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.
git 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/plugins/maziyarpanahi/openmed/openmed-skills)<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>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.
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/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.
- Skill assembling-fhir-bundles A 131 tokens
- Skill auditing-part11-trails A 222 tokens
- Skill batch-processing-clinical-text A 161 tokens
- Skill bridging-presidio-and-spacy A 154 tokens
- Skill coding-hcc-risk-adjustment A 200 tokens
- Skill detecting-pv-signals A 218 tokens
- Skill exporting-to-fhir A 163 tokens
- Skill reporting-adverse-events A 195 tokens
- Skill structuring-radiology-reports A 195 tokens
- Skill annotating-variants A 179 tokens
- Skill auditing-deid-leakage A 171 tokens
- Skill auditing-deidentification-runs A 155 tokens
- Skill auditing-safe-harbor-checklist A 146 tokens
- Skill authoring-model-cards A 135 tokens
- Skill benchmarking-clinical-ner A 164 tokens
- Skill building-gold-corpus A 159 tokens
- Skill building-patient-timelines A 154 tokens
- Skill checking-hipaa-compliance A 186 tokens
- Skill choosing-openmed-models A 134 tokens
- Skill coding-icd10 A 209 tokens
- Skill configuring-privacy-policies A 143 tokens
- Skill defining-cohort-phenotypes A 191 tokens
- Skill deidentifying-clinical-text A 144 tokens
- Skill deidentifying-multilingual-text A 158 tokens
- Skill deploying-openmed-mcp A 186 tokens
- Skill enforcing-nophi-logging A 139 tokens
- Skill etl-to-omop-cdm A 176 tokens
- Skill evaluating-with-leakage-gates A 158 tokens
- Skill exporting-bulk-fhir A 151 tokens
- Skill extracting-clinical-entities A 118 tokens
- Skill extracting-dicom-metadata A 147 tokens
- Skill extracting-lab-tables A 210 tokens
- Skill extracting-pii-entities A 141 tokens
- Skill extracting-sdoh A 163 tokens
- Skill fetching-fhir-resources A 166 tokens
- Skill gating-deid-leakage A 152 tokens
- Skill generating-synthetic-surrogates A 145 tokens
- Skill ingesting-clinical-documents A 151 tokens
- Skill linking-umls-concepts A 203 tokens
- Skill loading-openmed-models A 118 tokens
- Skill mapping-loinc A 197 tokens
- Skill mapping-to-snomed A 205 tokens
- Skill mining-pubmed-literature A 172 tokens
- Skill normalizing-rxnorm A 187 tokens
- Skill parsing-ccda-documents A 152 tokens
- Skill parsing-hl7v2-messages A 169 tokens
- Skill parsing-lab-values A 142 tokens
- Skill parsing-trial-eligibility A 152 tokens
- Skill pseudonymizing-for-gdpr A 158 tokens
- Skill querying-openfda-labels A 189 tokens
- Skill querying-terminology-service A 166 tokens
- Skill reconciling-problem-lists A 154 tokens
- Skill reidentifying-text A 131 tokens
- Skill resolving-clinical-context A 170 tokens
- Skill reviewing-reidentification-risk A 177 tokens
- Skill running-openmed-ondevice A 175 tokens
- Skill running-zeroshot-ner A 133 tokens
- Skill scaffolding-smart-on-fhir A 151 tokens
- Skill searching-clinicaltrials A 171 tokens
- Skill segmenting-clinical-sections A 163 tokens
- Skill shifting-clinical-dates A 135 tokens
- Skill summarizing-clinical-notes A 129 tokens
- Skill validating-us-core A 134 tokens
- Skill auditing-subgroup-fairness A 148 tokens
- Skill building-with-openmed A 85 tokens
- Skill computing-ecqms A 161 tokens
- Skill generating-synthea-data A 144 tokens
- Skill benchmark-pii-recall A 57 tokens
- Skill extract-clinical-entities-to-fhir A 69 tokens
- Skill deidentify-a-dataset A 68 tokens
- Skill pick-a-pii-model A 64 tokens
- Skill ask-openmed A 69 tokens
- Skill setup-openmed A 62 tokens
- Skill serving-openmed-rest-api B 168 tokens
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.
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.
- 4d ago First seen · 82 lines scan A be229c18dc69
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.
Other plugins, from other repositories
healthchain
Build healthcare AI services with HealthChain: FHIR gateways, validated FHIR resources, and typed agent tools.
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.
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.
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…
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…
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…