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 mapping-loincgit 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/mapping-loinc)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/mapping-loinc"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/mapping-loinc/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/mapping-loinc"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/mapping-loinc.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 | $0.00197 | $0.02087 |
| Opus 5 | $0.00098 | $0.01043 |
| Sonnet 5 | $0.00039 | $0.00417 |
| Haiku 4.5 | $0.00020 | $0.00209 |
Grade A, and why
mapping-loinc 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 10d 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.
r = requests.get( How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapping lab/observation names to LOINC
Ground free-text lab and observation names that OpenMed surfaces to LOINC (Logical Observation Identifiers Names and Codes), the universal standard for identifying what was measured. A LOINC code is a fully specified observation — not just an analyte but the full six-axis model: Component, Property, Time, System (specimen), Scale, Method.
LOINC is free to use. It is published by the Regenstrief Institute under the
LOINC license: you accept terms-of-use (and register to download the table), but
there is no fee and no per-use restriction. The standard, public path for
license-clean mapping is a FHIR terminology server exposing LOINC via
$lookup / $validate-code, or Regenstrief's hosted fhir.loinc.org.
When to use
- A note or report contains lab/observation names ("serum potassium", "hemoglobin A1c", "blood pressure") and you need a stable LOINC code each.
- You must disambiguate by specimen/system ("glucose in serum" vs "glucose in urine") or method ("HbA1c by HPLC").
- You need UCUM units to pair with the result value, or a US Core
Observation(Laboratory Result) coded with LOINC. - You are mapping a panel (e.g. CBC, BMP) vs its individual analytes.
For diagnoses/procedures use coding-icd10; for drugs use normalizing-rxnorm;
LOINC is for observations and measurements.
Quick start (real LOINC / FHIR terminology calls)
Regenstrief hosts a public FHIR terminology endpoint at https://fhir.loinc.org
(HTTP Basic auth with your free LOINC account). Many sites instead point at their
own server (HAPI, Ontoserver, Snowstorm-with-LOINC). The operations are the same.
import requests
from requests.auth import HTTPBasicAuth
FHIR = "https://fhir.loinc.org"
AUTH = HTTPBasicAuth("YOUR_LOINC_USER", "YOUR_LOINC_PASSWORD") # free account
LOINC_SYSTEM = "http://loinc.org"
def lookup(code: str) -> dict:
"""$lookup: return the fully specified name + axes for a LOINC code."""
r = requests.get(
f"{FHIR}/CodeSystem/$lookup",
params={"system": LOINC_SYSTEM, "code": code},
auth=AUTH, headers={"Accept": "application/fhir+json"}, timeout=15,
)
r.raise_for_status()
return r.json()
def validate(code: str, display: str) -> bool:
r = requests.get(
f"{FHIR}/CodeSystem/$validate-code",
params={"url": LOINC_SYSTEM, "code": code, "display": display},
auth=AUTH, headers={"Accept": "application/fhir+json"}, timeout=15,
)
r.raise_for_status()
params = {p["name"]: p.get("valueBoolean") for p in r.json().get("parameter", [])}
return bool(params.get("result"))
print(lookup("2823-3")) # Potassium [Moles/volume] in Serum or Plasma
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.
- 10d ago First seen · 162 lines · 197 tokens per session scan A 652b188e8cf0
mapping-loinc is a skill published in the GitHub repository maziyarpanahi/openmed (5,282 stars, last pushed today), licensed Apache-2.0. It adds 197 tokens to every session and 2,087 once invoked, about $0.0010 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.
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.