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/local-chatbot-multimodalWrote 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/local-chatbot-multimodal)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/local-chatbot-multimodal"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/local-chatbot-multimodal.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 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 Rogue Agent · line 68 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 69 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Privilege Escalation · line 102 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 113 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 119 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 120 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 165 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 | $0.00076 | $0.01313 |
| Opus 5 | $0.00038 | $0.00656 |
| Sonnet 5 | $0.00015 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade B, and why
local-chatbot-multimodal 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 tee /etc/docker/daemon.json > /dev/null << 'EOF' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:11434/api/tags Copies of this mod
1 near-identical copy found in the catalogue:
- local-chatbot-physical — 88% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice-Interactive Chatbot on Jetson (Multimodal)
Deploy a fully local voice chatbot that listens, thinks, and talks back. Combines NVIDIA Riva for speech recognition and synthesis with Ollama for local LLM inference. Everything runs in Docker containers on Jetson — no cloud required.
Execution model
Run one phase at a time. After each phase:
- Relay all output to the user.
- If output contains
[STOP]→ stop, consult the failure decision tree. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed.
Prerequisites
| Requirement | Detail |
|---|---|
| Hardware | NVIDIA Jetson (AGX Orin recommended for larger models) |
| JetPack | 6.0+ |
| Docker | Installed with NVIDIA runtime |
| NGC Account | API key from catalog.ngc.nvidia.com |
| Audio | Microphone and speaker connected to Jetson |
Phase 1 — Install Jetson Containers and Ollama (~5 min)
git clone https://github.com/dusty-nv/jetson-containers
bash jetson-containers/install.sh
Run Ollama and pull a model:
jetson-containers run --name ollama $(autotag ollama)
Inside the container:
ollama run llama3.2:1b
Type /bye to exit after confirming the model loads.
Verify from host:
curl http://localhost:11434/api/tags
[OK] when curl returns JSON listing the model.
[STOP] if Ollama container fails to start — check Docker and NVIDIA runtime.
Phase 2 — Install and configure NGC CLI (~3 min)
mkdir -p ~/ngc_setup && cd ~/ngc_setup
wget --content-disposition https://api.ngc.nvidia.com/v2/resources/nvidia/ngc-apps/ngc_cli/versions/3.36.0/files/ngccli_arm64.zip
unzip ngccli_arm64.zip
chmod u+x ngc-cli/ngc
echo "export PATH=\"\$PATH:$(pwd)/ngc-cli\"" >> ~/.bash_profile
source ~/.bash_profile
ngc config set
Enter your NGC API key when prompted.
[OK] when ngc config current shows your org/team.
[STOP] if API key is rejected — regenerate at catalog.ngc.nvidia.com.
Phase 3 — Install NVIDIA Riva (~15–30 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.
- 8d ago First seen · 172 lines · 76 tokens per session scan B 0863134855c5
local-chatbot-multimodal is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,313 once invoked, about $0.0004 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.