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 agentmods add skills/seeed-projects/seeed-jetson-developtool/deploy-efficient-vision-enginenpx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill deploy-efficient-vision-enginegit clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolWhat 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 | $0.00044 | $0.00338 |
| Opus 5 | $0.00022 | $0.00169 |
| Sonnet 5 | $0.00009 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
deploy-efficient-vision-engine 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 3d 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
Efficient Multi-Task Vision Inference Engine Deployment on Jetson
Execution model
- Confirm board model and JetPack/L4T version before applying commands.
- Read
references/source.body.mdfirst to extract prerequisites and command order. - Execute steps in smallest reproducible sequence and record command outputs.
- Validate final expected results and keep rollback notes.
Source
- Original markdown:
/home/darklee/tmp/jetson-develop/refer-参考完后会清除/Application/Computer_Vision/Efficient_Multi-Task_Vision_Inference_Engine_Deployment_on_Jetson.md - Scope:
application(Computer_Vision)
Topic summary
Visual Perception Engine is a cutting-edge framework that revolutionizes robotic perception by eliminating redundant computations through shared backbone networks. Unlike traditional approaches where each
Key sections
- Introduction
- Prerequisites
- Technical Highlights
- Environment Setup
- Performance Testing
- Real-time camera input for inference
- Other Applications
- Resources
- Tech Support & Product Discussion
Reference files
references/source.mdreferences/source.body.md
Agent instruction
- Do not skip prerequisite checks.
- If command output differs from expected behavior, pause and ask user before destructive steps.
- Prefer reversible changes and include verification commands.
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.
- 3d ago First seen · 40 lines · 44 tokens per session scan A 5787e1c44b9d
deploy-efficient-vision-engine is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 338 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
nemo-mbridge-perf-memory-tuning
Techniques for reducing peak GPU memory in Megatron Bridge, including expandable segments, PEFT plus sequence-parallel input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes. Use for GPU OOMs, inadequate memory headroom, LoRA or PEFT activation pressure, memory…
nemo-mbridge-perf-moe-hardware-configs
Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
dstack-presets
Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.
KernelWiki
Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete PR references from…
homeassistant-bridge
Bidirectional Home Assistant integration — HA cameras in, detection results out.