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 1Mangesh1/hipaa-guardian --skill healthcare-audit-loggergit clone --depth 1 https://github.com/1Mangesh1/hipaa-guardianWrote 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/1mangesh1/hipaa-guardian/healthcare-audit-logger)<a href="https://agentmods.dev/skills/1mangesh1/hipaa-guardian/healthcare-audit-logger"><img src="https://agentmods.dev/badge/skills/1mangesh1/hipaa-guardian/healthcare-audit-logger/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/1mangesh1/hipaa-guardian/healthcare-audit-logger"><img src="https://agentmods.dev/badge/skills/1mangesh1/hipaa-guardian/healthcare-audit-logger.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 | $0.00109 | $0.01486 |
| Opus 5 | $0.00055 | $0.00743 |
| Sonnet 5 | $0.00022 | $0.00297 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
healthcare-audit-logger 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 12d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Healthcare Audit Logger
Comprehensive HIPAA audit logging and event tracking skill for AI agents. Generates immutable audit trails for healthcare systems, tracks PHI access, monitors authentication events, and ensures compliance with 45 CFR §164.312(b) audit control requirements.
Capabilities
- Audit Log Generation - Create HIPAA-compliant audit logs with immutable records
- Event Classification - Categorize healthcare events (access, modification, deletion, export)
- PHI Access Tracking - Log all access to Protected Health Information
- Authentication Logging - Record login, logout, and privilege escalation events
- Modification Auditing - Track who changed what, when, and why for PHI records
- User Activity Monitoring - Follow user workflows and data interactions
- Timestamp Management - Synchronized UTC timestamps with tamper detection
- Retention Policies - Manage audit log retention per HIPAA requirements (6+ years)
- Log Export - Generate compliance reports and audit summaries
- Integrity Verification - Validate audit log authenticity and non-repudiation
Usage
/healthcare-audit-logger [command] [options]
Commands
init <config-file>- Initialize audit logging for a healthcare systemlog <event-type> <details>- Log a healthcare eventlog-access <user> <resource> <action>- Log PHI accesslog-auth <user> <event> <result>- Log authentication eventlog-modification <user> <resource> <change>- Log data modificationpolicy <retention-years>- Set audit log retention policyreport [date-range]- Generate audit reportverify <log-file>- Verify audit log integrityexport <format> <output>- Export audit logs (JSON, CSV, XML)
Options
--user <id>- User identifier--resource <path>- Resource being accessed (patient ID, record ID)--action <type>- Action type (read, write, delete, export)--reason <text>- Clinical reason for access--outcome <status>- Success or failure status--timestamp <iso8601>- Event timestamp (default: now)--retention <years>- Log retention period (default: 6 years per HIPAA)
What ships with it
3 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.
- 12d ago First seen · 152 lines · 109 tokens per session scan A 579dadacd286
healthcare-audit-logger is a skill published in the GitHub repository 1Mangesh1/hipaa-guardian (7 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 1,486 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
e-tax
A guide for entering Japanese tax-return data into the National Tax Agency's online tax-return preparation site, known as e-Tax, using browser automation.
brand-protection-shopify
Shopify/DTC brand protection toolkit. Detect counterfeit stores, unauthorized resellers, and trademark violations. Includes DMCA takedown templates, domain monitoring, and social media infringement detection. No API key required.
brand-protection-tiktok
TikTok Shop brand protection toolkit. Detect unauthorized sellers, counterfeit products, and affiliate abuse. Includes TikTok IP Protection reporting, influencer misuse detection, and complaint templates. No API key required.
brand-protection-ebay
Protect your brand from unauthorized sellers and counterfeits on eBay.
assess
A Japanese tax-filing assessment guide that asks about your income, family, and business situation to identify which tax returns you may need.
gather
A document-collection guide for Japanese tax filing that lists the documents needed for the filing type and explains where and how to obtain them.