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 assembling-fhir-bundlesgit 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/assembling-fhir-bundles)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/assembling-fhir-bundles"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/assembling-fhir-bundles/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/assembling-fhir-bundles"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/assembling-fhir-bundles.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 | $0.00131 | $0.02222 |
| Opus 5 | $0.00066 | $0.01111 |
| Sonnet 5 | $0.00026 | $0.00444 |
| Haiku 4.5 | $0.00013 | $0.00222 |
Grade A, and why
assembling-fhir-bundles 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assembling FHIR Bundles
A FHIR server ingests one transaction Bundle, not loose resources, and the
resources inside it must cross-reference each other (Condition.subject →
Patient, Observation.encounter → Encounter, DiagnosticReport.result →
Observation). OpenMed ships a deterministic, mechanical Bundle assembler —
openmed.clinical.exporters.fhir.to_bundle — that wraps the resources you built
in exporting-to-fhir into a valid R4 Bundle and wires up the references.
When to use
Use after you have a list of standalone resources from exporting-to-fhir and
the destination is a FHIR server. Reach for it when the user says "build a
Bundle", "transaction", "POST these resources", or needs internal references
resolved. To check the Bundle against US Core, hand off to validating-us-core.
What OpenMed gives you (verified API)
from openmed.clinical.exporters.fhir import to_bundle, deterministic_fullurl
bundle = to_bundle(
resources, # Sequence[Mapping] each with a resourceType
doc_id="note-2024-03-02-001", # seeds stable urn:uuid fullUrls
bundle_type="transaction", # "transaction" | "batch" | "collection" | ...
)
to_bundle does exactly three things, and never synthesises or validates:
- Deterministic
fullUrl. Each resource gets aurn:uuidseeded bydoc_id+ its index, so the same input always produces byte-identical output (golden-test friendly). You can pre-compute the same urn withdeterministic_fullurl(doc_id, index). - Reference rewriting. Any
{"reference": "ResourceType/id"}whose target is present in the Bundle is repointed at that resource'sfullUrl. References to resources absent from the Bundle (e.g. a Patient removed by de-identification) are left untouched — no dangling internal refs. - Request blocks. For
transaction/batchbundles each entry gets arequestblock ({"method": "POST", "url": "<ResourceType>"}) so the server knows to create it.
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 · 194 lines · 131 tokens per session scan A 651f5e1cf296
assembling-fhir-bundles is a skill published in the GitHub repository maziyarpanahi/openmed (5,290 stars, last pushed yesterday), licensed Apache-2.0. It adds 131 tokens to every session and 2,222 once invoked, about $0.0007 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…
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.
protocolsio-integration
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io…
healthchain
Use when building, debugging, or deploying a Python service that touches FHIR resources, EHR APIs, CDS Hooks, clinical documents, or patient data — including writing model or agent output back into a patient record, connecting to Epic/Cerner/Medplum, or serving FHIR tools to an agent over MCP or LangChain.
hl7-v2
When the user wants to design, parse, generate, or troubleshoot HL7 v2.x pipe-delimited messages. Use when the user mentions "HL7 v2," "HL7 2.x," "ADT," "ORM," "ORU," "MDM," "SIU," "DFT," "MSH," "PID," "OBX," "OBR," "ACK," "NAK," "MLLP," "Mirth," "NextGen Connect Integration Engine," "Rhapsody," "Cloverleaf,"…
healthcare-fhir
Design RESTful clinical data exchanges using HL7 FHIR standards.