openmed-skills

openmed-skills is a plugin for Claude Code from maziyarpanahi/openmed. Its manifest loads nothing; the 74 skills it bundles cost 11,398 tokens per session together, scanned A, original, Apache-2.0.

A collection of healthcare tools for removing patient identifiers, finding medical terms, exporting FHIR records, and checking privacy and model quality.

In plain words
What is it for?
De-identifying medical data, extracting clinical entities, building patient timelines and FHIR bundles, and evaluating healthcare models and datasets.
Why use it?
It supports clinical text processing while checking for leaked personal information and other workflow risks.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit De-identifying medical data, extracting clinical entities, building patient timelines and FHIR bundles, and evaluating healthcare models and datasets.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add maziyarpanahi/openmed/plugin install openmed-skills
About the project

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.

maziyarpanahi/openmed · 5,250 stars · on GitHub · openmed.life

Install

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.

Clone the repo
git clone --depth 1 https://github.com/maziyarpanahi/openmed

Made for: Claude Code.

Wrote 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.

agentmods badge for openmed-skills

README.md
[![agentmods](https://agentmods.dev/badge/plugins/maziyarpanahi/openmed/openmed-skills.svg)](https://agentmods.dev/plugins/maziyarpanahi/openmed/openmed-skills)
Your own site
<a href="https://agentmods.dev/plugins/maziyarpanahi/openmed/openmed-skills"><img src="https://agentmods.dev/badge/plugins/maziyarpanahi/openmed/openmed-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 74 skills cost 11,398 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

openmed-skills 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 4d 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.

.claude-plugin/marketplace.json#openmed-skills · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "openmed-skills",
  "description": "De-identify PHI, run clinical NER, export FHIR, evaluate with leakage gates, and the healthcare workflows around them.",
  "source": "./",
  "strict": false,
  "skills": [
    "./skills/annotating-variants",
    "./skills/ask-openmed",
    "./skills/assembling-fhir-bundles",
    "./skills/auditing-deid-leakage",
    "./skills/auditing-deidentification-runs",
    "./skills/auditing-part11-trails",
    "./skills/auditing-safe-harbor-checklist",
    "./skills/auditing-subgroup-fairness",
    "./skills/authoring-model-cards",
    "./skills/batch-processing-clinical-text",
    "./skills/benchmark-pii-recall",
    "./skills/benchmarking-clinical-ner",
    "./skills/bridging-presidio-and-spacy",
    "./skills/building-gold-corpus",
    "./skills/building-patient-timelines",
    "./skills/building-with-openmed",
    "./skills/checking-hipaa-compliance",
    "./skills/choosing-openmed-models",
    "./skills/coding-hcc-risk-adjustment",
    "./skills/coding-icd10",
    "./skills/computing-ecqms",
    "./skills/configuring-privacy-policies",
    "./skills/defining-cohort-phenotypes",
    "./skills/deidentify-a-dataset",
    "./skills/deidentifying-clinical-text",
    "./skills/deidentifying-multilingual-text",
    "./skills/deploying-openmed-mcp",
    "./skills/detecting-pv-signals",
    "./skills/enforcing-nophi-logging",
    "./skills/etl-to-omop-cdm",
    "./skills/evaluating-with-leakage-gates",
    "./skills/exporting-bulk-fhir",
    "./skills/exporting-to-fhir",
    "./skills/extract-clinical-entities-to-fhir",
    "./skills/extracting-clinical-entities",
    "./skills/extracting-dicom-metadata",
    "./skills/extracting-lab-tables",
    "./skills/extracting-pii-entities",
    "./skills/extracting-sdoh",
    "./skills/fetching-fhir-resources",
    "./skills/gating-deid-leakage",
    "./skills/generating-synthea-data",
    "./skills/generating-synthetic-surrogates",
    "./skills/ingesting-clinical-documents",
    "./skills/

Read the full file on GitHub · 82 lines

Contents

What it installs

The manifest is a name and a version. 74 skills travel with it, and installing the plugin installs all of them — 11,398 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#openmed-skills 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.

Changes

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.

  1. 4d ago First seen · 82 lines scan A be229c18dc69

Subscribe to this mod's changes

openmed-skills is a plugin published in the GitHub repository maziyarpanahi/openmed (5,250 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

Related

Other plugins, from other repositories

healthchain

Build healthcare AI services with HealthChain: FHIR gateways, validated FHIR resources, and typed agent tools.

healthchainai/HealthChain · not measured

neuroarxiv

Grounds a coding agent's architecture decisions in real arXiv prior art: parallel isolated reads of papers found category-wise (divergence), converged into one recommended path with citations, a first step, and known failure modes to avoid.

UditAkhourii/neuroarxiv · not measured

animal-geneticist-breeder

Reasons from additive genetic variance, response to selection (R = i h sigmaA), accuracy, and inbreeding depression through REML/BLUP and ssGBLUP pipelines (BLUPF90, ASReml, WOMBAT), economic selection indices, optimum-contribution mate allocation, and Interbull MACE while treating confounded contemporary groups, pred.

K-Dense-AI/scientific-agents · not measured

carbon-cycle-scientist

Reasons from carbon mass balance across reservoirs and timescales, sign conventions, and budget closure through the Global Carbon Budget protocol, ONEFlux/REddyProc eddy-covariance processing, atmospheric inversions (CarbonTracker, CAMS, GEOS-Chem), Δ¹⁴C/δ¹³C isotopic partitioning, and ILAMB model evaluation while…

K-Dense-AI/scientific-agents · not measured

aerospace-engineer

Reasons from margin-managed factors of safety, mass properties, and the analysis-test-similarity V&V hierarchy through FUN3D/SU2 CFD, NASTRAN/Abaqus FEA, JSBSim/Simulink 6-DOF, and FAR/CS, DO-178C, and NASA-STD compliance while treating flutter, buckling, inlet distortion, mass growth, and single-point failures as…

K-Dense-AI/scientific-agents · not measured

agricultural-engineer

Reasons from mass, energy, and momentum balances on variable biological media through ET-based scheduling, psychrometric grain-drying balances, ASABE D497 draft estimates, EPANET pipe networks, and RTK-GNSS/ISOBUS precision-ag validation while treating soil compaction, clogged drip emitters, grain-bin hotspots, GPS…

K-Dense-AI/scientific-agents · not measured