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 extracting-sdohgit 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/extracting-sdoh)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/extracting-sdoh"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/extracting-sdoh/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/extracting-sdoh"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/extracting-sdoh.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 | $0.00163 | $0.01995 |
| Opus 5 | $0.00081 | $0.00997 |
| Sonnet 5 | $0.00033 | $0.00399 |
| Haiku 4.5 | $0.00016 | $0.00199 |
Grade A, and why
extracting-sdoh 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.
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.
Extracting SDOH and Mapping to ICD-10-CM Z-Codes
Social determinants of health (SDOH) — the conditions in which people live, work, and age — drive an estimated 80% of health outcomes, yet they live almost entirely in free-text narrative. Multiple chart-review studies find SDOH documented in notes but coded with a Z-code under ~2% of the time. The information is there; the structured signal is not. This skill recovers it: run OpenMed NER over de-identified notes, then map the resulting spans to the ICD-10-CM Z55–Z65 family.
When to use
- A note clearly describes a social risk ("lives in her car", "skips meals to afford insulin", "no ride to dialysis") and you want a coded, queryable signal.
- You are building health-equity dashboards, risk stratification, or closed-loop referral feeds and need SDOH as discrete data.
- You want to reconcile what the chart says against what was coded, and flag Z-code gaps for a coder or care team to confirm.
This is a decision-support step. It proposes Z-codes; a human assigns them. SDOH coding is sensitive — never expose individual SDOH inferences outside the care/coding workflow, and never feed them to coverage or pricing decisions.
Quick start
De-identify first, run NER, then map spans to Z-codes:
import openmed
from sdoh_zcode_map import SDOH_ZCODES # see references/sdoh_zcode_map.md
note = (
"62F with CHF. Reports she lost her apartment last month and is "
"staying in a shelter. Often runs out of food before month-end. "
"No car; misses appointments because the bus does not run to clinic."
)
# 1) Strip PHI before any downstream processing or storage.
deid = openmed.deidentify(note, method="replace", policy="hipaa_safe_harbor")
# 2) Run clinical NER. Use an SDOH/clinical model from the registry; discover
# available keys with openmed.get_models_by_category(...).
result = openmed.analyze_text(deid.text, output_format="dict")
# 3) Map each entity span to a candidate Z-code.
for ent in result["entities"]:
code = SDOH_ZCODES.get(ent["label"].lower())
if code:
print(f"{ent['text']!r:40} {ent['label']:18} -> {code}")
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.
- 9d ago First seen · 145 lines · 163 tokens per session scan A b081dd4ac82e
extracting-sdoh is a skill published in the GitHub repository maziyarpanahi/openmed (5,282 stars, last pushed today), licensed Apache-2.0. It adds 163 tokens to every session and 1,995 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 2026-08-30.
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.
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.
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.
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.