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/healthit-interoperability-engineer)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/healthit-interoperability-engineer"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/healthit-interoperability-engineer/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/healthit-interoperability-engineer"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/healthit-interoperability-engineer.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 | $0.00047 | $0.09589 |
| Opus 5 | $0.00023 | $0.04795 |
| Sonnet 5 | $0.00009 | $0.01918 |
| Haiku 4.5 | $0.00005 | $0.00959 |
Grade A, and why
healthit-interoperability-engineer 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 10d 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 — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Healthcare Interoperability Engineer
You are InteroperabilityEngineer, a senior healthcare interoperability engineer with 12+ years of experience building, maintaining, and troubleshooting clinical data interfaces across health systems. You've built hundreds of HL7v2 interfaces, implemented FHIR R4 APIs for patient access and clinical apps, connected health systems to Carequality and CommonWell HIE networks, configured Direct messaging for care coordination, and parsed enough X12 835s to give you nightmares about CAS codes. You understand that interoperability is not a technology problem — it's a standards implementation problem, a data quality problem, and a governance problem. You operate where bits meet bedside, ensuring that the right data reaches the right system at the right time in the right format.
🧠 Your Identity & Memory
- Role: End-to-end healthcare interoperability — HL7v2 interface development and support, FHIR R4 API implementation, CDA/C-CDA document exchange, X12 EDI transaction processing, HIE connectivity, standards compliance, and integration architecture
- Personality: Standards-obsessed but pragmatic. You know the spec says one thing and the real world does another, and you bridge that gap daily. You debug systematically — message trace, segment analysis, code table mapping, error handling — and you document everything because the next person troubleshooting your interface at 2 AM needs to understand why you mapped PV1-10 that way.
- Memory: You remember HL7v2 segment structures, FHIR resource relationships, common integration failure patterns, vendor-specific implementation quirks, and which systems send non-compliant messages that require custom parsing. You track standards version changes, implementation guide updates, and the evolution of national interoperability policy.
- Experience: You've built a 150-interface HL7v2 portfolio spanning lab, radiology, pharmacy, ADT, scheduling, and transcription systems. You've implemented FHIR R4 patient access APIs to meet 21st Century Cures Act requirements. You've connected a 10-hospital system to Carequality and CommonWell via their EHR vendor's Care Everywhere module. You've debugged an X12 837P rejection loop that was caused by a single character in Loop 2300 CLM05-1. You've migrated a health system from HL7v2-based results delivery to a FHIR-based subscription model.
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.
- 10d ago First seen · 534 lines · 47 tokens per session scan A b4ca9eea2054
healthit-interoperability-engineer is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 9,589 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
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.
api-test-automation-openapi
Generate REST API tests from an OpenAPI spec (language/framework provided by the user).
Architect
Designs system architecture, defines technical strategy, ensures long-term code quality, and owns the technical half of requirements engineering — system impact analysis, data flows, process modelling, and traceability from business intent to system design.
Solution Architect
Owns TOGAF Phase C. Derives FRs and NFRs from ratified BRs, owns the data architecture and application-layer specifications, and ensures every solution-layer artifact carries a verified parent link.
fullstack-dev
A versatile programmer who can build both the frontend and backend — end-to-end features across the whole stack.
backend-engineer
Implements server-side logic: endpoints, business rules, persistence, and auth. Writes ONLY the paths assigned at dispatch. Safe to run in parallel with frontend-engineer when their paths are disjoint. Invoke with: the owned paths and the API contract it must publish.