Mirobody is a health data engine that collects information from labs, wearables, genomics, imaging, and other sources, then standardizes it for AI use. It supports health applications and agents that answer questions about a person’s medical data with charts and citations. The catalogue skill extends interaction with this engine.
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 thetahealth/mirobody --skill standardize-health-datagit clone --depth 1 https://github.com/thetahealth/mirobodyWrote 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/thetahealth/mirobody/standardize-health-data)<a href="https://agentmods.dev/skills/thetahealth/mirobody/standardize-health-data"><img src="https://agentmods.dev/badge/skills/thetahealth/mirobody/standardize-health-data/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/thetahealth/mirobody/standardize-health-data"><img src="https://agentmods.dev/badge/skills/thetahealth/mirobody/standardize-health-data.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 | $0.00133 | $0.04312 |
| Opus 5.5 | $0.00053 | $0.01725 |
| Sonnet 5.5 | $0.00027 | $0.00862 |
| Haiku 4.5 | $0.00013 | $0.00431 |
Grade A, and why
standardize-health-data 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 today.
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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standardize health data
Health data arrives under whatever name the source used. Last year's checkup
wrote A1c, this year's HbA1c, the clinic Glycated Hemoglobin; a Chinese
report prints 血红蛋白 for what an English one calls hemoglobin. One
test, several names, nothing to compare until each lands on one code. And a
model reading a report is fluent about the rows it got wrong: the failure is
never "I don't know", it is a confident paragraph about the wrong analyte.
This skill is the offline standardizer for both problems: names to LOINC, units to UCUM, complaints and diagnoses to ICPC-3, a FHIR Observation for the result. The codes come from the vocabulary, never from you. When the vocabulary does not know a term the answer is a refusal, and a refusal is an output to report, not a gap to fill from memory.
Setup
pip install mirobody # resolution, units, ICPC-3, Apple export: no key, no network
pip install 'mirobody[parse]' # adds document parsing, which needs one model key
The first is two packages, numpy and this one; the vocabulary ships inside
the wheel and the first call loads it in a few seconds. It needs Python 3.12
or newer: on an older interpreter pip quietly installs a release from before
1.2, which has no mirobody resolve. Install into a virtual environment
(python3.12 -m venv .venv), never into the user's system Python. With uvx,
no install: uvx --python 3.12 mirobody resolve 血红蛋白 (uv fetches that
Python if it is missing). For parsing, put ONE key in the environment or a
.env in the working directory (OPENROUTER_API_KEY, OPENAI_API_KEY,
GOOGLE_API_KEY, ANTHROPIC_API_KEY, DEEPSEEK_API_KEY or
DASHSCOPE_API_KEY). The model reads the document into rows; the codes still
come from the offline resolver.
No key, no search. If neither the environment nor the working directory's
.env has a key, do not look for one anywhere else: no find ~, no reading
another project's .env or ~/.config. Read the document yourself, then
resolve every row with resolve_reading(name, value, unit), which needs no
key. Ask the user for a key only if they want mirobody parse itself.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 309 lines · 133 tokens per session scan A 332d2da56aa5
standardize-health-data is a skill published in the GitHub repository thetahealth/mirobody (1,394 stars, last pushed today), licensed Apache-2.0. It adds 133 tokens to every session and 4,312 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
markdown-converter
Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool. Use when a user attaches a binary file and you need to read its contents.
neqsim-technical-document-reading
Extracts structured engineering data from documents (PDF, Word, Excel, CSV) and drawings/images (P&IDs, datasheets, arrangements, performance maps). USE WHEN: a user provides datasheets, technical requirements, design basis, well tests, inspection reports, standards, vendor drawings, compressor maps, phase envelopes…
faostat-analytical-brief
Use when the user wants a short, FAOSTAT-style analytical brief — a multi-page PDF policy document in the FAOSTAT house visual style, with a HIGHLIGHTS box, global/regional/country sections, numbered figures with source lines, explanatory notes, and a data appendix. Use when the user asks for "an analytical brief on…
modelviz-skill
A manually triggered tool for turning CSV or spreadsheet data and a written chart request into scientific figures using Python templates. It checks the technical and visual result and can produce PNG, SVG, or PDF files with reproducible code.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…