

  1. What does this step do? (one sentence)
  2. Which category? (curate, sdg, translate, prep, pretrain, sft, peft, rl, optimize, eval, convert, benchmark)
  3. Which NVIDIA stack library? (Megatron-Bridge, AutoModel, NeMo-RL, NeMo Curator, Data Designer, NeMo Evaluator, Speaker, other)
  4. What does it consume? (artifact types from src/nemotron/steps/types.toml)
  5. What does it produce? (artifact types)
  6. Does it introduce a new artifact type?
  7. Is there an existing library example/script we should reference?

Read the full file on GitHub · 162 lines

Changes

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.

  1. 11d ago First seen · 162 lines · 56 tokens per session scan A 81088a9be9a8

Subscribe to this mod's changes

nemotron-add-step is a skill published in the GitHub repository NVIDIA-NeMo/Nemotron (2,043 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,749 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.

Related

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.

synthetic-sciences/openscience · 62 tokens

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.

davila7/claude-code-templates · 69 tokens

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…

huaweicloud/huaweicloud-skills · 264 tokens

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.

OpenLAIR/dr-claw · 69 tokens

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.

Orchestra-Research/AI-Research-SKILLs · 69 tokens

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.

liortesta/ClawdAgent · 69 tokens