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 home-security-benchmarkgit 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/home-security-benchmark)<a href="https://agentmods.dev/skills/sharpai/deepcamera/home-security-benchmark"><img src="https://agentmods.dev/badge/skills/sharpai/deepcamera/home-security-benchmark/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/home-security-benchmark"><img src="https://agentmods.dev/badge/skills/sharpai/deepcamera/home-security-benchmark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Data Exfiltration · line 65 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.
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 | $0.00017 | $0.01566 |
| Opus 5.5 | $0.00007 | $0.00626 |
| Sonnet 5.5 | $0.00003 | $0.00313 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
Home Security AI Benchmark 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Security AI Benchmark
Comprehensive benchmark suite evaluating LLM and VLM models on 143 tests across 16 suites — context preprocessing, tool use, security classification, prompt injection resistance, alert routing, knowledge injection, VLM-to-alert triage, and scene analysis.
Setup
Requires npm install. This skill has a package.json with dependencies (e.g. openai SDK). The deployment agent should check for package.json and run npm install in the skill directory before launching.
Entry script: scripts/run-benchmark.cjs
Verification
node scripts/run-benchmark.cjs --help
Quick Start
As an Aegis Skill (automatic)
When spawned by Aegis, all configuration is injected via environment variables. The benchmark discovers your LLM gateway and VLM server automatically, generates an HTML report, and opens it when complete.
Standalone
# LLM-only (VLM tests skipped)
node scripts/run-benchmark.cjs
# With VLM tests (base URL without /v1 suffix)
node scripts/run-benchmark.cjs --vlm http://localhost:5405
# Custom LLM gateway
node scripts/run-benchmark.cjs --gateway http://localhost:5407
# Skip report auto-open
node scripts/run-benchmark.cjs --no-open
Configuration
Environment Variables (set by Aegis)
| Variable | Default | Description |
|---|---|---|
AEGIS_GATEWAY_URL |
http://localhost:5407 |
LLM gateway (OpenAI-compatible) |
AEGIS_LLM_URL |
— | Direct llama-server LLM endpoint |
AEGIS_LLM_API_TYPE |
openai |
LLM provider type (builtin, openai, etc.) |
AEGIS_LLM_MODEL |
— | LLM model name |
AEGIS_LLM_API_KEY |
— | API key for cloud LLM providers |
AEGIS_LLM_BASE_URL |
— | Cloud provider base URL (e.g. https://api.openai.com/v1) |
AEGIS_VLM_URL |
(disabled) | VLM server base URL |
AEGIS_VLM_MODEL |
— | Loaded VLM model ID |
AEGIS_SKILL_ID |
— | Skill identifier (enables skill mode) |
AEGIS_SKILL_PARAMS |
{} |
JSON params from skill config |
What ships with it
55 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 342 B
- fixtures/frames/backyard_animal.png 876 KB
- fixtures/frames/bicycle_sidewalk.png 833 KB
- fixtures/frames/box_carrier.png 706 KB
- fixtures/frames/condensation_lens.png 438 KB
- fixtures/frames/doorstep_package.png 792 KB
- fixtures/frames/driveway_full.png 854 KB
- fixtures/frames/fallen_person.png 748 KB
- fixtures/frames/fog_scene.png 462 KB
- fixtures/frames/front_door_person.png 746 KB
- fixtures/frames/front_porch_group.png 783 KB
- fixtures/frames/garden_path.png 998 KB
- fixtures/frames/garden_tool_person.png 853 KB
- fixtures/frames/glare_sunlight.png 580 KB
- fixtures/frames/headlights_night.png 766 KB
- fixtures/frames/hivis_worker.png 713 KB
- fixtures/frames/indoor_blocked_exit.png 611 KB
- fixtures/frames/indoor_child_cabinet.png 671 KB
- fixtures/frames/indoor_elec_cord.png 676 KB
- fixtures/frames/indoor_elec_powerstrip.png 712 KB
- fixtures/frames/indoor_fall_person.png 553 KB
- fixtures/frames/indoor_fall_shelf.png 664 KB
- fixtures/frames/indoor_fire_candle.png 679 KB
- fixtures/frames/indoor_fire_heater.png 652 KB
- fixtures/frames/indoor_fire_iron.png 709 KB
- fixtures/frames/indoor_fire_stove.png 506 KB
- fixtures/frames/indoor_trip_stairs.png 721 KB
- fixtures/frames/indoor_trip_wetfloor.png 638 KB
- fixtures/frames/jogger_sidewalk.png 697 KB
- fixtures/frames/living_room_empty.png 754 KB
- fixtures/frames/mailbox_delivery.png 745 KB
- fixtures/frames/motorcycle_driveway.png 763 KB
- fixtures/frames/multi_class_scene.png 637 KB
- fixtures/frames/multiple_animals.png 754 KB
- fixtures/frames/multiple_vehicles.png 593 KB
- fixtures/frames/night_motion.png 696 KB
- fixtures/frames/occluded_person.png 923 KB
- fixtures/frames/open_garage.png 772 KB
- fixtures/frames/parking_lot_vehicle.png 901 KB
- fixtures/frames/patio_furniture.png 744 KB
- fixtures/frames/pool_area.png 869 KB
- fixtures/frames/rain_scene.png 692 KB
- fixtures/frames/snow_scene.png 746 KB
- fixtures/frames/spider_web_lens.png 807 KB
- fixtures/frames/street_traffic.png 853 KB
- fixtures/frames/vehicle_detail.png 736 KB
- fixtures/frames/wheelchair_user.png 728 KB
- fixtures/frames/window_peeper.png 652 KB
- fixtures/tool-use-scenarios.json 22 KB
- package-lock.json 874 B
- package.json 308 B
- README.md 5.9 KB
- scripts/generate-report.cjs 50 KB runs code
- scripts/run-benchmark.cjs 159 KB runs code
- scripts/test-model-config.cjs 9.8 KB runs code
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 · 146 lines · 17 tokens per session scan A 6a5d5a168495
Home Security AI Benchmark is a skill published in the GitHub repository SharpAI/DeepCamera (3,105 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,566 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
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
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…
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-running-evaluations
Execute TruLens evaluations and view results.
edd
Eval-driven development loop for this repo (rag-loop, an aircraft-systems RAG app on LangGraph, OpenAI, Qdrant Cloud, and TruLens). Use when the user wants to run an experiment, inspect feedback metrics, or decide keep-or-reject on a config/prompt change.