pseudonymizing-for-gdpr

pseudonymizing-for-gdpr is a skill for Claude Code, Codex from maziyarpanahi/openmed. It costs 158 tokens per session (1,884 once invoked), scanned A, original, Apache-2.0.

A procedure for replacing identifying details in clinical or personal text while keeping a separate key that can restore the original identities under authorization. Under GDPR, pseudonymized data can still identify people with the key and therefore remains personal data.

In plain words
What is it for?
Use it to prepare personal or health data for work, preserve links across longitudinal records, recontact a patient, or respond to an access request. It covers the replacement map, separate key storage, and authorized re-linking.
Why use it?
It reduces exposure of names and other identifiers while preserving the ability to reconnect records later. Keeping the re-linking key separate limits who can restore identities and supports controlled handling of sensitive EU data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the openmed-skills plugin — 74 skills shipped together

Good fit Use it to prepare personal or health data for work, preserve links across longitudinal records, recontact a patient, or respond to an access request. It covers the replacement map, separate key storage, and authorized re-linking.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr
About the project

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.

maziyarpanahi/openmed · 5,282 stars · on GitHub · openmed.life

Install

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.

Any agent
npx skills add maziyarpanahi/openmed --skill pseudonymizing-for-gdpr
Clone the repo
git clone --depth 1 https://github.com/maziyarpanahi/openmed

Made for: Claude Code, Codex.

Or install openmed-skills, the plugin that ships this one along with the rest of its 74 skills.

Wrote 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.

agentmods badge for pseudonymizing-for-gdpr

README.md
[![agentmods](https://agentmods.dev/badge/skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr/github.svg)](https://agentmods.dev/skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr)
Your own site
<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr/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.

agentmods 80×15 button for pseudonymizing-for-gdpr

Your own site · 80×15
<a href="https://agentmods.dev/skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr"><img src="https://agentmods.dev/badge/skills/maziyarpanahi/openmed/pseudonymizing-for-gdpr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00158 $0.01884
Opus 5 $0.00079 $0.00942
Sonnet 5 $0.00032 $0.00377
Haiku 4.5 $0.00016 $0.00188

Measured 10d ago against content hash a4df912d7860, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pseudonymizing-for-gdpr 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 10d 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.

skills/pseudonymizing-for-gdpr/SKILL.md · 144 lines

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.

Pseudonymizing for GDPR

Pseudonymization under the GDPR (Art. 4(5)) means processing personal data so it "can no longer be attributed to a specific data subject without the use of additional information" — provided that additional information (the re-linkage key) is "kept separately and is subject to technical and organisational measures." Crucially, pseudonymized data is still personal data (Recital 26): re-linkage is possible, so GDPR still applies. This is the opposite of anonymization, where re-identification is irreversibly prevented and the data falls outside the GDPR.

OpenMed implements this with a single reversible de-identification pass plus a mapping you store away from the data. This skill covers producing that mapping, vaulting the key separately, and re-linking under authorization.

When to use

  • You process EU residents' personal or special-category health data (Art. 9) and need a lawful, reversible safeguard rather than full anonymization.
  • You need to keep a record-linkage capability (e.g. to recontact a patient, reconcile longitudinal records, or honor a Subject Access Request) but must separate the linkage key from the working dataset.
  • A reviewer asks for the pseudonymization-vs-anonymization distinction in writing, or for the ENISA-style "additional information kept separately" control to be demonstrable.

Do not use this when the goal is irreversible anonymization for open release — there, drop the mapping entirely and gate residual risk with reviewing-reidentification-risk. Pseudonymization keeps a key; anonymization must not.

Quick start

import openmed

# Synthetic record — never run this skill's examples on real PHI.
note = "Patient Maria Schmidt (ID 4471) seen 2024-03-02; contact [email protected]."

result = openmed.deidentify(
    note,
    method="replace",                 # realistic surrogates, not [LABEL] holes
    policy="gdpr_pseudonymization",   # bundled GDPR profile
    keep_mapping=True,                # produce the reversible re-linkage map
    consistent=True,                  # same input -> same surrogate in the doc
    seed=20240302,                    # cross-run reproducibility of surrogates
)

pseudonymized_text = result.deidentified_text   # safe to process / analyze
relink_key = result.mapping                      # surrogate -> original; SECRET

Read the full file on GitHub · 144 lines

Changes

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.

  1. 10d ago First seen · 144 lines · 158 tokens per session scan A a4df912d7860

Subscribe to this mod's changes

pseudonymizing-for-gdpr is a skill published in the GitHub repository maziyarpanahi/openmed (5,282 stars, last pushed today), licensed Apache-2.0. It adds 158 tokens to every session and 1,884 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.

Related

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…

Blaizzy/mlx-vlm · 74 tokens

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.

Blaizzy/mlx-vlm · 67 tokens

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…

Blaizzy/mlx-vlm · 99 tokens

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.

Blaizzy/mlx-vlm · 80 tokens

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.

synthetic-sciences/openscience · 43 tokens

meta-compliance-audit-bundle

Auditable compliance bundle: deep-research with citations → signable .docx report → read-only PDF archive → memory note of audit findings.

opensquilla/opensquilla · 37 tokens