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 setup-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/setup-openmed)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/setup-openmed"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/setup-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/setup-openmed"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/setup-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 | $0.00062 | $0.01562 |
| Opus 5 | $0.00031 | $0.00781 |
| Sonnet 5 | $0.00012 | $0.00312 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
setup-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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up an OpenMed de-identification policy
Use this skill before a de-identification pipeline when the privacy decisions are not already recorded. It creates a small policy document; it does not inspect, transform, upload, or retain clinical data. The setup is local-first, deterministic, and has no mandatory network call.
The output is a draft configuration contract, not a compliance certification, legal opinion, or guarantee of de-identification. A human must review and approve the draft before it controls a run.
When to use this skill
Use it when a project needs to turn implicit privacy choices into a reviewable
DEID-POLICY.md file. Use the focused de-identification skills afterward to
apply or audit the selected policy.
Do not use this skill to collect a note, dataset row, identifier, model output, secret, credential, or any other source payload. The setup questions accept policy choices only. Keep logs, exceptions, reports, and fixtures free of raw sensitive values.
Bounded decision contract
Collect these five decisions, one at a time. Do not invent a sixth field or silently choose a value. The value written to the artifact must be the lowercase canonical value in the right-hand column.
| Decision | Bounded choices (canonical value) |
|---|---|
| Jurisdiction or operating context | us, eu, canada, research, organization-defined |
| Recall floor | 0.90, 0.95, 0.99 |
| Surrogate strategy | mask, remove, replace, hash |
| Model policy | local-preinstalled, local-user-supplied, rules-only |
| Audit location | separate-local-directory, controlled-artifact-store, no-retention |
The jurisdiction choices are context labels, not findings that a law applies.
For example, us may be used for a US/HIPAA-context workflow and eu for an
EU/GDPR-context workflow, but the generated document must not claim that the
workflow is compliant. research and organization-defined require the
project's own governance review.
What ships with it
1 file beside SKILL.md 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.
- 5d ago First seen · 139 lines · 62 tokens per session scan A 9c56db90034b
setup-openmed is a skill published in the GitHub repository maziyarpanahi/openmed (5,263 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,562 once invoked, about $0.0003 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 2026-09-03.
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…
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…
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.
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.
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
meta-compliance-audit-bundle
Auditable compliance bundle: deep-research with citations → signable .docx report → read-only PDF archive → memory note of audit findings.