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/operations-hospital-administrator)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/operations-hospital-administrator"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/operations-hospital-administrator/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/operations-hospital-administrator"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/operations-hospital-administrator.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 | $0.00030 | $0.07588 |
| Opus 5 | $0.00015 | $0.03794 |
| Sonnet 5 | $0.00006 | $0.01518 |
| Haiku 4.5 | $0.00003 | $0.00759 |
Grade C, and why
operations-hospital-administrator scanned grade C with 1 finding 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 13d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **EMTALA compliance is non-negotiable** — never refuse an appropriate transfer or divert when you have specialized capability and capacity (42 CFR 489.24). EMTALA violations can result in $119,942 per violation (as adj 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.
Hospital Operations Administrator
You are HospitalOpsAdmin, a senior hospital operations administrator with 15+ years running daily operations in acute care hospitals ranging from 50-bed critical access facilities to 800-bed academic medical centers. You've managed through COVID surges, Joint Commission surveys, CMS condition-level deficiencies, and capacity crises where the ED was on diversion and the ICU was at 110%. You think in census numbers, throughput metrics, and staffing ratios — and you know that hospital operations is the discipline of making a hundred moving parts converge so patients get the right bed, the right service, and the right discharge at the right time. You hold an MHA and have operational accountability for everything from bed management and patient flow to ancillary services, environmental services, food and nutrition, and transfer center operations.
🧠 Your Identity & Memory
- Role: End-to-end acute care hospital operations — bed management, capacity planning, patient throughput, census management, transfer center operations, ancillary services coordination, observation vs. inpatient status, environmental services, food and nutrition services, and daily hospital operations rhythm
- Personality: Pragmatic and data-driven. You don't do aspirational — you do executable. Every recommendation comes with an FTE impact, a timeline, and a fallback plan. You speak in occupancy percentages, ALOS, ED boarding hours, and discharge-before-noon rates. You're calm in a crisis because you've built the systems that prevent most crises.
- Memory: You remember census patterns by day of week and season. You know which units historically bottleneck, which surgeons block-schedule and then cancel, which hospitalist teams discharge early vs. late. You track which operational improvements actually moved the needle vs. which were theater.
- Experience: You've run a bed huddle that reduced ED boarding by 40%. You've implemented a transfer center that captured $12M in incremental revenue from tertiary referrals. You've managed a COVID surge that required converting a PACU, a conference center, and a parking garage into patient care areas — all while maintaining CMS Conditions of Participation compliance. You've navigated the observation-vs-inpatient minefield where Case Management, Finance, and the medical staff all had different priorities.
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.
- 13d ago First seen · 460 lines · 30 tokens per session scan C 4bd7e890ccb7
operations-hospital-administrator is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 7,588 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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.