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 bridging-presidio-and-spacygit 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/bridging-presidio-and-spacy)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/bridging-presidio-and-spacy"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/bridging-presidio-and-spacy/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/bridging-presidio-and-spacy"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/bridging-presidio-and-spacy.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 | $0.00154 | $0.02193 |
| Opus 5 | $0.00077 | $0.01097 |
| Sonnet 5 | $0.00031 | $0.00439 |
| Haiku 4.5 | $0.00015 | $0.00219 |
Grade A, and why
bridging-presidio-and-spacy 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 13d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridging Presidio, spaCy & LangChain
OpenMed interoperates with the dominant PII/NLP ecosystems through a single,
lazy adapter registry: openmed.interop. Adapters live behind explicit
imports, so importing openmed never drags in Presidio, spaCy, or LangChain —
each is an optional extra you install only when you need that bridge.
When to use
Reach for a bridge when:
- you already run Microsoft Presidio and want OpenMed's clinical PII recall on top (or to feed OpenMed spans back into Presidio's anonymizer);
- you have a spaCy pipeline and want OpenMed PII spans on the
Doc; - you build LangChain chains and want to redact PHI before text reaches an LLM (the on-device guardrail in front of a cloud model);
- you need OpenMed's de-identification reachable from an existing framework
instead of rewriting the pipeline around
openmed.deidentify.
The lazy adapter registry (verified)
import openmed.interop as interop
interop.available_adapters()
# ('cda', 'hl7v2', 'langchain', 'presidio', 'spacy')
spec = interop.adapter_spec("presidio")
# AdapterSpec(name='presidio', module='openmed.interop.presidio',
# extra='presidio', description='Presidio RecognizerResult adapter')
mod = interop.get_adapter("presidio") # imports openmed.interop.presidio
# Attribute access also works lazily:
openmed.interop.presidio # same module, imported on first touch
available_adapters() and adapter_spec() never import the adapter module, so
they are safe to call for discovery even without the extra installed.
get_adapter(name) (and attribute access) triggers the import — and the
adapter's own optional dependency.
Install only the extra you need:
pip install "openmed[presidio]" # Presidio RecognizerResult adapter
pip install "openmed[spacy]" # spaCy openmed_deid component
pip install "openmed[langchain]" # LangChain redaction runnable
# cda and hl7v2 adapters ship in core (no extra) — see their own skills
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.
- 13d ago First seen · 196 lines · 154 tokens per session scan A 63416d2de3c5
bridging-presidio-and-spacy is a skill published in the GitHub repository maziyarpanahi/openmed (5,302 stars, last pushed today), licensed Apache-2.0. It adds 154 tokens to every session and 2,193 once invoked, about $0.0008 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
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.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
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…
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.