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.
/plugin marketplace add NVIDIA-NeMo/Nemotronnpx agentmods add plugins/nvidia-nemo/nemotron/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/plugins/nvidia-nemo/nemotron/nemotron-customize)<a href="https://agentmods.dev/plugins/nvidia-nemo/nemotron/nemotron-customize"><img src="https://agentmods.dev/badge/plugins/nvidia-nemo/nemotron/nemotron-customize.svg" alt="Measured on agentmods" height="20"></a>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 4d 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.
What it actually says
{
"name": "nemotron-customize",
"description": "Plan and configure repo-native Nemotron customization workflows from existing steps: curate/nemo_curator JSONL cleaning, translate/nemo_curator corpus translation, sft/automodel, peft/automodel, sft/megatron_bridge, peft/megatron_bridge, pretrain/CPT, rl/nemo_rl alignment, byob/mcq benchmarks, convert/megatron_to_hf and other checkpoint conversion, optimize/modelopt, eval/model_eval, env/env_toml profiles, and end-to-end pipelines.",
"version": "0.1.1",
"author": {
"name": "NVIDIA Nemotron Team"
},
"homepage": "https://github.com/NVIDIA/Nemotron",
"skills": ["./"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 159 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 4d ago First seen · 11 lines scan A 0a59e24515b0
nemotron-customize is a plugin published in the GitHub repository NVIDIA-NeMo/Nemotron (2,012 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
mjswan
Skills for mjswan: build, port and ship MuJoCo scenes as browser apps.
training-hub
LLM post-training — unified interface for SFT, OSFT, LoRA fine-tuning, and GRPO reinforcement learning.
vmware-privateai
VMware Private AI (NVIDIA): GPU inventory, vGPU profiles, utilization, model serving — 17 tools.
unsloth-buddy
Fine-tune LLMs end-to-end: env setup, LoRA training (SFT/DPO/GRPO/vision), evaluation, and export. Works on NVIDIA GPUs and Apple Silicon.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.