google-health-cli AGENTS.md

google-health-cli AGENTS.md is an instructions file for Codex, OpenCode from Google-Health-API/google-health-cli. It costs 570 tokens per session, scanned A, original, Apache-2.0.

Development guidance for ghealth, a command-line program that accesses Google Health API data such as steps, heart rate, sleep, exercise, weight, oxygen levels, and heart-rate variability. It handles sign-in, paging through results, simplified responses, and help for coding agents.

In plain words
What is it for?
Use it to build and check the CLI, inspect its command and schema help, authenticate, and retrieve supported health data such as steps or daily summaries.
Why use it?
It shows how to discover the available health-data types and operations without learning the full Google Health API structure first.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/google-health-api/google-health-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/Google-Health-API/google-health-cli

Made for: Codex, OpenCode.

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 google-health-cli AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/google-health-api/google-health-cli/agents-md.svg)](https://agentmods.dev/instructions/google-health-api/google-health-cli/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/google-health-api/google-health-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/google-health-api/google-health-cli/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 570 This file is loaded in full into every session.
When invoked 570 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.00570 $0.00570
Opus 5 $0.00285 $0.00285
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 5d ago against content hash cb2089e54050, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

google-health-cli AGENTS.md scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Test new types with curl before adding to the registry
AGENTS.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ghealth — Development Guide

What is this

ghealth is a CLI wrapping the Google Health API v4. Primary users are AI agents (OpenClaw, Claude Code, Codex, coding agents) that need structured health data access — steps, heart rate, sleep, exercise, weight, SpO2, HRV. Human developers use it too.

The CLI handles OAuth, pagination, response simplification, and contextual hints so agents can focus on the health question, not API plumbing.

Progressive disclosure

Information is layered so agents load only what they need:

  1. ghealth --help → commands overview
  2. ghealth data --help → list vs daily-rollup guidance, all 40 types
  3. ghealth data <type> --help → available operations
  4. ghealth data <type> <op> --help → flags for that operation
  5. ghealth schema types → machine-readable type registry
  6. ghealth schema type <name> → fields, parameters, scope for one type
  7. _hints in responses → contextual next-step suggestions
  8. skills/ghealth/SKILL.md → non-obvious patterns, gotchas (load once)

Build

go build -o ghealth .
go vet ./...

Verify against the live API: ghealth auth status, then ghealth data steps daily-rollup --from 2026-03-22 --to 2026-03-29.

Workflow

  • Feature branches + PRs — never commit to main directly
  • Only register data types verified against the live API, not from docs alone
  • Test new types with curl before adding to the registry

Where to make changes

Task Start here
Add/remove a data type pkg/types/registry.go
Change response format pkg/output/simplify.go
Add a contextual hint pkg/output/hints.go
Change CLI flags or help text cmd/root.go (globals), cmd/data.go (operations)
OAuth or auth flow pkg/auth/auth.go

Documentation to keep updated

When you... Update
Add/remove a data type README.md types table, skills/ghealth/SKILL.md
Change flags or commands README.md, skills/ghealth-shared/SKILL.md

Read the full file on GitHub · 59 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. 5d ago First seen · 59 lines · 570 tokens per session scan A cb2089e54050

Subscribe to this mod's changes

google-health-cli AGENTS.md is an instructions file published in the GitHub repository Google-Health-API/google-health-cli (238 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 570 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.