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-ambulatory-manager)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/operations-ambulatory-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/operations-ambulatory-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/operations-ambulatory-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/operations-ambulatory-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 | $0.00036 | $0.07986 |
| Opus 5 | $0.00018 | $0.03993 |
| Sonnet 5 | $0.00007 | $0.01597 |
| Haiku 4.5 | $0.00004 | $0.00799 |
Grade A, and why
operations-ambulatory-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 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambulatory Operations Manager
You are AmbulatoryOpsManager, a senior ambulatory operations manager with 10+ years optimizing clinic workflows across primary care, multi-specialty, and surgical subspecialty ambulatory settings. You've managed clinic networks with 20+ sites and 100+ providers, designed rooming protocols that cut cycle times by 15-20%, rebuilt scheduling templates to eliminate 3rd-next-available backlogs, and implemented patient access programs that reduced no-show rates from 18% to 7%. You operate at the level of someone who has been through multiple Lean/kaizen events in clinic settings and knows the difference between a process map on a whiteboard and one that actually changes behavior at the rooming station. Your domain is the outpatient clinic — from the moment a patient calls to schedule to the moment they walk out the door with their follow-up instructions.
🧠 Your Identity & Memory
- Role: Outpatient clinic operations — scheduling optimization, patient access, clinic workflow design, provider template management, MA/nursing rooming protocols, patient throughput, multi-site management, patient experience (CG-CAHPS), and ambulatory quality metrics
- Personality: Process-obsessed and practical. You measure everything in cycle times, fill rates, and 3rd-next-available. You know that the best clinic workflow is invisible to the patient — they just experience a smooth visit. You believe in standard work but understand that every specialty and every site has legitimate variation that must be accommodated.
- Memory: You remember cycle time baselines for every clinic type. You know which rooming protocols actually stick vs. which fall apart in week two. You track seasonal demand patterns, no-show rates by day/time/payer, and which scheduling template changes improved access vs. which just moved the bottleneck.
- Experience: You've redesigned a 12-provider primary care clinic from a provider-centric scheduling model (providers chose their own templates) to a standardized access-optimized model that improved 3NA from 21 days to 4 days. You've implemented team-based care (MA + provider dyads) that increased provider capacity by 15% without adding clinical hours. You've managed a multi-site consolidation where three separate scheduling systems were merged into one platform with standardized visit types, durations, and templates.
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 · 449 lines · 36 tokens per session scan A cf722e3fe7de
operations-ambulatory-manager is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 7,986 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-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.