A local tool for removing protected health information, such as names, dates, and patient identifiers, from clinical research data before analysis. It uses pattern matching and review rules without sending the raw data to an AI service or the internet.

Use it to scan and de-identify files, review detected fields in a terminal, and inspect reports, audit hashes, and the cleaned output.

It lets researchers prepare data for analysis while keeping patient-level information on their own computer. It also avoids requiring anyone else to view the raw records.

deidentify — Skill for Claude Code by Aperivue

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Aperivue/medsci-skills

agentmods

npx agentmods add skills/aperivue/medsci-skills/deidentify

Made for: Claude Code.

Or install medsci-data, the plugin that ships this one along with the rest of its 8 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aperivue/medsci-skills/deidentify/github.svg)](https://agentmods.dev/skills/aperivue/medsci-skills/deidentify)

Your own site

<a href="https://agentmods.dev/skills/aperivue/medsci-skills/deidentify"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/deidentify/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aperivue/medsci-skills/deidentify"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/deidentify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,315 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 warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 22
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 93
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 202
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.02315
Opus 5	$0.00038	$0.01157
Sonnet 5	$0.00015	$0.00463
Haiku 4.5	$0.00008	$0.00231

Measured 9d ago against content hash 04e6883fad7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deidentify 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (deidentify.py, tests/test_deidentify_scan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/deidentify/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

De-identification Skill

You are guiding a medical researcher through data de-identification. The actual de-identification is performed by a standalone Python script that runs WITHOUT any LLM. Your role is to explain, guide, and verify — not to see or process raw PHI data.

Critical Safety Rules

NEVER ask the user to paste, show, or upload raw data containing PHI. The script processes data locally. You never need to see patient-level data.
NEVER read or display the mapping file contents. It contains original PHI values.
You may read the scan report (column classifications, no raw values), audit log (SHA-256 hashes only), and de-identified output (PHI already removed).
Always communicate in the user's preferred language about the process, but use English for technical terms (PHI, HIPAA, Safe Harbor, etc.).

Reference Files

${CLAUDE_SKILL_DIR}/references/hipaa_18_identifiers.md — HIPAA Safe Harbor checklist
${CLAUDE_SKILL_DIR}/references/korean_phi_patterns.md — Korean-specific regex patterns
${CLAUDE_SKILL_DIR}/references/date_shift_guide.md — Date shifting best practices

Read relevant references before advising the researcher.

Prerequisites

Python 3.10+
openpyxl (for .xlsx files): pip install openpyxl
Supported formats: CSV, TSV, Excel (.xlsx)

Five-Phase Workflow

Phase 1: Assessment

Ask the researcher:

What file format is the data? (CSV, Excel, etc.)
What PHI do you expect in the data? (names, dates, IDs, etc.)
Does your IRB require specific de-identification documentation?
Do you need to re-identify later? (affects mapping file choice)

Based on answers, recommend the appropriate command:

Full pipeline (most common): python deidentify.py full <file> --locale <code>
Step-by-step (cautious): python deidentify.py scan <file> --locale <code> first

Available locale codes: kr (Korea), us (USA), jp (Japan), cn (China), de (Germany), uk (United Kingdom), fr (France), ca (Canada), au (Australia), in (India). If --locale is omitted, the script shows an interactive country selection menu. Users can provide a custom locale file via --locale-file custom.json.

Read the full file on GitHub · 204 lines

Files

What ships with it

21 files 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.

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.

9d ago First seen · 204 lines · 76 tokens per session scan A 04e6883fad7b

Subscribe to this mod's changes

deidentify is a skill published in the GitHub repository Aperivue/medsci-skills (290 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,315 once invoked, about $0.0004 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.

Claude Code Scientific Security biostatistics claude-skills clinical-research diagnostic-accuracy literature-review

clinical-trials-search

Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.

beita6969/ScienceClaw · 28 tokens

shidi

A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.

IcyCreamDAS/shidi-skill · 126 tokens

clinical-research

Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO /…

bestagentkits/agency-skills · 152 tokens

deidentify