nemotron-add-pattern

nemotron-add-pattern is a skill for Claude Code, Codex from NVIDIA-NeMo/Nemotron. It costs 58 tokens per session (1,399 once invoked), scanned A, original, Apache-2.0.

A contributor workflow for adding a reusable machine-learning decision pattern to a project’s pattern catalogue.

In plain words
What is it for?
Use it to add patterns such as tokenizer locking, evaluation bookends, or choosing LoRA for small datasets. You must provide the topic, triggers, affected steps, confidence level, and whether it is new or existing knowledge.
Why use it?
It helps encode recurring guidance consistently, with the correct metadata, catalogue entry, and tests.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is I’ll mark it `high` confidence only if the guidance is already established team practice, regenerate `PATTERNS.md` with `uv run python src/nemotron/steps/index..

Good fit Use it to add patterns such as tokenizer locking, evaluation bookends, or choosing LoRA for small datasets. You must provide the topic, triggers, affected steps, confidence level, and whether it is new or existing knowledge.

Compare 6 skills from other repositories ↓
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 · 2,032 stars · on GitHub · docs.nvidia.com

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Nemotron
agentmods
npx agentmods add skills/nvidia-nemo/nemotron/nemotron-add-pattern

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-pattern

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-nemo/nemotron/nemotron-add-pattern"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/nemotron/nemotron-add-pattern.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 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 $0.00058 $0.01399
Opus 5 $0.00029 $0.00700
Sonnet 5 $0.00012 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured 9d ago against content hash f9b39404a40a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nemotron-add-pattern 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 9d 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-pattern/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nemotron-add-pattern

Invocation: /nemotron-add-pattern.

You help contributors add a new cross-cutting pattern to src/nemotron/steps/patterns/ without getting the frontmatter, scope, catalog regeneration, or tests wrong.

Tone

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

  • Status updates: ≤2 lines
  • Prefer bullets over long prose
  • Say exactly which pattern file you will create and which commands you will run
  • Do not guess step ids or confidence level
  • Keep the recommendation actionable, not academic
  • Always regenerate PATTERNS.md and run tests

Workflow

Four phases. Always in this order.

1. Orient

Read these first:

  • src/nemotron/steps/patterns/sft-small-dataset-prefer-lora.md
  • src/nemotron/steps/PATTERNS.md
  • src/nemotron/steps/index.py
  • tests/steps/test_patterns.py

Then ask the contributor:

  1. What is the pattern about? (one sentence)
  2. When should it apply? (natural-language triggers)
  3. Which steps does it touch? (step ids, or [] for global)
  4. What is the confidence level? (high, medium, or experimental)
  5. Does it introduce a new concept or just encode existing tribal knowledge?

Use these repo conventions:

  • Pattern files live at src/nemotron/steps/patterns/{id}.md.
  • The filename stem must match the frontmatter id.
  • Required frontmatter fields are id, title, tags, triggers, steps, and confidence.
  • steps: [] is valid for a global pattern.
  • Valid confidence values are high, medium, and experimental.
  • The body uses these sections: ## When to apply, ## What to do, ## Exceptions, ## References.
  • Step-strategy cross-links in step.toml are a separate task. Do not edit them here.

2. Generate

Create:

  • src/nemotron/steps/patterns/{id}.md

The pattern file must contain:

  • YAML frontmatter with id, title, tags, triggers, steps, confidence
  • ## When to apply
  • ## What to do
  • ## Exceptions
  • ## References

Generation rules:

  1. Keep the pattern id kebab-case and make it match the filename exactly.
  2. Turn vague triggers into 2–4 concrete, observable conditions.
  3. Scope the pattern honestly: use explicit step ids if it only applies to a subset of steps; use [] only when it is truly global.
  4. Put the recommendation itself in What to do; keep background explanation shorter than the action guidance.
  5. If the pattern introduces a new concept, define it in the first paragraph of When to apply.
  6. Do not modify existing patterns.
  7. Regenerate the catalog with:
    • uv run python src/nemotron/steps/index.py
  8. Run validations with:
    • uv run pytest tests/steps -q

Read the full file on GitHub · 153 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. 9d ago First seen · 153 lines · 58 tokens per session scan A f9b39404a40a

Subscribe to this mod's changes

nemotron-add-pattern is a skill published in the GitHub repository NVIDIA-NeMo/Nemotron (2,032 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,399 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

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

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.

vuralserhat86/antigravity-agentic-skills · 67 tokens