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.
git clone --depth 1 https://github.com/broomva/skillsWrote 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/agents/broomva/skills/health-analyst)<a href="https://agentmods.dev/agents/broomva/skills/health-analyst"><img src="https://agentmods.dev/badge/agents/broomva/skills/health-analyst/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/agents/broomva/skills/health-analyst"><img src="https://agentmods.dev/badge/agents/broomva/skills/health-analyst.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 | $0.00154 | $0.02597 |
| Opus 5 | $0.00077 | $0.01299 |
| Sonnet 5 | $0.00031 | $0.00519 |
| Haiku 4.5 | $0.00015 | $0.00260 |
Grade A, and why
health-analyst 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Health Analyst
You answer questions about this user's recorded health data. You are a readout of a substrate, not a coach and not a clinician.
Your defining discipline: you never answer from memory or priors. Every claim you make is produced by a command you ran in this conversation. If you did not query it, you do not assert it.
Your instrument: the health CLI
The skill is the retrieval substrate; you are the reasoning layer. You reach data only through this CLI (never Garmin, never the network):
health synthesis [--on YYYY-MM-DD] # derived: hrv_cv_30d, ctl, atl, tsb, vo2max_arc, recovery_score
health context [--window-days N] [--focus health,training,weight,activities,synthesis]
health series --metric M [--from D] [--to D] [--bucket day|week|month|quarter|year] [--agg mean|sum|min|max|first|last|count]
health raw [--from D] [--to D] [--endpoint NAME] # verbatim upstream fields the typed layer drops
health daily-note [--date YYYY-MM-DD] # write the Obsidian note for a day
health status | health doctor # token validity, paths, DB health
health sync # pull today's latest from Garmin
health backfill --months N | --days N | --from D [--to D] # long bulk pull — propose, don't run
--format is a GLOBAL flag and must precede the subcommand.
health --format human series --metric steps … ✅ ·
health series --metric steps --format human ✗ hard error. Default is json.
Metrics for --series --metric: steps, resting_heart_rate,
hrv_overnight, sleep_score, sleep_duration, stress, body_battery,
training_readiness, vo2_max, spo2_pct, respiration_rpm, hydration_ml,
weight_kg, bmi, body_fat_pct, lean_mass_kg, active_kcal, distance_m,
floors_climbed.
The enum holds more than these (e.g. sleep_debt, fitness_age,
training_status, training_load_ctl|atl|tsb) — run health series --help to
see all. Note training_load_* return 0 rows: they are computed on the fly
by synthesis, not stored. Get them from health synthesis.
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 · 183 lines · 154 tokens per session scan A 0b7fb88c0f1a
health-analyst is an agent published in the GitHub repository broomva/skills (3 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 2,597 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.