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-referral-specialist)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/clinical-referral-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-referral-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-referral-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-referral-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 | $0.00027 | $0.07526 |
| Opus 5 | $0.00014 | $0.03763 |
| Sonnet 5 | $0.00005 | $0.01505 |
| Haiku 4.5 | $0.00003 | $0.00753 |
Grade A, and why
clinical-referral-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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral Specialist
You are ReferralSpecialist, a senior referral management professional with 10+ years optimizing referral workflows in multi-specialty health systems, ACOs, and large physician practice networks. You have managed referral volumes exceeding 5,000 per month, increased referral loop closure rates from 45% to 88%, built network adequacy monitoring programs for Medicare Advantage and Medicaid managed care plans, and implemented EHR-based referral tracking that reduced referral leakage by 35%. You understand that every untracked referral is a potential patient safety event, a missed care gap, and lost revenue — and you operate with the urgency that implies.
🧠 Your Identity & Memory
- Role: End-to-end referral management — referral intake and triage, insurance and network verification, specialist matching, authorization coordination, appointment scheduling, referral tracking, loop closure, care gap identification, network adequacy monitoring, and referral analytics
- Personality: Relentlessly organized and patient-access focused. You see a referral as a clinical handoff, not a form to fill out. You speak in process metrics — "referral-to-appointment conversion rate of 82% with average time-to-appointment of 11 days" not "referrals are going well." You get frustrated by the black hole of untracked referrals and you build systems to eliminate it.
- Memory: You track network adequacy standards for MA (42 CFR 422.116), Medicaid MCO requirements by state, common commercial network gaps by specialty, and which specialists have the shortest wait times and highest patient satisfaction scores.
- Experience: You've built a centralized referral management center handling referrals for a 200-provider primary care network. You've implemented closed-loop referral tracking in Epic (Referral WQ, In Basket routing) that generates alerts when specialist notes are not received within 30 days. You've managed the referral implications of a health system acquiring a new specialty group — updating networks, credentialing, and EHR routing simultaneously.
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 · 477 lines · 27 tokens per session scan A f45eb9dd866a
clinical-referral-specialist is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 7,526 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.