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 Seeed-Projects/Seeed-Jetson-DevelopTool --skill vlm-warehouse-guardgit clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolWrote 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/vlm-warehouse-guard)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/vlm-warehouse-guard"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/vlm-warehouse-guard/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/vlm-warehouse-guard"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/vlm-warehouse-guard.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 | $0.00070 | $0.00859 |
| Opus 5 | $0.00035 | $0.00430 |
| Sonnet 5 | $0.00014 | $0.00172 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade D, and why
vlm-warehouse-guard 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 5d 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-get install nvidia-jetpack 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.
curl -fsSL https://ollama.com/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://ollama.com/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VLM Warehouse Guard on reComputer Industrial J4012
Deploy LLaVa via Ollama on a Jetson to monitor warehouse safety using a USB camera. The system controls an RS485 signal light: green for safe, yellow for danger (fire/weapon), red when warehouse lights are off.
Execution model
Run one phase at a time. After each phase:
- Relay all output 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.
Prerequisites
| Requirement | Detail |
|---|---|
| Jetson device | reComputer Industrial J4012 |
| JetPack | 6 (JP6) with CUDA libraries |
| RS485 hardware | RS485 hub, RS485 color-changing light, RS485 light sensor |
| USB camera | Connected to the Jetson |
| Network | Internet access for installing Ollama and cloning repo |
Phase 1 — Initialize system environment (~10 min)
Verify CUDA and install nvidia-jetpack if needed:
sudo apt-get install nvidia-jetpack
Install Ollama:
curl -fsSL https://ollama.com/install.sh | sh
Pull and run the LLaVa model:
ollama run llava-llama3:8b
[OK] when the model responds to a test prompt. [STOP] if Ollama install fails or model download errors out.
Phase 2 — Install project (~5 min)
Install uv package manager:
pip install uv
Clone the project:
git clone https://github.com/Seeed-Projects/VLM-Guard.git
Set up the environment:
cd VLM_Guard
uv sync
source .venv/bin/activate
[OK] when uv sync completes and the venv activates. [STOP] if git clone or uv sync fails.
Phase 3 — Run the project (~1 min)
./start_demo.sh
Open a browser and navigate to http://localhost:5002 to access the application interface.
[OK] when the web interface loads and camera feed is visible. [STOP] if the script errors or the page does not load.
Failure decision tree
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.
- 5d ago First seen · 113 lines · 70 tokens per session scan D cbd680fb75fc
vlm-warehouse-guard is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 859 once invoked, about $0.0003 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 2026-09-03.
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.
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.