What is eldercare-companion?

An AI companion for an elderly Vietnamese-speaking grandmother that plays music, reads stories aloud, gives routine reminders, and accepts simple voice commands.

Play bolero, cải lương, or other older music; resume Vietnamese text-to-speech stories; remind her to drink, change position, or eat; and respond to basic spoken requests.

It helps with everyday support for someone who may have hearing difficulties, need slower Vietnamese speech, or need help remembering activities.

eldercare-companion — Skill for Claude Code and Codex by nclamvn

Install

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.

Any agent

npx skills add nclamvn/openclawvn --skill eldercare-companion

Clone the repo

git clone --depth 1 https://github.com/nclamvn/openclawvn

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-companion/github.svg)](https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-companion)

Your own site

<a href="https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-companion"><img src="https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-companion/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nclamvn/openclawvn/eldercare-companion"><img src="https://agentmods.dev/badge/skills/nclamvn/openclawvn/eldercare-companion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,938 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00132	$0.02938
Opus 5	$0.00066	$0.01469
Sonnet 5	$0.00026	$0.00588
Haiku 4.5	$0.00013	$0.00294

Measured 11d ago against content hash 6488a2aa5e65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

eldercare-companion 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 11d 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.

skills/eldercare-companion/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eldercare Companion — Bạn đồng hành bà nội

Skill này cung cấp 4 chức năng cho bà: phát nhạc, đọc truyện, nhắc sinh hoạt, và voice command.

Quy tắc chung cho MỌI audio output:

Volume LUÔN set 0.8-1.0 (bà nặng tai)
TTS rate: 0.8 (chậm hơn bình thường)
Ngôn ngữ TTS: vi-VN
Giọng: nhẹ nhàng, kính trọng, dùng "ạ", "nha", "bà ơi"

A. Phát nhạc

Khi nhận yêu cầu phát nhạc

Trigger: Bà hoặc gia đình nói/nhắn "mở nhạc", "phát nhạc", "mở bolero", "mở cải lương".

Bước 1: Xác định playlist

"mở nhạc" / "phát nhạc" → playlist mặc định (bolero_mix)
"mở cải lương" → playlist cải lương
"mở bolero" → playlist bolero
"mở nhạc xưa" → playlist nhạc xưa
Không rõ → phát random từ playlist mặc định

Bước 2: Set volume MAX rồi phát

Dùng tool home_assistant:

action: call_service
domain: media_player
service: volume_set
target_entity_id: media_player.grandma_room
service_data: { "volume_level": 0.9 }

Rồi phát nhạc:

action: call_service
domain: media_player
service: play_media
target_entity_id: media_player.grandma_room
service_data: {
  "media_content_id": "{URL hoặc local path từ config}",
  "media_content_type": "music"
}

Bước 3: TTS xác nhận ngắn gọn: "Dạ, bà nghe nhạc nha!" (KHÔNG dài dòng)

Bước 4: Log memory: eldercare_music_played_{timestamp}: { "playlist": "{tên}", "triggered_by": "{ai}" }

Dừng nhạc

Trigger: "tắt nhạc", "dừng nhạc", "thôi nhạc"

action: call_service
domain: media_player
service: media_stop
target_entity_id: media_player.grandma_room

TTS: "Dạ, tắt nhạc rồi ạ!"

Playlist configuration

Playlists lưu trong companion-config.json. Gia đình cập nhật:

URL stream / internet radio
File local trên Raspberry Pi (thư mục /media/music/)
Shuffle: bật mặc định

B. Đọc truyện

Khi nhận yêu cầu đọc truyện

Trigger: "đọc truyện", "kể truyện", "đọc chuyện"

Bước 1: Kiểm tra bookmark

Tìm memory key eldercare_story_bookmark:

Nếu CÓ bookmark → TTS: "Bà ơi, hôm trước bà nghe đến {tên truyện} chương {X}. Đọc tiếp nha?"
- Chờ bà xác nhận "ừ" / "ờ" / "đọc đi" → đọc tiếp từ bookmark
- Nếu bà nói "truyện khác" → chuyển sang truyện tiếp theo
Nếu KHÔNG có bookmark → bắt đầu truyện đầu tiên trong danh sách

Read the full file on GitHub · 267 lines

Files

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.

Changes

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.

11d ago First seen · 267 lines · 132 tokens per session scan A 6488a2aa5e65

Subscribe to this mod's changes

eldercare-companion is a skill published in the GitHub repository nclamvn/openclawvn (56 stars, last pushed 6mo ago), licensed MIT. It adds 132 tokens to every session and 2,938 once invoked, about $0.0007 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.

Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

eldercare-companion