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 deidentifying-multilingual-textgit 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/deidentifying-multilingual-text)<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/deidentifying-multilingual-text"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/deidentifying-multilingual-text/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/deidentifying-multilingual-text"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/deidentifying-multilingual-text.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 | $0.00158 | $0.01769 |
| Opus 5 | $0.00079 | $0.00885 |
| Sonnet 5 | $0.00032 | $0.00354 |
| Haiku 4.5 | $0.00016 | $0.00177 |
Grade A, and why
deidentifying-multilingual-text 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
De-identifying multilingual text
OpenMed de-identifies clinical text in many languages, each with a dedicated
PII model, language-specific regex patterns (national IDs, phone formats), and a
locale-aware surrogate generator. Pass lang= to deidentify / extract_pii
and the right model, patterns, and fake-data tables are selected automatically.
Everything runs on-device.
When to use this skill
Use it whenever the source text is not English, or when surrogates must look native to the locale (a German note should get German-looking fake names and a valid-format Steuer-ID surrogate, not a US SSN).
Discover supported languages at runtime — don't hardcode
import openmed
from openmed.core.pii_i18n import SUPPORTED_LANGUAGES, get_patterns_for_language
print(sorted(SUPPORTED_LANGUAGES)) # query it; the set is the source of truth
# Language-appropriate default model for a code:
models = openmed.get_pii_models_by_language("es")
# Language-specific regex patterns (national IDs, phones, etc.):
patterns = get_patterns_for_language("de")
The set currently spans English plus European, South Asian, Middle Eastern, and
East Asian languages — but always read SUPPORTED_LANGUAGES rather than
trusting a number, since it changes as models ship. MCP exposes the same list
via openmed_list_pii_languages.
Quick start (Spanish)
import openmed
nota = (
"El paciente Carlos Hernández (DNI 12345678Z), nacido el 11/04/1979, "
"vive en Calle Mayor 5, Madrid. Teléfono 612 345 678."
)
result = openmed.deidentify(
nota,
lang="es", # selects the Spanish PII model + ES patterns
method="replace", # locale-native fake values
locale="es_ES", # Faker locale (defaults from lang via LANG_TO_LOCALE)
)
print(result.deidentified_text)
# El paciente [surrogate name] (DNI [surrogate]), nacido el [date], ...
For German, just switch the code:
befund = "Patientin Anna Müller, geb. 11.04.1979, Steuer-ID 12 345 678 901."
result = openmed.deidentify(befund, lang="de", method="replace")
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 · 145 lines · 158 tokens per session scan A f81604c19834
deidentifying-multilingual-text is a skill published in the GitHub repository maziyarpanahi/openmed (5,290 stars, last pushed today), licensed Apache-2.0. It adds 158 tokens to every session and 1,769 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
simple-english
Rewrite text to ASD-STE100 Simplified Technical English.
whisper
Transcribe and translate speech in 99 languages.
website-maintainer
Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.
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…
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.