medharness: Skill for Claude Code

.claude/skills/compliance-review/SKILL.md

compliance-review is a skill for Claude Code from charliehzm/medharness. It costs 205 tokens per session (2,073 once invoked), scanned A, original, Apache-2.0.

A compliance check for a code change that already passed functional and code review. It looks for exposed health data, unsafe paths from untrusted text to AI models, unapproved model calls, and test data that could identify real patients.

In plain words
What is it for?
Use it before final archiving to produce a COMPLIANCE_REPORT.md covering protected health information, prompt injection, model allowlists, and test-data lineage.
Why use it?
Functional tests show whether intended behavior works, but they may miss privacy and security problems. This review checks what the change could expose or do unintentionally.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is charliehzm/medharness's own configuration. It tells Claude Code how to work on medharness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything medharness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to charliehzm/medharness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/charliehzm/medharness/main/.claude/skills/compliance-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/charliehzm/medharness

Made for: Claude Code.

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 compliance-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/charliehzm/medharness/compliance-review/github.svg)](https://agentmods.dev/skills/charliehzm/medharness/compliance-review)
Your own site
<a href="https://agentmods.dev/skills/charliehzm/medharness/compliance-review"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/compliance-review/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 compliance-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/charliehzm/medharness/compliance-review"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/compliance-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,073 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.
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 $0.00205 $0.02073
Opus 5 $0.00102 $0.01037
Sonnet 5 $0.00041 $0.00415
Haiku 4.5 $0.00020 $0.00207

Measured 12d ago against content hash 2c31c075ef11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compliance-review 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.

.claude/skills/compliance-review/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance Review (Step 10)

The Compliance Gate. Functional correctness was proven by Verify; this skill proves compliance correctness.

Core mental model

You are looking for four classes of risk in a change that already works:

  1. PHI leakage: data that should not have escaped the controlled zone (logs, exceptions, caches, external API payloads)
  2. Prompt-injection surface: new ingress paths where untrusted text reaches a model
  3. Model-call non-conformance: any LLM invocation outside MODEL_ALLOWLIST.json
  4. Test-data lineage breach: synthetic data that turns out to be reversible to real patients

Functional tests don't catch any of these — they test what's intended. You test what's unintended.

Why heterogeneous model?

If the change's coder used DeepSeek-V4-Pro and Compliance-Agent also uses DeepSeek-V4-Pro, you get correlated blind spots — both will overlook the same prompt-injection style. The Compliance-Agent's backing model MUST be a different family (e.g. Qwen if coder used DeepSeek, or vice versa). This is enforced by mcp-model-router; do not try to override.

What this skill produces

openspec/changes/<slug>/COMPLIANCE_REPORT.md with this exact section structure:

# COMPLIANCE_REPORT — <change_id>
## 1. Audit metadata (auditor model id, date, inputs)
## 2. Findings — High Risk        (must be 0 to pass)
## 3. Findings — Medium Risk      (each needs owner + remediation)
## 4. Findings — Low Risk         (informational)
## 5. PHI handling assessment
## 6. Prompt-injection surface assessment
## 7. Model-call conformance assessment
## 8. Test-data lineage assessment
## 9. Sign-off block

When NOT to use this skill

Skip for:

  • Changes that have not yet passed Step 7 Verify (functional bugs first)
  • Pure docs / build / CI changes touching no L3/L4 path (use lightweight checklist instead)
  • Bug-fix-only changes inside an already-archived bundle (those go through Step 11 mini-loop)

Active context bundle

Read the full file on GitHub · 164 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. 12d ago First seen · 164 lines · 205 tokens per session scan A 2c31c075ef11

Subscribe to this mod's changes

compliance-review is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 205 tokens to every session and 2,073 once invoked, about $0.0010 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

hipaa-review

Performs a HIPAA Security Rule compliance review against all Administrative, Physical, and Technical Safeguards defined in 45 CFR Part 164, Subpart C. Auto-invoked when discussing healthcare data security, ePHI protection, HIPAA audit readiness, or business associate compliance. Evaluates required and addressable…

UnitOneAI/SecuritySkills · 86 tokens

Healthcare Compliance

HIPAA compliance, healthcare regulations, privacy and security standards for medical organizations and providers.

jmsktm/claude-settings · 19 tokens

compliance

Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…

ericrisco/rsc-harness · 96 tokens

performing-soc2-type2-audit-preparation

Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…

adriannoes/awesome-agentic-ai · 112 tokens

akf-trust-metadata-v2

AKF — The AI Native File Format workflow skill. Use this skill when the user needs The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing and the operator should preserve…

diegosouzapw/awesome-omni-skills · 100 tokens

compliance-audit

Regulatory compliance auditing across GDPR, HIPAA, PCI DSS, SOC 2, and ISO frameworks with automated evidence collection and gap analysis. Use when conducting compliance assessments, preparing for certifications, or implementing regulatory controls.

NickCrew/Claude-Cortex · 48 tokens