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 exporting-to-fhirgit 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/exporting-to-fhir)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/exporting-to-fhir"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/exporting-to-fhir/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/exporting-to-fhir"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/exporting-to-fhir.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 | $0.02774 |
| Opus 5 | $0.00081 | $0.01387 |
| Sonnet 5 | $0.00033 | $0.00555 |
| Haiku 4.5 | $0.00016 | $0.00277 |
Grade A, and why
exporting-to-fhir 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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exporting to FHIR
OpenMed's NER (openmed.analyze_text) returns spans — text, label, offsets,
confidence. To make those spans interoperable you wrap each clinically relevant
span in a FHIR R4 resource (Condition, MedicationStatement,
Observation, ...) carrying a coded CodeableConcept. OpenMed ships the
mechanical R4 export helpers for this in openmed.clinical.exporters; you
own the small amount of clinical mapping (which span becomes which resource).
When to use
Use this after NER, when the consumer is a FHIR system (an EHR, a registry, a
data lake on FHIR). Reach for it when the user says "export to FHIR", "make a
Condition/Observation", "build a CodeableConcept", or needs RxNorm/LOINC/ICD-10/
SNOMED-coded resources. For packaging many resources into one transaction
Bundle, hand off to assembling-fhir-bundles. To check the result against US
Core, hand off to validating-us-core.
What OpenMed gives you (verified API)
OpenMed deliberately ships the purely mechanical pieces and leaves clinical judgement to you. The verified entry points:
# CodeableConcept builder — openmed/clinical/exporters/codeable_concept_simple.py
from openmed.clinical.exporters.codeable_concept_simple import (
system_uri, # vocab id -> canonical HL7 system URI
coding, # (system, code, display) -> Coding dict
codeable_concept, # [Coding, ...] -> CodeableConcept dict (deterministic order)
)
# Bundle + reference + OperationOutcome — openmed/clinical/exporters/fhir/
from openmed.clinical.exporters.fhir import (
to_bundle, # [resource, ...] -> R4 transaction Bundle
deterministic_fullurl, # (doc_id, index) -> stable urn:uuid
OperationOutcomeIssue, # issue dataclass
to_operation_outcome, # [issue, ...] -> OperationOutcome
from_validation_result, # validator result -> OperationOutcome
)
system_uri knows these vocabularies out of the box: rxnorm, icd-10-cm,
loinc, snomed, hpo, mesh (and passes through any http(s):// URI
unchanged). It is the single source of truth for vocab-id → system-URI mapping.
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.
- 12d ago First seen · 240 lines · 163 tokens per session scan A c7793d9cbcc7
exporting-to-fhir is a skill published in the GitHub repository maziyarpanahi/openmed (5,302 stars, last pushed today), licensed Apache-2.0. It adds 163 tokens to every session and 2,774 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
saelens
Train sparse autoencoders to interpret model features.
add-new-model
Use this skill when the user wants to add or port a new model architecture to MLX-VLM — mapping a Hugging Face modeltype to a new file under mlxvlm/models, writing the ModelConfig, matching layer/weight names, reusing a similar existing model, adding a test class, and validating the port. Covers vision-language…
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…
cli-inference
Use this skill when the user wants to run or debug MLX-VLM inference from the command line, including uv run mlxvlm.generate, image/audio/video inputs, local model paths, Hugging Face model IDs, deterministic repro commands, and CLI errors around processors, prompts, model loading, or missing weights.
convert-quantize
Use this skill when the user wants to convert a Hugging Face model to MLX or quantize/dequantize one with mlxvlm.convert, including bits and group size, quant modes (affine, mxfp4, nvfp4, mxfp8), RTN vs AWQ, mixed-bit recipes, dtype casts, calibration (text or multimodal), local vs Hub paths, revisions, uploading to…
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.