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 agentmods add skills/maziyarpanahi/openmed/validating-us-corenpx skills add maziyarpanahi/openmed --skill validating-us-coregit 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/validating-us-core)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/validating-us-core"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/validating-us-core.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00134 | $0.01902 |
| Opus 5 | $0.00067 | $0.00951 |
| Sonnet 5 | $0.00027 | $0.00380 |
| Haiku 4.5 | $0.00013 | $0.00190 |
Grade A, and why
validating-us-core 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 3d 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.
curl -L -o validator_cli.jar \ How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validating US Core
Producing syntactically valid R4 (which exporting-to-fhir and
assembling-fhir-bundles do) is not the same as conforming to US Core — the
HL7 US realm profiles that EHRs (Epic, Cerner/Oracle Health) require for
ingestion and that USCDI mandates for certified exchange. This skill validates
OpenMed-produced FHIR against US Core before you submit it.
When to use
Use it as the gate right before submission, after you have assembled a Bundle. Reach for it when the user says "US Core", "USCDI", "must-support", "will Epic accept this", or "validate my FHIR". It is the conformance counterpart to the mechanical builders — OpenMed builds the JSON; the HL7 validator judges it.
Quick start: run the official validator
The reference implementation is the HL7 validator_cli.jar (the same engine
behind https://validator.fhir.org). Validate against the US Core package by IG:
# One-time: get the validator
curl -L -o validator_cli.jar \
https://github.com/hapifhir/org.hl7.fhir.core/releases/latest/download/validator_cli.jar
# Validate a resource/Bundle against the current US Core IG
java -jar validator_cli.jar condition.json \
-version 4.0.1 \
-ig hl7.fhir.us.core \
-tx https://tx.fhir.org # terminology server for code validation
-ig hl7.fhir.us.core pulls the current published US Core package; pin a
version (e.g. -ig hl7.fhir.us.core#6.1.0) for reproducible CI. The validator
exits non-zero on errors and prints issues with FHIRPath locations.
For ad-hoc checks without a JVM, paste the JSON into the public validator UI at https://validator.fhir.org (do not paste real PHI — validate synthetic or de-identified resources only).
Declare the profile you claim
US Core only validates against a profile if the resource claims it via
meta.profile. Add the canonical URL for the profile you target:
{
"resourceType": "Condition",
"meta": {
"profile": [
"http://hl7.org/fhir/us/core/StructureDefinition/us-core-condition-problems-health-concerns"
]
}
}
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.
- 3d ago First seen · 156 lines · 134 tokens per session scan A a1718cbe01eb
validating-us-core is a skill published in the GitHub repository maziyarpanahi/openmed (5,237 stars, last pushed today), licensed Apache-2.0. It adds 134 tokens to every session and 1,902 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
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.
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.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
add-service
Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
api-auth
Authentication, authorization, and multi-tenancy patterns for @cyanheads/mcp-ts-core. Use when implementing auth scopes on tools/resources, configuring auth modes (none/jwt/oauth), working with JWT/OAuth env vars, or understanding how tenantId flows through ctx.state.