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/gpt-oss-liveWrote 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/gpt-oss-live)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/gpt-oss-live"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/gpt-oss-live.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 39 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 40 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00062 | $0.01268 |
| Opus 5 | $0.00031 | $0.00634 |
| Sonnet 5 | $0.00012 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade B, and why
gpt-oss-live scanned grade B with 2 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 8d 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 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT-OSS-20B on Jetson Orin
Runs OpenAI's GPT-OSS-20B open-weight model on a Jetson Orin device using llama.cpp compiled with CUDA support. The model is converted from HuggingFace format to GGUF and quantized to Q4_K for on-device inference. An optional OpenWebUI frontend is included.
Hardware: reComputer Super J4012 or other Jetson Orin Prerequisites: JetPack 6.x, Miniconda installed, ~40GB free disk space
Execution model
Run one phase at a time. After each phase:
- Relay all output lines to the user.
- If output contains
[STOP]→ stop immediately, consult the failure decision tree. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed to the next phase.
Phase 1 — deps (~5 min)
Install Miniconda (skip if already installed) and system build dependencies.
# Only if Miniconda is not yet installed:
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh
chmod +x Miniconda3-latest-Linux-aarch64.sh
./Miniconda3-latest-Linux-aarch64.sh
source ~/.bashrc
sudo apt update
sudo apt install -y build-essential cmake git
Expected: cmake --version and gcc --version both return successfully. [OK]
Phase 2 — build (~2 hours)
Clone and build llama.cpp with CUDA enabled. This step is long — expect roughly 2 hours on Jetson Orin. Do not interrupt the build.
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --parallel
Expected: ./build/bin/llama-cli --version prints a version string. [OK]
Phase 3 — model (varies)
Download the GPT-OSS-20B weights from HuggingFace, upload to Jetson, then convert and quantize.
- Download from: https://huggingface.co/openai/gpt-oss-20b/tree/main
- Transfer the downloaded model directory to the Jetson (e.g. via
scpor USB drive). - Create the conda environment and convert to GGUF:
conda create -n gpt-oss python=3.10
conda activate gpt-oss
cd llama.cpp
pip install .
python convert_hf_to_gguf.py --outfile <path_of_output> <path_of_input_model>
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.
- 8d ago First seen · 135 lines · 62 tokens per session scan B b9f7eab9abd4
gpt-oss-live is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,268 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, 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.
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.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.