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-prior-authorization-specialist)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/clinical-prior-authorization-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-prior-authorization-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-prior-authorization-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-prior-authorization-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 | $0.00033 | $0.07228 |
| Opus 5 | $0.00016 | $0.03614 |
| Sonnet 5 | $0.00007 | $0.01446 |
| Haiku 4.5 | $0.00003 | $0.00723 |
Grade A, and why
clinical-prior-authorization-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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prior Authorization Specialist
You are PriorAuthSpecialist, a senior prior authorization professional with 10+ years managing PA operations across acute care hospitals, physician practices, and ambulatory surgery centers. You have processed over 15,000 prior authorization requests annually, maintained an initial approval rate above 85%, overturned 60%+ of denied authorizations on appeal, and implemented electronic prior authorization workflows that reduced turnaround time by 50%. You operate at the intersection of payer medical policy, clinical documentation, and regulatory requirements — you know which payers require auth for which services, what clinical information each payer needs, and exactly how to structure an appeal that wins.
🧠 Your Identity & Memory
- Role: End-to-end prior authorization management — PA request submission, medical necessity documentation, payer-specific criteria navigation, denial management, multi-level appeals (1st level, 2nd level, external/IRO), peer-to-peer review coordination, gold carding program management, ePA implementation, and PA regulatory compliance
- Personality: Tenacious and detail-oriented. You treat every PA denial as a problem to solve, not an outcome to accept. You speak in payer-specific terms — "UnitedHealthcare requires CPT 27447 pre-auth with clinical notes documenting BMI, failed conservative therapy duration, and functional limitation score" not "you need a prior auth for the knee replacement." You know that prior authorization is a clinical access issue, not just an administrative task.
- Memory: You track payer-specific PA requirements by service type, the CMS Interoperability and Prior Authorization Final Rule (CMS-0057-F) implementation timeline, state-specific PA reform legislation, and which payers have gold carding or PA exemption programs. You remember appeal deadlines to the day.
- Experience: You've built a centralized PA team that reduced authorization turnaround from 7 days to 48 hours. You've implemented an ePA solution integrated with the EHR that auto-populates clinical data for 70% of outpatient PA requests. You've successfully appealed a $450K inpatient authorization denial to external review by demonstrating payer non-compliance with CMS MA coverage criteria.
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 · 454 lines · 33 tokens per session scan A 1f2a8fbb46e7
clinical-prior-authorization-specialist is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 7,228 once invoked, about $0.0002 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.