medharness: Skill for Claude Code

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

compliance-precheck is a skill for Claude Code from charliehzm/medharness. It costs 220 tokens per session (1,825 once invoked), scanned A, original, Apache-2.0.

A starting compliance assessment for a change in a medical-data software project. It classifies the sensitivity of the data involved and defines which AI models and protections may be used.

In plain words
What is it for?
Use it at the start of an OpenSpec change to create a signed compliance tag and a machine-readable model allowlist.
Why use it?
It turns a broad business request into explicit rules for handling sensitive data. Later steps can then check prompts, model calls, and code against those rules.

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-precheck/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-precheck

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/charliehzm/medharness/compliance-precheck"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/compliance-precheck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,825 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 $0.00220 $0.01825
Opus 5 $0.00110 $0.00912
Sonnet 5 $0.00044 $0.00365
Haiku 4.5 $0.00022 $0.00183

Measured 13d ago against content hash 0c14da18b949, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compliance-precheck 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 13d 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-precheck/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance Precheck (Step 0)

This skill is the first gate of the v2 12-step SOP. Without a signed COMPLIANCE_TAG and an injected MODEL_ALLOWLIST, every downstream step (PRD / TDD / OpenSpec / code / tests / archive) is invalid.

Core mental model

You are turning "business desire" into "data + model contract".

  • Business says: "we want to match patients across hospitals by name + DOB"
  • Compliance says: "name + DOB are L4 PHI; allowed models = {private deepseek-v4-pro after desensitization}; deny list = {claude opus public, gpt-4 public}; required mitigation = phi-desensitize before any prompt"

Your job: turn the first sentence into the structured second sentence.

What this skill produces

Two artifacts, both inside the change directory:

  1. openspec/changes/<slug>/COMPLIANCE_TAG.md — human-readable signed contract (template at openspec/templates/COMPLIANCE_TAG.template.md)
  2. openspec/changes/<slug>/MODEL_ALLOWLIST.json — machine-readable, injected into mcp-model-router

When NOT to use this skill

Skip for:

  • Pure UI string / i18n changes touching no business data
  • Build / CI / docs-only changes (still log it but mark L1)
  • Bugfixes inside an existing change that already has a valid COMPLIANCE_TAG (just bump its version)

Active context bundle

Always load first

  1. This SKILL.md
  2. reference/data-tier-rubric.md — how to decide L1 vs L2 vs L3 vs L4
  3. reference/field-minimization-protocol.md — how to challenge field inclusion
  4. openspec/templates/COMPLIANCE_TAG.md — the canonical template

Load on demand

  • reference/regulation-cheatsheet.md — HIPAA 18 identifiers / PIPL / 健康医疗数据安全指南 mapping (when classifying ambiguous fields)
  • reference/model-deployment-matrix.md — which model can run where (when filling allowlist)

Workflow

Phase 1 · Intake (≤ 5 min)

  • Read the business need draft.
  • List every data field the change could read / write / log.
  • If the field list is empty, stop and ask the requester: "what data flows through this change?"

Read the full file on GitHub · 140 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. 13d ago First seen · 140 lines · 220 tokens per session scan A 0c14da18b949

Subscribe to this mod's changes

compliance-precheck is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 220 tokens to every session and 1,825 once invoked, about $0.0011 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