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 nclamvn/openclawvn --skill eldercare-fall-detectgit clone --depth 1 https://github.com/nclamvn/openclawvnWrote 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/nclamvn/openclawvn/eldercare-fall-detect)<a href="https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-fall-detect"><img src="https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-fall-detect/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/nclamvn/openclawvn/eldercare-fall-detect"><img src="https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-fall-detect.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 | $0.00105 | $0.02437 |
| Opus 5 | $0.00053 | $0.01218 |
| Sonnet 5 | $0.00021 | $0.00487 |
| Haiku 4.5 | $0.00011 | $0.00244 |
Grade A, and why
eldercare-fall-detect 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 9d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eldercare Fall Detect — Phát hiện bà ngã
Skill này phát hiện té ngã bằng 2 layer và xác nhận trước khi escalate.
Khi nào skill này chạy
Skill này KHÔNG chạy theo cron. Nó được trigger bởi:
- HA Event:
state_changedtrên entity fall detection (Layer 1) - Từ eldercare-monitor: Khi monitor phát hiện pattern nghi ngờ ngã (Layer 2)
Layer 1: Aqara FP2 Native Fall Detection
Kiểm tra entity tồn tại
Trước tiên, kiểm tra xem firmware FP2 có hỗ trợ fall detection không:
action: get_state
entity_id: binary_sensor.grandma_room_fall_detected
- Nếu entity TỒN TẠI → Layer 1 active, subscribe event
- Nếu entity KHÔNG TỒN TẠI (unavailable / not found) → Layer 1 disabled, chỉ dùng Layer 2
Khi FP2 báo fall detected
Khi binary_sensor.grandma_room_fall_detected chuyển sang on:
- Log:
eldercare_fall_raw_{timestamp}: { "source": "fp2_native", "entity_state": "on" } - Chuyển sang Bước Xác Nhận (xem bên dưới)
False positive filtering (Layer 1)
FP2 fall detection có thể false positive khi:
- Bà nằm xuống giường bình thường (từ ngồi → nằm)
- Trẻ con/thú nuôi di chuyển nhanh
Lọc:
- Nếu
sensor.grandma_room_motion_minutes< 2 VÀbinary_sensor.grandma_room_presence= on → có thể bà chỉ nằm xuống - Vẫn tiếp tục TTS xác nhận, nhưng ghi note:
"likely_normal_movement": true
Layer 2: AI Pattern Detection
Pattern: Motion Spike → Sudden Stillness
Được trigger từ eldercare-monitor khi phát hiện pattern sau:
- Motion spike: Camera motion (
binary_sensor.grandma_room_camera_motion) chuyểnonđột ngột - Rồi bất động:
sensor.grandma_room_motion_minutestăng nhanh (> 5 phút bất động) ngay sau spike - Presence vẫn on:
binary_sensor.grandma_room_presence= on (người vẫn trong phòng)
Quy tắc phát hiện (eldercare-monitor gọi skill này khi):
- Camera motion
on→ rồiofftrong vòng 30 giây (spike ngắn) - SAU ĐÓ: motion_minutes tăng liên tục > 5 phút
- VÀ: KHÔNG phải giờ ngủ đêm (22-6h) hoặc giờ nap (13-15h)
- VÀ: Presence = on
What ships with it
1 file 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.
- 9d ago First seen · 230 lines · 105 tokens per session scan A 07b3b63177b3
eldercare-fall-detect is a skill published in the GitHub repository nclamvn/openclawvn (56 stars, last pushed 6mo ago), licensed MIT. It adds 105 tokens to every session and 2,437 once invoked, about $0.0005 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.