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 jschulte/claude-plugins --skill health-audit-domaingit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/health-audit-domain)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/health-audit-domain"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/health-audit-domain/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/jschulte/claude-plugins/health-audit-domain"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/health-audit-domain.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 | $0.00110 | $0.10112 |
| Opus 5.5 | $0.00044 | $0.04045 |
| Sonnet 5.5 | $0.00022 | $0.02022 |
| Haiku 4.5 | $0.00011 | $0.01011 |
Grade A, and why
health-audit-domain 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 24d 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 — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Logic & Domain Integrity Audit Skill
Use this skill when the user wants a deep audit of whether the codebase faithfully and completely implements the business domain. The skill may audit the whole domain model or focus on a user-specified workflow, state machine, pricing path, entitlement system, permission model, or business rule cluster. This is NOT a code quality audit (/health-audit does that) or a UX audit (/health-audit-ux does that). This skill is about whether the business rules are correct, consistent, complete, and impossible to circumvent. This audit finds the bugs that cost money — pricing errors, permission gaps, billing edge cases, state machine impossibilities, and logic that silently does the wrong thing.
Mission
Perform a rigorous, evidence-backed business logic and domain integrity audit: domain model accuracy, state machine correctness, pricing and billing logic, permission enforcement, validation consistency across entry points, edge case handling, feature gating and entitlements, workflow completeness, data consistency, temporal logic, and external integration contracts.
Think like a product manager who just discovered a billing bug. Think like a QA engineer hunting edge cases. Think like a financial auditor checking calculations. Think like a lawyer asking "what happens if...?"
Do not flag code quality issues unless they directly threaten business rule correctness. Do not report vague "best practices" violations. Do not nitpick naming or style. Every finding must answer: "What business rule is wrong, missing, or inconsistent, and what real-world harm does it cause?"
Focus Prompt Support
This skill can take an optional prompt that describes the business/domain area to focus on.
Examples:
- "Focus on subscription lifecycle logic"
- "Review billing, credits, and refunds"
- "Audit RBAC and entitlements"
- "Look at order state transitions"
- "Review invoicing rules for enterprise accounts"
When a focus prompt is provided:
- Treat it as the primary audit scope
- Resolve it into concrete entities, state machines, calculations, permission checks, workflows, and tests
- Audit out-of-scope logic only when it is required to explain an in-scope contradiction or shared rule
- Keep findings, scores, and recommendations scoped to that area instead of implying a full-domain correctness grade
- State assumptions, included workflows, excluded workflows, and unresolved domain questions explicitly in the output
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.
- 24d ago First seen · 626 lines · 110 tokens per session scan A d259eb2723b5
health-audit-domain is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 110 tokens to every session and 10,112 once invoked, about $0.0004 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 2026-10-12.
Other skills, from other repositories
reviewing-personhog-protocol
The full review process for personhog coordination-protocol changes — leases, fencing, handoffs, supervisors, failure budgets, warming, and changelog semantics. Use before pushing or requesting review on any personhog protocol changeset, when asked for an exhaustive or careful review of personhog code, and after any…
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
qj-strategy-reviewer
Use this skill to review a QuantJourney strategy for correctness before trusting its results. Check each item.
product-economics
Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.