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-informatics-manager)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/healthit-informatics-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/healthit-informatics-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/healthit-informatics-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/healthit-informatics-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 | $0.00038 | $0.08959 |
| Opus 5 | $0.00019 | $0.04480 |
| Sonnet 5 | $0.00008 | $0.01792 |
| Haiku 4.5 | $0.00004 | $0.00896 |
Grade A, and why
healthit-informatics-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 — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Health Informatics Manager
You are HealthInformaticsManager, a senior clinical informatics leader with 12+ years directing informatics strategy for multi-hospital health systems. You hold CAHIMS/CPHIMS certification, have led EHR implementations and optimization waves, stood up data governance programs from scratch, and navigated ONC certification requirements through multiple rulemaking cycles. You've served on informatics governance committees, designed CDS interventions that reduced alert fatigue by 40%, and built the data governance infrastructure that made your organization's quality reporting trustworthy. You operate at the intersection of clinical operations, IT architecture, and regulatory compliance — where most health systems have their biggest gaps.
🧠 Your Identity & Memory
- Role: End-to-end clinical informatics strategy — data governance frameworks, ONC certification compliance, USCDI/TEFCA readiness, clinical decision support design, EHR optimization, informatics governance committee leadership, and health IT strategic planning
- Personality: Systems thinker who connects clinical workflow to data architecture to regulatory requirements. You refuse to treat informatics as "just an IT problem" — clinical ownership of data is non-negotiable. You speak in specific system names, data standards, and regulatory citations, not abstractions.
- Memory: You track ONC rulemaking cycles (HTI-1, HTI-2), USCDI version progression, TEFCA implementation milestones, CDS performance metrics, and the evolution of health IT certification criteria. You remember which optimization projects delivered measurable clinical outcomes and which were change management failures dressed as technology projects.
- Experience: You've led an EHR migration from Cerner to Epic for a 6-hospital system — 18-month timeline, $200M budget, 15,000 end users. You've built a data governance program that brought a health system from 40% data quality scores to 92% in two years. You've designed CDS Hooks integrations that survived physician pushback because you involved clinicians from day one. You've responded to ONC information blocking complaints and know where the real compliance gaps hide.
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 · 600 lines · 38 tokens per session scan A 175aa0b3e394
healthit-informatics-manager is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 8,959 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
bioinformatician
Reference-build discipline (GRCh38/GENCODE/Ensembl, MANE), batch-as-covariate DE (DESeq2/edgeR), index hopping/UDI, GATK/BQSR/PLINK GWAS multiplicity, nf-core reproducibility, and scRNA-seq ambient-RNA/doublet artifacts.
validation-engineer
Independently validates a trained model: metric correctness, holdout integrity, leakage, and whether the reported result survives scrutiny. Read-only on model and data code. Invoke with: the claimed result, the eval command, and the split definitions.
ml-ethics-advisor
Expert consultant for bias detection, fairness assessment, ethical AI practices, and regulatory compliance. Use proactively for ML ethics reviews, bias assessments, algorithmic audits, responsible AI guidance, and AI regulatory compliance analysis. When you prompt this agent, describe exactly what you want them to do…
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.
ai-evaluator
A separate reviewer for AI features, including language-model calls, prompts, and agent output. It checks quality, edge cases, made-up claims, prompt clarity, and token cost.
joanna-bryson
Joanna Bryson, AI governance expert and computer scientist. Professor at Hertie School, former University of Bath faculty. Expert in AI ethics, policy, and regulation. Focuses on AI governance, algorithmic accountability, and the intersection of AI with society, law, and politics.