health-data-model-planning

health-data-model-planning is a skill for Claude Code, Codex from StanfordSpezi/SpeziVibe. It costs 26 tokens per session (1,386 once invoked), scanned A, original, MIT.

A planning process for the health concepts, entities, relationships, and rules an app must store. It often starts with FHIR, a standard way for healthcare systems to represent and exchange clinical data.

In plain words
What is it for?
Use it to plan clinical concepts, relationships, lifecycle states, and data governance for a mobile app, backend, analytics system, or research workflow.
Why use it?
It helps prevent unclear data structures and costly changes later. It also makes interoperability—the ability to exchange data with other systems—part of the design from the beginning.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan clinical concepts, relationships, lifecycle states, and data governance for a mobile app, backend, analytics system, or research workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stanfordspezi/spezivibe/health-data-model-planning
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 StanfordSpezi/SpeziVibe --skill health-data-model-planning
Clone the repo
git clone --depth 1 https://github.com/StanfordSpezi/SpeziVibe

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.

agentmods badge for health-data-model-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/stanfordspezi/spezivibe/health-data-model-planning/github.svg)](https://agentmods.dev/skills/stanfordspezi/spezivibe/health-data-model-planning)
Your own site
<a href="https://agentmods.dev/skills/stanfordspezi/spezivibe/health-data-model-planning"><img src="https://agentmods.dev/badge/skills/stanfordspezi/spezivibe/health-data-model-planning/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-data-model-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/stanfordspezi/spezivibe/health-data-model-planning"><img src="https://agentmods.dev/badge/skills/stanfordspezi/spezivibe/health-data-model-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,386 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 $0.00026 $0.01386
Opus 5 $0.00013 $0.00693
Sonnet 5 $0.00005 $0.00277
Haiku 4.5 $0.00003 $0.00139

Measured 12d ago against content hash 5eb5cc325088, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

health-data-model-planning 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.

skills/health-data-model-planning/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Health Data Model Planner

Plan a health data model with a strong bias toward FHIR before committing to storage, code structures, or client-specific architecture.

When to Use

Use this skill when you need to:

  • define the core health concepts a product needs to represent
  • decide which entities, relationships, and lifecycle states matter
  • reason about interoperability requirements with FHIR as the default starting point for clinical data
  • prepare for later implementation in a mobile app, backend, analytics pipeline, or research workflow

Relationship to fhir-data-model-design: this skill plans the concepts — entities, relationships, lifecycle states, and whether FHIR fits. When the app needs a concrete FHIR R4 specification (specific resources, profiles, and terminology bindings), run fhir-data-model-design afterwards; its output supersedes this brief's preliminary FHIR recommendations.

Working Style

Start with the domain, but assume that clinically meaningful data will often benefit from a FHIR-oriented design unless there is a strong reason not to.

Clarify:

  1. what the product is trying to track or coordinate
  2. who creates, reads, updates, or interprets the data
  3. what must be longitudinal, auditable, shareable, or clinically meaningful
  4. what needs to be structured versus free-form
  5. which standards, institutions, or downstream systems matter

Default Bias Toward FHIR

In digital health, prefer asking "How would this map to FHIR?" early rather than treating interoperability as a late-stage add-on.

Default questions:

  • should this concept become a FHIR resource instead of a custom object
  • is there an existing FHIR pattern for this workflow
  • should values use established terminologies such as LOINC, SNOMED CT, or RxNorm
  • will this data eventually need to move between apps, research systems, backend services, or EHR-adjacent systems

Read the full file on GitHub · 179 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. 12d ago First seen · 179 lines · 26 tokens per session scan A 5eb5cc325088

Subscribe to this mod's changes

health-data-model-planning is a skill published in the GitHub repository StanfordSpezi/SpeziVibe (24 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 1,386 once invoked, about $0.0001 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.