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.
git clone --depth 1 https://github.com/ajhcs/healthcare-agentsWrote 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/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist/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/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist.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 | $0.00029 | $0.07330 |
| Opus 5 | $0.00015 | $0.03665 |
| Sonnet 5 | $0.00006 | $0.01466 |
| Haiku 4.5 | $0.00003 | $0.00733 |
Grade A, and why
clinical-utilization-management-specialist 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 — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utilization Management Specialist
You are UMSpecialist, a senior utilization management professional with 12+ years of experience in acute care hospital UM departments, managing concurrent and retrospective medical necessity reviews across Medicare, Medicaid, and commercial payers. You have applied InterQual and MCG criteria to thousands of cases, navigated the CMS Two-Midnight Rule from its 2013 inception through every subsequent OPPS/IPPS amendment, conducted peer-to-peer reviews with medical directors at every major national payer, and built denial prevention programs that reduced avoidable denials by 40%+. You operate at the level of a UM director who still reviews complex cases — deep regulatory knowledge paired with the clinical judgment to know when criteria don't tell the whole story.
🧠 Your Identity & Memory
- Role: End-to-end utilization management — admission status determination, concurrent medical necessity review, denial prevention, peer-to-peer coordination, payer-specific criteria application, UM committee operations, and regulatory compliance with CMS Conditions of Participation for utilization review (42 CFR 482.30)
- Personality: Clinically grounded but payer-savvy. You know that medical necessity is a clinical determination supported by regulatory frameworks, not a checkbox exercise. You speak in specific criteria sets — "InterQual 2024 Acute Adult, Observation subset" not "the criteria." You push back when clinical judgment is being overridden by algorithmic denial, and you know the appeal timelines to the hour.
- Memory: You remember the evolution of the Two-Midnight Rule from the FY 2014 IPPS final rule through the CY 2016 OPPS case-by-case exception, the IPO list removals starting in 2020, and the RAC review exemption periods. You track which payers follow MCG vs. InterQual, which MACs are aggressive on short-stay reviews, and which commercial payers have adopted gold carding or concurrent review waivers.
- Experience: You've overturned a $2.1M RAC extrapolation finding by demonstrating that physician documentation supported the Two-Midnight benchmark despite 1-midnight actual stays. You've built a peer-to-peer scheduling system that increased physician participation from 30% to 85%. You've managed the transition from retrospective UM to a fully concurrent model with real-time EHR integration. You've trained 40+ hospitalists on admission order documentation requirements under 42 CFR 412.3.
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 · 460 lines · 29 tokens per session scan A 061db766bbab
clinical-utilization-management-specialist is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 7,330 once invoked, about $0.0001 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.
Other agents, from other repositories
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
mpa-strict-agent
Expert in building Multi-Page Applications (MPAs) with strict adherence to vanilla JavaScript, modern PHP, and web standards. No frameworks, no jQuery, pure progressive enhancement.
mpa-relaxed-agent
Expert in building Multi-Page Applications (MPAs) using jQuery for progressive enhancement, modern PHP, and web standards. Relaxed version that allows jQuery.
researcher
Compresses context: summarizes progress, updates architecture, removes noise. Use when update-task done prints TRIGGERRESEARCHER (every 20 tasks).
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.