SharpAI/DeepCamera is an open-source camera platform that analyzes surveillance video locally with vision-language models, object detection, and related AI skills. It is for home and CCTV monitoring, and its catalogue skills add pluggable camera capabilities to the platform.
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 SharpAI/DeepCamera --skill yolo-detection-2026git clone --depth 1 https://github.com/SharpAI/DeepCameraWrote 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/sharpai/deepcamera/yolo-detection-2026)<a href="https://agentmods.dev/skills/sharpai/deepcamera/yolo-detection-2026"><img src="https://agentmods.dev/badge/skills/sharpai/deepcamera/yolo-detection-2026/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/sharpai/deepcamera/yolo-detection-2026"><img src="https://agentmods.dev/badge/skills/sharpai/deepcamera/yolo-detection-2026.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.01769 |
| Opus 5.5 | $0.00009 | $0.00708 |
| Sonnet 5.5 | $0.00004 | $0.00354 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
yolo-detection-2026 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YOLO 2026 Object Detection
Real-time object detection using the latest YOLO 2026 models. Detects 80+ COCO object classes including people, vehicles, animals, and everyday objects. Outputs bounding boxes with labels and confidence scores.
Model Sizes
| Size | Speed | Accuracy | Best For |
|---|---|---|---|
| nano | Fastest | Good | Real-time on CPU, edge devices |
| small | Fast | Better | Balanced speed/accuracy |
| medium | Moderate | High | Accuracy-focused deployments |
| large | Slower | Highest | Maximum detection quality |
Hardware Acceleration
The skill uses env_config.py to automatically detect hardware and convert the model to the fastest format for your platform. Conversion happens once during deployment and is cached.
| Platform | Backend | Optimized Format | Compute Units | Expected Speedup |
|---|---|---|---|---|
| NVIDIA GPU | CUDA | TensorRT .engine |
GPU | ~3-5x |
| Apple Silicon (M1+) | MPS | CoreML .mlpackage |
Neural Engine (NPU) | ~2x |
| Intel CPU/GPU/NPU | OpenVINO | OpenVINO IR .xml |
CPU/GPU/NPU | ~2-3x |
| AMD GPU | ROCm | ONNX Runtime | GPU | ~1.5-2x |
| CPU (any) | CPU | ONNX Runtime | CPU | ~1.5x |
Apple Silicon Note: Detection defaults to
cpu_and_ne(CPU + Neural Engine), keeping the GPU free for LLM/VLM inference. Setcompute_units: allto include GPU if not running local LLM.
How It Works
deploy.shdetects your hardware viaenv_config.HardwareEnv.detect()- Installs the matching
requirements_{backend}.txt(e.g. CUDA → includestensorrt) - Pre-converts the default model to the optimal format
- At runtime,
detect.pyloads the cached optimized model automatically - Falls back to PyTorch if optimization fails
Set use_optimized: false to disable auto-conversion and use raw PyTorch.
Auto Start
Set auto_start: true in the skill config to start detection automatically when Aegis launches. The skill will begin processing frames from the selected camera immediately.
What ships with it
13 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.
- config.yaml 2.0 KB
- deploy.bat 9.3 KB runs code
- deploy.sh 9.7 KB runs code
- requirements_cpu.txt 266 B
- requirements_cuda.txt 273 B
- requirements_intel.txt 228 B
- requirements_mps.txt 327 B
- requirements_rocm.txt 479 B
- requirements.txt 420 B
- scripts/detect.py 14 KB runs code
- scripts/env_config.py 37 KB runs code
- yolo26n_names.json 1.5 KB
- yolo26n.onnx 9659 KB
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.
- 1mo ago First seen · 187 lines · 22 tokens per session scan A 3e074ce90a54
yolo-detection-2026 is a skill published in the GitHub repository SharpAI/DeepCamera (3,105 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,769 once invoked, about $0.0001 per session on Opus 5.5. 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
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
perforatedai
Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration), 'load my perforated model for inference' (deploy trained models), 'export my perforated model'…
perforatedai-analyze
Analyze PerforatedAI training results and provide optimization recommendations. Trigger: 'Analyze my perforated results' (after training completes). Reviews CSV outputs, identifies performance patterns, recommends configuration improvements. For initial setup or debugging, use the perforatedai skill instead.
perforatedai-distributed
Multi-GPU setup for PerforatedAI with DataParallel or DistributedDataParallel (DDP). Invoked automatically by the perforatedai skill when multi-GPU training is detected. Handles initialization workflow, checkpoint loading, rank 0 handling, and shell script generation for DDP.
perforatedai-libraries-transformers
HuggingFace Transformers integration for PerforatedAI. Handles the Trainer-specific differences: usingperforatedai=True, GPA.metric, evalstrategy. Use when the user's script uses HuggingFace Trainer.