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 building-with-openmedgit 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/building-with-openmed)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/building-with-openmed"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/building-with-openmed/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/building-with-openmed"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/building-with-openmed.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 | $0.00085 | $0.01545 |
| Opus 5 | $0.00043 | $0.00772 |
| Sonnet 5 | $0.00017 | $0.00309 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
building-with-openmed 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 11d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building with OpenMed
OpenMed is an Apache-2.0, local-first Python library for clinical and biomedical NLP. Models download once from the Hugging Face Hub and then run fully on-device — no network calls, no telemetry, no raw PHI in logs, caches, or temp files. This skill is the map: it tells you what OpenMed can do and which focused skill (or API) to reach for next.
When to use this skill
Use it to scope a task and pick an entry point. For the actual work, hand off to the focused OpenMed skills (each is grounded in the real API):
| Task | Skill / API |
|---|---|
| Find and load a model | loading-openmed-models, choosing-openmed-models |
| Run clinical/biomedical NER | extracting-clinical-entities (openmed.analyze_text) |
| Zero-shot NER (no fine-tune) | running-zeroshot-ner (openmed zero) |
| Remove / mask PHI | deidentifying-clinical-text (openmed.deidentify) |
| Detect PHI spans only | extracting-pii-entities (openmed.extract_pii) |
| Restore masked PHI | reidentifying-text (openmed.reidentify) |
| Pick a privacy policy | configuring-privacy-policies (7 bundled profiles) |
| Non-English PHI | deidentifying-multilingual-text |
| Signed, no-PHI audit | auditing-deidentification-runs (audit=True) |
| Negation / temporality | resolving-clinical-context (openmed.clinical) |
| Evaluate with leakage gates | evaluating-with-leakage-gates (openmed.eval) |
| FHIR R4 export | exporting-to-fhir (openmed.interop) |
| Serve REST / MCP | serving-openmed-rest-api, deploying-openmed-mcp |
| Run on Apple Silicon / edge | running-openmed-ondevice (MLX / CoreML / ONNX) |
Install
pip install openmed # core: NER + de-identification
pip install "openmed[hf]" # add Hugging Face model downloads
pip install "openmed[mcp]" # Model Context Protocol server
pip install "openmed[service]" # FastAPI REST service
pip install "openmed[mlx]" # Apple Silicon acceleration
pip install "openmed[presidio]" # Microsoft Presidio bridge
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.
- 11d ago First seen · 130 lines · 85 tokens per session scan A bb217d704683
building-with-openmed is a skill published in the GitHub repository maziyarpanahi/openmed (5,290 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,545 once invoked, about $0.0004 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…
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.
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.