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 checking-hipaa-compliancegit 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/checking-hipaa-compliance)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/checking-hipaa-compliance"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/checking-hipaa-compliance/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/checking-hipaa-compliance"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/checking-hipaa-compliance.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 | $0.00186 | $0.01997 |
| Opus 5 | $0.00093 | $0.00999 |
| Sonnet 5 | $0.00037 | $0.00399 |
| Haiku 4.5 | $0.00019 | $0.00200 |
Grade A, and why
checking-hipaa-compliance 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checking HIPAA compliance before deploying on PHI
Before any pipeline touches protected health information (PHI), the operating entity (a covered entity or its business associate) must have the HIPAA Privacy Rule and Security Rule safeguards in place. This skill walks a concrete pipeline against those requirements and emits a gap report: which controls are met, which are missing, and where OpenMed's on-device de-identification and signed audit trail satisfy a requirement.
The full control list — administrative, physical, and technical safeguards with their 45 CFR citations — is in references/hipaa-checklist.md. This skill is a self-assessment aid, not legal advice; a Privacy Officer signs off on compliance.
When to use
- You are about to deploy OpenMed (or any pipeline) on real PHI and need a go/no-go compliance review.
- You must document safeguards and minimum-necessary controls for an audit, a BAA, or a security questionnaire.
- You want to decide between Safe Harbor and Expert Determination de-identification and record the rationale.
- You need a reproducible gap report you can hand to a Privacy/Security Officer.
The two paths to "no longer PHI"
HIPAA recognizes two de-identification methods (45 CFR 164.514):
- Safe Harbor — remove all 18 identifier categories and have no actual knowledge the result can re-identify. Deterministic, the common path.
- Expert Determination — a qualified statistician certifies "very small" re-identification risk. Used when you must keep some quasi-identifiers.
OpenMed's deidentify(..., policy="hipaa_safe_harbor") targets the Safe Harbor
identifier set on-device, and deidentify(..., audit=True) produces a signed,
PHI-free AuditReport that documents what was removed — the evidence a Safe
Harbor attestation and a Security Rule audit control both want.
Quick start
import openmed
# A representative record from the pipeline (synthetic — never log real PHI).
sample = "John Doe (MRN 1234567), DOB 1970-01-15, seen 2024-03-02 in Boston."
# 1) De-identify on-device under the Safe Harbor policy.
result = openmed.deidentify(sample, method="replace", policy="hipaa_safe_harbor")
print(result.deidentified_text) # identifiers removed/surrogated
# 2) Produce the signed, no-PHI audit record for the compliance file.
report = openmed.deidentify(sample, policy="hipaa_safe_harbor", audit=True)
report.sign(b"<release-hmac-key-from-vault>", key_id="hipaa-2026")
# 3) Walk the checklist (see references/hipaa-checklist.md) and record gaps.
controls = {
"encryption_at_rest": True,
"encryption_in_transit": True,
"access_controls_rbac": True,
"audit_logging": True, # satisfied in part by the signed AuditReport
"minimum_necessary": False, # <-- gap: pipeline pulls full notes
"baa_in_place": True,
"deidentification_method": "safe_harbor",
}
gaps = [name for name, ok in controls.items() if not ok]
print("GAPS:", gaps)
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.
- 11d ago First seen · 144 lines · 186 tokens per session scan A d872ce5534c8
checking-hipaa-compliance is a skill published in the GitHub repository maziyarpanahi/openmed (5,290 stars, last pushed today), licensed Apache-2.0. It adds 186 tokens to every session and 1,997 once invoked, about $0.0009 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
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…
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.
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.
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.