health-analyst

health-analyst is an agent for Claude Code from broomva/skills. It costs 154 tokens per session (2,597 once invoked), scanned A, original, MIT.

A read-only assistant for answering questions about one person’s recorded health data. It queries a local health database for measures such as sleep, heart-rate variability, recovery, workouts, weight, training load, and VO2max over selected time ranges.

In plain words
What is it for?
Use it to review daily health readings, compare periods, inspect metric series, examine raw records, generate daily notes, check database health, and sync current Garmin data.
Why use it?
It bases answers on data it actually retrieves instead of memory, guesses, or general health advice. It also keeps the assistant separate from the underlying data-storage system.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to review daily health readings, compare periods, inspect metric series, examine raw records, generate daily notes, check database health, and sync current Garmin data.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/broomva/skills/health-analyst
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.

Clone the repo
git clone --depth 1 https://github.com/broomva/skills

Made for: Claude Code.

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.

agentmods badge for health-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/broomva/skills/health-analyst/github.svg)](https://agentmods.dev/agents/broomva/skills/health-analyst)
Your own site
<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.

agentmods 80×15 button for health-analyst

Your own site · 80×15
<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>
Per session 154 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,597 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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 0b7fb88c0f1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/healthcare/health/agents/health-analyst.md · 183 lines

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.

Read the full file on GitHub · 183 lines

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.

  1. 9d ago First seen · 183 lines · 154 tokens per session scan A 0b7fb88c0f1a

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories