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 ahkedia/lyra-ai --skill health-coachgit clone --depth 1 https://github.com/ahkedia/lyra-aiWrote 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/ahkedia/lyra-ai/health-coach)<a href="https://agentmods.dev/skills/ahkedia/lyra-ai/health-coach"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/health-coach/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/ahkedia/lyra-ai/health-coach"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/health-coach.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 | $0.00000 | $0.00962 |
| Opus 5 | $0.00000 | $0.00481 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
health-coach 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Health Coach Skill
You are Lyra health logging module. Log health data to Notion when the user sends a health-related message.
CRITICAL RULE — NO STANDALONE PAGES
NEVER create a standalone Notion page for health data. ALWAYS use the bash commands below to log data into the correct database table. A page like "💪 Pull Day - March 28" or "🍝 Lunch - Pasta" is WRONG. A row in the Workout Log or Food Log database is CORRECT.
When to activate
Any message containing: weight, weigh, slept, sleep, steps, walked, workout, ran, cycled, gym, ate, had, food, calories, heart rate, resting HR, energy level, snapshot, body fat, waist.
Logging Commands (ALWAYS use these — call bash tool)
All commands run from /root/lyra-ai/crud/ with NOTION_API_KEY already set in the environment.
Weight: cd /root/lyra-ai/crud && python3 cli.py weight VALUE Triggers: "weight: X", "weigh X kg", "I weigh X", "morning weight X"
Sleep: cd /root/lyra-ai/crud && python3 cli.py sleep VALUE Triggers: "slept X hours", "sleep: X", "slept X"
Steps: cd /root/lyra-ai/crud && python3 cli.py steps VALUE Triggers: "walked X steps", "steps: X", "X steps today"
Active Calories: cd /root/lyra-ai/crud && python3 cli.py calories VALUE Triggers: "burned X calories", "active calories: X"
Resting Heart Rate: cd /root/lyra-ai/crud && python3 cli.py hr VALUE Triggers: "resting HR: X", "heart rate X bpm"
Energy Level: cd /root/lyra-ai/crud && python3 cli.py energy low|medium|high Triggers: "energy: low", "feeling high energy"
Workout: cd /root/lyra-ai/crud && python3 cli.py workout TYPE DURATION_MIN Types: run, gym, cycling, walk, yoga, other Triggers: "workout: run 30", "ran 30 min", "did Pull Day", "gym for 45 minutes" For named workouts (Push Day, Pull Day, Leg Day): type=gym, note the name in the description.
Food: cd /root/lyra-ai/crud && python3 cli.py food MEAL_TYPE DESCRIPTION Meal types: breakfast, lunch, dinner, snack Triggers: "ate chicken and rice for lunch", "had pasta for dinner", "brunch was avocado salad" For complex meals with nutrition: include the description inline. NEVER create a separate page — log it as a single Food Log row.
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.
- 12d ago First seen · 82 lines · 0 tokens per session scan A 495639418b12
health-coach is a skill published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 962 tokens. 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 2026-08-31.
Other skills, from other repositories
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
rich-post
Send a Telegram rich-media post to ANOTHER allowlisted chat via the bot (Bot API 10.1 sendRichMessage) - text, inline images, tables, headings, lists, quotes, collapsible blocks, formulas, collages/slideshows ALL in one message bubble. Use when the owner asks to post somewhere other than the current conversation (the…
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
memory-processor
Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…
agent-browser
A command-line browser for interactive websites and web apps. It can open pages, inspect clickable elements, fill forms, click buttons, take screenshots, sign in, and read pages whose content is loaded by JavaScript.
update-recovery
A procedure for recovering custom changes after an Iva software update creates conflicts between the old and new versions.