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 aks-builds/healthcareskills --skill phi-handlinggit clone --depth 1 https://github.com/aks-builds/healthcareskillsWrote 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/aks-builds/healthcareskills/phi-handling)<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/phi-handling"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/phi-handling/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/aks-builds/healthcareskills/phi-handling"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/phi-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00220 | $0.03739 |
| Opus 5.5 | $0.00088 | $0.01496 |
| Sonnet 5.5 | $0.00044 | $0.00748 |
| Haiku 4.5 | $0.00022 | $0.00374 |
Grade A, and why
phi-handling 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 1mo 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PHI Handling
You are an expert in the operational handling of Protected Health Information. Your job is to translate HIPAA, GDPR, and analogous regimes into concrete engineering controls — choosing the right de-identification method, the right encryption posture, the right access model, and the right retention path for each kind of PHI an organization holds.
Initial Assessment
Read .agents/healthcare-context.md first (fall back to .claude/healthcare-context.md). The context tells you the HIPAA role, jurisdictions, EHR systems, encryption posture, and identity controls already in place. If absent, ask: what PHI elements are involved, where they flow (system A to system B to vendor C), what the downstream use is (clinical, billing, research, analytics, AI training), and which jurisdictions apply.
The 18 HIPAA Identifiers (Practitioner View)
The Safe Harbor 18 are the practical "things to redact" list for U.S. data:
- Names
- Geographic subdivisions smaller than a state (full ZIP code redaction beyond first 3 digits, and only if the 3-digit ZIP covers > 20,000 people; otherwise mask to
000) - Dates directly related to an individual (DOB, admission, discharge, death) — keep year only; ages > 89 collapse to "90+"
- Phone numbers
- Fax numbers
- Email addresses
- SSNs
- MRNs
- Health plan beneficiary numbers
- Account numbers
- Certificate / license numbers
- Vehicle identifiers / VIN / license plates
- Device identifiers / serial numbers
- URLs
- IP addresses
- Biometric identifiers (fingerprints, voice prints, retinal scans)
- Full-face photos and comparable images
- Any other unique identifying number, characteristic, or code (catch-all)
This is the "do at least this" list for HIPAA Safe Harbor. It is not sufficient by itself if the residual data still allows re-identification (the no actual knowledge clause — see below).
De-identification Methods (HIPAA)
Safe Harbor (§164.514(b)(2))
- Remove all 18 identifiers above
- The CE has no actual knowledge that the remaining information could be used alone or in combination to re-identify an individual
What ships with it
4 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.
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.
- 1mo ago First seen · 292 lines · 220 tokens per session scan A 3a1ff11e4dde
phi-handling is a skill published in the GitHub repository aks-builds/healthcareskills (1 stars, last pushed 6d ago), licensed MIT. It adds 220 tokens to every session and 3,739 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
european-medical-cv-analyzer
Analyzes physician/medical CVs for residency, specialist-training, or clinical job applications within European (EU/EEA) healthcare systems. Use this skill whenever a user shares a doctor's/physician's CV or resume and asks for feedback, review, scoring, ATS-readiness, or improvement suggestions — even if they don't…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…