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 archetypeai/agent-skills --skill atai-newton-omega-nvidia-nemotrongit clone --depth 1 https://github.com/archetypeai/agent-skillsWrote 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/archetypeai/agent-skills/atai-newton-omega-nvidia-nemotron)<a href="https://agentmods.dev/skills/archetypeai/agent-skills/atai-newton-omega-nvidia-nemotron"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-newton-omega-nvidia-nemotron/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/archetypeai/agent-skills/atai-newton-omega-nvidia-nemotron"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-newton-omega-nvidia-nemotron.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 | $0.00228 | $0.03399 |
| Opus 5.5 | $0.00091 | $0.01360 |
| Sonnet 5.5 | $0.00046 | $0.00680 |
| Haiku 4.5 | $0.00023 | $0.00340 |
Grade A, and why
atai-newton-omega-nvidia-nemotron 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Newton Omega × NVIDIA Nemotron — Omega senses, Nemotron explains
Omega turns sensor windows into embeddings; a client-side KNN turns those into a verdict (healthy / fault, normal / attack, …). That verdict is accurate but mute. This skill adds NVIDIA Nemotron as the explanation layer: when Omega flags something, Nemotron reads the verdict and plain window statistics and writes what an operator needs — what changed, the likely cause, what to check.
sensor window ──► scale ──► Omega /query (one per channel) ──► KNN vs n-shot library ──► verdict + votes
│
window stats (+ healthy baseline or peer) ─────────────────────────┤
▼
NVIDIA Nemotron (chat/completions, JSON only)
│
validate ──► cache ──► UI
When to Apply
- An Omega + KNN pipeline already produces verdicts and you want operator-facing text: fault briefs, suggested actions, alert summaries.
- The user specifically wants NVIDIA Nemotron (hosted on build.nvidia.com) as the reasoning model.
Do not use this skill when:
- You need the Omega call, windowing or the KNN library — that's
atai-newton-omega-model(andatai-newton-omega-model-data-prepbefore it). This skill assumes those work. - You want Newton's own reasoning model on
/query— that'satai-newton-fusion-model.
The split: what Nemotron sees
Never send embeddings to Nemotron. A 768-d vector means nothing to a language model. Send what Omega and KNN concluded, plus numbers a person could read off a dashboard:
What ships with it
10 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.
- references/_common.py 13 KB runs code
- references/.env.example 518 B
- references/check_nemotron.py 3.9 KB runs code
- references/explain_knn.py 4.8 KB runs code
- references/requirements.txt 195 B
- references/sample_data/bearing_degraded.csv 70 KB
- references/sample_data/bearing_healthy.csv 69 KB
- references/sample_data/bearing_incoming.csv 18 KB
- references/sample_data/README.md 1.8 KB
- tests/test_references.py 9.1 KB runs code
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.
- 9d ago First seen · 194 lines · 228 tokens per session scan A 53aee08a1c80
atai-newton-omega-nvidia-nemotron is a skill published in the GitHub repository archetypeai/agent-skills (6 stars, last pushed today), licensed Apache-2.0. It adds 228 tokens to every session and 3,399 once invoked, about $0.0009 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 2026-10-08.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
deepstream-import-vision-model
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.