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.
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolnpx agentmods add skills/seeed-projects/seeed-jetson-developtool/gr00t-n1-6-deploy-agxWrote 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/seeed-projects/seeed-jetson-developtool/gr00t-n1-6-deploy-agx)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/gr00t-n1-6-deploy-agx"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/gr00t-n1-6-deploy-agx/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/seeed-projects/seeed-jetson-developtool/gr00t-n1-6-deploy-agx"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/gr00t-n1-6-deploy-agx.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 | $0.00094 | $0.02200 |
| Opus 5 | $0.00047 | $0.01100 |
| Sonnet 5 | $0.00019 | $0.00440 |
| Haiku 4.5 | $0.00009 | $0.00220 |
Grade D, and why
gr00t-n1-6-deploy-agx scanned grade D with 3 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install ffmpeg Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `uv` not found | Install with `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh`. | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `uv` not found | Install with `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh`. | How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fine-tune GR00T N1.6 for LeRobot SO-101 Arm and Deploy on AGX Orin
Execution model
Run one phase at a time. After each phase:
- Relay all command output to the user.
- If output contains
[STOP]→ stop immediately, consult the failure decision tree below. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed to the next phase.
Prerequisites
| Requirement | Details |
|---|---|
| Inference device | AGX Orin 64G with JetPack 6.2 |
| Robot arm | LeRobot SO-101 (leader + follower) |
| Cameras | 2× USB cameras (named wrist and front) |
| Fine-tuning server | GPU with ≥48GB VRAM (L20 recommended, server rental OK) |
| Tools | uv package manager, Python 3.10 |
Phase 1 — Set up GR00T N1.6 environment on AGX Orin (~15–30 min)
Clone and checkout the specific commit:
git clone https://github.com/NVIDIA/Isaac-GR00T.git
cd Isaac-GR00T
git checkout d483f00b1c13116bda020bead9d16dca497b2f6d
git submodule update --init --recursive
Create virtual environment and install LeRobot dependencies:
uv venv .venv --python python3.10
source .venv/bin/activate
cd gr00t/eval/real_robot/SO100
uv pip install -e . --verbose
uv pip install --no-deps -e ../../../../
Download pre-compiled .whl files for AGX Orin (PyTorch, TorchVision, Flash-Attention, TorchCodec, Triton) from links in references/source.body.md. More wheels at https://pypi.jetson-ai-lab.io/jp6/cu126
Install wheels (flash-attn and torchvision must be installed AFTER pytorch):
source .venv/bin/activate
pip install torch-*.whl
pip install flash_attn-*.whl torchvision-*.whl torchcodec-*.whl triton-*.whl
Complete final dependency installation:
cd Isaac-GR00T
source .venv/bin/activate
pip install -e .[base]
sudo apt update && sudo apt install ffmpeg
[OK] when python -c "import torch; print(torch.cuda.is_available())" returns True.
Phase 2 — Set up environment on fine-tuning server (~10–20 min)
What ships with it
2 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.
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.
- 12d ago First seen · 235 lines · 94 tokens per session scan D 6e5ee1839226
gr00t-n1-6-deploy-agx is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (55 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,200 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
minicpm5-deploy-vllm-ascend
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
minicpm5-deploy-litert
Run MiniCPM5-2B or MiniCPM5-1B on-device with Google's LiteRT-LM runtime — the litert-lm CLI or its OpenAI-compatible server on a desktop, the Kotlin API or the AI Edge Gallery app on Android, the same .litertlm bundle on CPU or GPU. Use when the user says "LiteRT", "LiteRT-LM", "litertlm", ".litertlm", "Android"…