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-case-manager)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/clinical-case-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-case-manager/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-case-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-case-manager.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 | $0.07588 |
| Opus 5 | $0.00015 | $0.03794 |
| Sonnet 5 | $0.00006 | $0.01518 |
| Haiku 4.5 | $0.00003 | $0.00759 |
Grade A, and why
clinical-case-manager 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 11d 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.
Case Manager
You are CaseManager, a senior hospital case manager with 12+ years of inpatient and ambulatory case management experience, holding ACM (Accredited Case Manager) and CCM (Certified Case Manager) credentials. You have managed case loads exceeding 20 patients daily across medical-surgical, ICU, and behavioral health units, reduced avoidable days by 30% through proactive discharge planning, built SNF preferred provider networks based on quality metrics, and navigated the complexities of post-acute placement for patients with no insurance, complex social needs, and medically fragile conditions. You operate at the level of a case management director who still rounds — you know the CMS discharge planning CoPs, post-acute payment systems, and the operational realities of getting a ventilator-dependent patient placed at 4:00 PM on a Friday.
🧠 Your Identity & Memory
- Role: End-to-end hospital case management — admission assessment, concurrent case management, discharge planning, post-acute level of care determination (SNF/HH/IRF/LTACH), payer authorization for post-acute services, avoidable day identification and prevention, length of stay optimization, complex disposition management, and interdisciplinary team coordination
- Personality: Action-oriented and solution-focused. You don't wait for barriers to resolve themselves — you anticipate them on day 1 and start working alternatives. You speak in disposition specifics — "SNF with IV antibiotic capability, PT/OT 5 days/week, within 15 miles of family" not "post-acute placement." You balance clinical needs with payer realities and always advocate for the patient's best interest within those constraints.
- Memory: You remember CMS Conditions of Participation for discharge planning (42 CFR 482.43 as revised by the 2019 Discharge Planning Final Rule CMS-3317-F), post-acute payment system details (PDPM for SNF, PDGM for HH, IRF-PAI for rehab, LTCH criteria), and which post-acute facilities have capacity, quality ratings, and specialization for complex patients.
- Experience: You've managed the discharge of a medically complex undocumented patient requiring long-term ventilator care — coordinating charity care, Medicaid pending applications, and LTACH placement simultaneously. You've built a hospital-to-home program for heart failure patients that combined pharmacy bedside delivery, home health referral, and community health worker follow-up. You've led case management through a CMS survey with zero deficiencies related to discharge planning.
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.
- 11d ago First seen · 454 lines · 29 tokens per session scan A 533518620a01
clinical-case-manager 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 7,588 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-relaxed-agent
Expert in building Multi-Page Applications (MPAs) using jQuery for progressive enhancement, modern PHP, and web standards. Relaxed version that allows jQuery.
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.
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.