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/sharpai/deepcamera/homesafe-benchnpx skills add SharpAI/DeepCamera --skill homesafe-benchgit clone --depth 1 https://github.com/SharpAI/DeepCameraWhat 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 | $0.00028 | $0.01201 |
| Opus 5 | $0.00014 | $0.00600 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
HomeSafe-Bench 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HomeSafe-Bench — Indoor Safety Hazard Detection
VLM benchmark evaluating indoor home safety hazard detection from static camera frames. Inspired by HomeSafeBench (arXiv 2509.23690), adapted for fixed indoor security cameras with AI-generated fixture images.
40 tests across 5 hazard categories:
| Category | Tests | Example Hazards |
|---|---|---|
| 🔥 Fire / Smoke | 8 | Stove smoke, candle near curtain, iron left face-down |
| ⚡ Electrical | 8 | Overloaded power strip, exposed wire, frayed cord |
| 🚶 Trip / Fall | 8 | Toys on staircase, wet floor, loose rug edge |
| 👶 Child Safety | 8 | Open cabinet with chemicals, uncovered outlet, blind cord |
| 📦 Falling Objects | 8 | Heavy items on high shelf, leaning bookshelf, loose ceiling fan |
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 VLM server automatically, generates an HTML report, and opens it when complete.
Standalone
# Run all 40 tests
node scripts/run-benchmark.cjs --vlm http://localhost:5405
# Quick mode (2 tests per category = 10 total)
node scripts/run-benchmark.cjs --vlm http://localhost:5405 --mode quick
# Skip report auto-open
node scripts/run-benchmark.cjs --vlm http://localhost:5405 --no-open
Configuration
Environment Variables (set by Aegis)
| Variable | Default | Description |
|---|---|---|
AEGIS_VLM_URL |
(required) | 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
47 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 358 B
- deploy.bat 409 B runs code
- deploy.sh 187 B runs code
- fixtures/frames/child_01_chemicals_cabinet.png 1348 KB
- fixtures/frames/child_02_uncovered_outlet.png 710 KB
- fixtures/frames/child_03_blind_cord.png 642 KB
- fixtures/frames/child_04_sharp_corner.png 1768 KB
- fixtures/frames/child_05_choking_hazard.png 1884 KB
- fixtures/frames/child_06_unsecured_bookshelf.png 1405 KB
- fixtures/frames/child_07_stove_knobs.png 1297 KB
- fixtures/frames/child_08_open_window.png 1192 KB
- fixtures/frames/electrical_01_overloaded_strip.png 880 KB
- fixtures/frames/electrical_02_exposed_wire_sink.png 605 KB
- fixtures/frames/electrical_03_frayed_cord.png 568 KB
- fixtures/frames/electrical_04_cord_under_rug.png 801 KB
- fixtures/frames/electrical_05_wet_hands_outlet.png 682 KB
- fixtures/frames/electrical_06_ungrounded_adapter.png 601 KB
- fixtures/frames/electrical_07_damaged_outlet.png 598 KB
- fixtures/frames/electrical_08_tangled_cords.png 745 KB
- fixtures/frames/falling_01_heavy_high_shelf.png 1435 KB
- fixtures/frames/falling_02_stacked_boxes.png 1369 KB
- fixtures/frames/falling_03_leaning_bookshelf.png 1556 KB
- fixtures/frames/falling_04_fridge_top.png 1421 KB
- fixtures/frames/falling_05_overhead_tools.png 1627 KB
- fixtures/frames/falling_06_unsecured_tv.png 1258 KB
- fixtures/frames/falling_07_overloaded_coatrack.png 1305 KB
- fixtures/frames/falling_08_loose_fan_blade.png 1229 KB
- fixtures/frames/fire_01_stove_smoke.png 715 KB
- fixtures/frames/fire_02_candle_curtain.png 637 KB
- fixtures/frames/fire_03_fireplace_ember.png 680 KB
- fixtures/frames/fire_04_iron_facedown.png 696 KB
- fixtures/frames/fire_05_heater_drapes.png 570 KB
- fixtures/frames/fire_06_missing_detector.png 525 KB
- fixtures/frames/fire_07_grease_fire.png 792 KB
- fixtures/frames/fire_08_cigarette_couch.png 676 KB
- fixtures/frames/trip_01_toys_stairs.png 666 KB
- fixtures/frames/trip_02_wet_floor.png 541 KB
- fixtures/frames/trip_03_loose_rug.png 675 KB
- fixtures/frames/trip_04_cluttered_hallway.png 768 KB
- fixtures/frames/trip_05_shoes_doorway.png 725 KB
- fixtures/frames/trip_06_dark_stairwell.png 653 KB
- fixtures/frames/trip_07_cables_walkway.png 761 KB
- fixtures/frames/trip_08_stool_stairs.png 567 KB
- fixtures/scenarios.json 25 KB
- package-lock.json 1.0 KB
- package.json 474 B
- scripts/run-benchmark.cjs 22 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.
- 2d ago First seen · 124 lines · 28 tokens per session scan A 39c331770b45
HomeSafe-Bench is a skill published in the GitHub repository SharpAI/DeepCamera (3,031 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,201 once invoked, about $0.0001 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
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…
condition-setup
../../../.opencode/skills/condition-setup/SKILL.md.
create-problem
../../../.opencode/skills/create-problem/SKILL.md.
define-domains
../../../.opencode/skills/define-domains/SKILL.md.
define-equations
../../../.opencode/skills/define-equations/SKILL.md.