agentsclimarketplace

Hipaa compliance

Skill rbr7/MedClawMini/skills/hipaa-compliance

Ensure HIPAA compliance when handling PHI (Protected Health Information). Use when writing code that accesses user health data, check-ins, journal entries, or any sensitive information. Activates for audit logging, data access, security events, and compliance questions.From its SKILL.md

Install
npx -y skills add rbr7/MedClawMini --skill hipaa-compliance

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.9 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

HIPAA Compliance for Recovery Coach

This skill helps you maintain HIPAA compliance when developing features that handle Protected Health Information (PHI).

What is PHI in This Application?

Data TypePHI StatusHandling
Check-in mood/cravingsPHIAudit all access
Journal entriesPHIAudit all access
Chat conversationsPHIAudit all access
User profile (name, email)PHIAudit modifications
Sobriety datePHIAudit access
Emergency contactsPHIAudit access
Usage analytics (aggregated)NOT PHINo audit needed
Page views (no content)NOT PHINo audit needed

Audit Logging Requirements

When to Log

Always log these operations:

  • Viewing any PHI (check-ins, journal, messages)
  • Creating/updating/deleting PHI
  • Exporting user data
  • Admin access to user information
  • Failed authentication attempts
  • Security events (rate limiting, unauthorized access)

How to Log

Use the audit logging utilities in src/lib/hipaa/audit.ts:

import {
  logPHIAccess,
  logPHIModification,
  logSecurityEvent,
  logAdminAction
} from '@/lib/hipaa/audit';

// Viewing PHI
await logPHIAccess(
  userId,
  'checkin',        // targetType
  checkinId,        // targetId
  AuditAction.PHI_VIEW
);

// Modifying PHI
await logPHIModification(
  userId,
  'journal',
  journalId,
  AuditAction.PHI_UPDATE,
  { field: 'content' }  // Never include actual content!
);

// Security event
await logSecurityEvent(
  userId,
  AuditAction.RATE_LIMIT,
  { path: '/api/chat', attempts: 60 }
);

// Admin action
await logAdminAction(
  adminId,
  AuditAction.ADMIN_USER_VIEW,
  'user',
  targetUserId
);

Data Sanitization

Never Log These Fields

The audit system automatically sanitizes, but be explicit:

// BAD - Contains PHI
await logPHIAccess(userId, 'journal', id, action, {
  content: journalEntry.content  // NEVER DO THIS
});

// GOOD - Only metadata
await logPHIAccess(userId, 'journal', id, action, {
  wordCount: journalEntry.content.length,
  hasAttachments: false
});

Sanitized Fields (Auto-Redacted)

  • password, token, secret, key
  • authorization, cookie, session
  • credential, content, message, notes

Session Security Requirements

From src/lib/auth.ts:

  • Session timeout: 15 minutes of inactivity (HIPAA requirement)
  • Max session: 8 hours absolute maximum
  • Failed login lockout: 5 attempts = 30 minute ban
  • Password requirements: 12+ chars, mixed case, numbers, special chars

Code Patterns

API Route with Audit Logging

import { getSession, requireAuth } from '@/lib/auth';
import { logPHIAccess } from '@/lib/hipaa/audit';

export async function GET(request: Request) {
  const session = await getSession();
  if (!session) {
    return Response.json({ error: 'Unauthorized' }, { status: 401 });
  }

  // Fetch the data
  const data = await fetchUserData(session.userId);

  // Log the access
  await logPHIAccess(
    session.userId,
    'userdata',
    session.userId,
    AuditAction.PHI_VIEW
  );

  return Response.json(data);
}

Component with PHI Access

'use client';

import { useEffect } from 'react';

export function JournalViewer({ entryId }: { entryId: string }) {
  useEffect(() => {
    // Log view on mount (server-side preferred, but client backup)
    fetch('/api/audit/log', {
      method: 'POST',
      body: JSON.stringify({
        action: 'PHI_VIEW',
        targetType: 'journal',
        targetId: entryId
      })
    });
  }, [entryId]);

  // ... render
}

Compliance Checklist

Before shipping any feature that touches PHI:

  • All PHI access is audit logged
  • No PHI content in logs (only IDs and metadata)
  • Data access requires authentication
  • Admin access has separate audit trail
  • Failed access attempts are logged
  • Data export includes audit entry
  • Sensitive fields are encrypted at rest
  • Session timeout is enforced

Audit Log Retention

  • Minimum: 6 years (HIPAA requirement)
  • Format: Raw logs for 1 year, compressed thereafter
  • Location: audit_log table in database
  • Export: Encrypted exports for compliance audits

Emergency Access (Break Glass)

For emergency situations, use break-glass access:

import { requestBreakGlassAccess } from '@/lib/hipaa/break-glass';

// This creates enhanced audit trail
const access = await requestBreakGlassAccess(
  adminId,
  targetUserId,
  'Emergency support required - user reported crisis'
);

Break glass access:

  • Requires written justification
  • Creates permanent audit record
  • Triggers alert to compliance officer
  • Must be reviewed within 24 hours

Resources

  • HIPAA Security Rule: 45 C.F.R. § 164.312
  • Audit controls standard: 45 C.F.R. § 164.312(b)
  • Incident response plan: docs/INCIDENT-RESPONSE-PLAN.md
  • Security documentation: docs/SECURITY-HARDENING.md

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most regulatory compliance skills give in ~1.2k tokens

Counted across 187 of the 188 authors here whose files we hold, read 2026-08-07

  • Retain audit logs for at least 6 yearshere, and in 10 of 187, across 8 files
  • Remove or alter HIPAA identifiersin 9 of 187, across 4 files
  • Document patient consent for publicationin 9 of 187, across 4 files
  • Stamp files after creating or modifying themin 8 of 187, across 2 files
  • Inspect detailed trust scores before modifying filesin 8 of 187, across 2 files
  • Check root account MFA statusin 8 of 187, across 2 files
  • Check for unused credentials over ninety days oldin 8 of 187, across 2 files
  • Check IAM users for MFA enforcementin 8 of 187, across 2 files
  • Verify CloudTrail is enabled and loggingin 8 of 187, across 2 files
  • Check S3 bucket access logging configurationin 8 of 187, across 2 files
  • Use standardized reporting templatesin 8 of 187, across 3 files
  • Read existing metadata before modifying filesin 8 of 187, across 2 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,790. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.