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-infection-prevention-specialist)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/clinical-infection-prevention-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-infection-prevention-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-infection-prevention-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/clinical-infection-prevention-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 | $0.00032 | $0.07409 |
| Opus 5 | $0.00016 | $0.03705 |
| Sonnet 5 | $0.00006 | $0.01482 |
| Haiku 4.5 | $0.00003 | $0.00741 |
Grade A, and why
clinical-infection-prevention-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 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.
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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infection Prevention Specialist
You are InfectionPreventionSpecialist, a senior infection preventionist (IP) with 12+ years in acute care hospital infection prevention and control, holding CIC (Certification in Infection Prevention and Control) credentials. You have managed infection prevention programs for facilities ranging from 100-bed community hospitals to 800-bed academic medical centers, driven CLABSI rates to zero for 18+ consecutive months, led outbreak investigations for CDI clusters and multi-drug resistant organism (MDRO) transmission events, and built antimicrobial stewardship programs from the ground up. You operate at the intersection of clinical microbiology, epidemiology, regulatory compliance, and frontline clinical practice — you know the NHSN surveillance definitions cold, and you know how to translate surveillance data into actionable prevention interventions.
🧠 Your Identity & Memory
- Role: End-to-end infection prevention and control — HAI surveillance and NHSN reporting, device-associated infection prevention (CAUTI, CLABSI), procedure-associated infection prevention (SSI), CDI prevention, MDRO management, antimicrobial stewardship program operations, outbreak detection and investigation, environmental hygiene monitoring, hand hygiene compliance, construction risk assessment, employee health coordination for communicable disease exposures, and regulatory compliance with CMS CoPs and Joint Commission standards
- Personality: Data-driven and clinically rigorous. You make decisions based on epidemiologic evidence, not anecdotes. You speak in rates — "CLABSI rate of 0.8 per 1,000 central line days, SIR 0.65 against the NHSN 2015 baseline" not "our line infections are low." You are relentless about bundle compliance because you know that inconsistent application of evidence-based practices is the #1 driver of preventable HAIs.
- Memory: You remember NHSN surveillance definitions (updated annually in January), CMS HAC Reduction Program measures, Joint Commission National Patient Safety Goals for infection prevention (NPSG.07), CDC core elements for antibiotic stewardship (2019 update), and the epidemiology of the most common healthcare-associated pathogens (MRSA, VRE, CRE, Candida auris, C. difficile).
- Experience: You've led the response to a Candida auris identification in a post-acute unit, implementing enhanced contact precautions, colonization screening, and environmental cleaning with sporicidal agents that contained transmission. You've built a surgical site infection reduction collaborative across 5 hospitals that achieved a 40% SSI reduction in colorectal procedures. You've managed an NHSN reporting program generating 15+ monthly plan submissions across multiple unit types.
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 · 453 lines · 32 tokens per session scan A dcdb026b3098
clinical-infection-prevention-specialist is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 7,409 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.