OpenMed is local-first healthcare AI software that extracts clinical information and removes personally identifying details from clinical text on hardware controlled by the user. Healthcare developers use its Python runtime, Apple Silicon and mobile SDKs, and browser support for on-device clinical NER and PII de-identification.
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 maziyarpanahi/openmed --skill etl-to-omop-cdmgit clone --depth 1 https://github.com/maziyarpanahi/openmedWrote 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/maziyarpanahi/openmed/etl-to-omop-cdm)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/etl-to-omop-cdm"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/etl-to-omop-cdm/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/maziyarpanahi/openmed/etl-to-omop-cdm"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/etl-to-omop-cdm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00176 | $0.02024 |
| Opus 5 | $0.00088 | $0.01012 |
| Sonnet 5 | $0.00035 | $0.00405 |
| Haiku 4.5 | $0.00018 | $0.00202 |
Grade A, and why
etl-to-omop-cdm 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 13d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ETL to OMOP CDM
The OMOP Common Data Model (CDM) is the OHDSI standard for observational health
data. This skill maps OpenMed-derived clinical facts — entities from
analyze_text that you have already linked to a source terminology — into the
OMOP clinical event tables condition_occurrence, drug_exposure, and
measurement. The NLP runs on-device; OMOP loading is a downstream,
deterministic transform.
When to use this skill
After you have (a) extracted entities with OpenMed and (b) coded them to a source vocabulary (ICD-10-CM / SNOMED for conditions, RxNorm for drugs, LOINC for labs — see the linking skills). Use this skill to turn those coded facts into OMOP rows. It is not a clinical NER skill and not a code-linking skill; it assumes both are done.
Quick start
import openmed
note = "Assessment: type 2 diabetes mellitus. Started metformin 500 mg PO BID. HbA1c 8.2%."
result = openmed.analyze_text(note, output_format="dict")
# result["entities"] -> [{text,label,confidence,start,end}, ...]
# You then code each entity to a SOURCE concept using the OHDSI vocabulary you
# downloaded (see linking-umls-concepts / normalizing-rxnorm / mapping-loinc),
# and map SOURCE -> STANDARD via CONCEPT_RELATIONSHIP ('Maps to').
fact = {
"person_id": 1001,
"domain": "Condition",
"source_code": "E11.9", # ICD-10-CM, from your coding step
"source_vocabulary": "ICD10CM",
"source_concept_id": 45533010, # OHDSI CONCEPT for E11.9 (lookup)
"standard_concept_id": 201826, # 'Maps to' -> SNOMED 'Type 2 diabetes mellitus'
"start_date": "2024-03-12", # from building-patient-timelines
"char_span": (fact_start, fact_end),
}
OpenMed never ships UMLS/SNOMED/RxNorm/LOINC content. You supply the OHDSI vocabulary bundle (Athena download) and do the lookups under your own license. OpenMed provides the spans and labels.
The source → standard pattern (the heart of OMOP)
Every clinical event row carries two concept ids:
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.
- 13d ago First seen · 145 lines · 176 tokens per session scan A 7d9f3bfbc788
etl-to-omop-cdm is a skill published in the GitHub repository maziyarpanahi/openmed (5,302 stars, last pushed today), licensed Apache-2.0. It adds 176 tokens to every session and 2,024 once invoked, about $0.0009 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.
Other skills, from other repositories
benchmarking
Use this skill when the user wants to benchmark an MLX-VLM change and present the numbers in a PR — fork-vs-main A/B comparisons, isolated-module micro-benchmarks, median-of-N timing with warmup, peak-memory reporting, correctness checks, parameter sweeps, and self-contained reproducible bench scripts to paste into a…
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
server-inference
Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlxvlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
geo-database
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.