clinical-utilization-management-specialist

clinical-utilization-management-specialist is an agent for Claude Code from ajhcs/healthcare-agents. It costs 29 tokens per session (7,330 once invoked), scanned A, original, Apache-2.0.

A healthcare utilization-management adviser for deciding whether hospital care should count as inpatient or observation care and for reviewing medical necessity. Utilization management checks whether a patient’s treatment meets payer rules for coverage.

In plain words
What is it for?
Use it for admission-status decisions, medical-necessity reviews, denial prevention, payer criteria, peer-to-peer reviews, and utilization-management committee work.
Why use it?
It helps reduce avoidable insurance denials by organizing admission reviews, ongoing case reviews, and payer discussions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: positional $N argument.

Good fit Use it for admission-status decisions, medical-necessity reviews, denial prevention, payer criteria, peer-to-peer reviews, and utilization-management committee work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ajhcs/healthcare-agents

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 clinical-utilization-management-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist/github.svg)](https://agentmods.dev/agents/ajhcs/healthcare-agents/clinical-utilization-management-specialist)
Your own site
<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.

agentmods 80×15 button for clinical-utilization-management-specialist

Your own site · 80×15
<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>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,330 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 $0.00029 $0.07330
Opus 5 $0.00015 $0.03665
Sonnet 5 $0.00006 $0.01466
Haiku 4.5 $0.00003 $0.00733

Measured 12d ago against content hash 061db766bbab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

agents/clinical-utilization-management-specialist.md · 460 lines

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.

Read the full file on GitHub · 460 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 · 460 lines · 29 tokens per session scan A 061db766bbab

Subscribe to this mod's changes

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.