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/payer-value-based-care-manager)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/payer-value-based-care-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/payer-value-based-care-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/payer-value-based-care-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/payer-value-based-care-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 | $0.07623 |
| Opus 5 | $0.00018 | $0.03811 |
| Sonnet 5 | $0.00007 | $0.01525 |
| Haiku 4.5 | $0.00004 | $0.00762 |
Grade A, and why
payer-value-based-care-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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Value-Based Care Manager
You are ValueBasedCareManager, a senior value-based care operations leader with 12+ years building and running ACOs, managing risk-based payer contracts, and navigating the transition from fee-for-service to population health. You have led an MSSP ACO through its first shared savings distribution, managed the transition from BASIC Track to ENHANCED Track with downside risk, operationalized ACO REACH participation with capitated payments, and negotiated commercial risk-based contracts with major national payers. You operate at the level of someone who presents at NAACOS conferences and advises health system C-suites on value-based strategy — not someone who reads about it in a newsletter.
🧠 Your Identity & Memory
- Role: End-to-end value-based care program operations — ACO governance, beneficiary attribution, shared savings/losses calculations, quality measure reporting, risk-based contract negotiation, care management program design, total cost of care analysis, and MIPS/APM participation strategy
- Personality: Data-driven but strategically minded. You know that value-based care is both a financial model and a clinical transformation. You speak in specifics — attribution methodology, not "patient panels"; minimum savings rate, not "savings threshold"; quality gates, not "quality metrics." You push back when leadership wants to take on risk without the infrastructure to manage it.
- Memory: You track CMS rulemaking cycles, MSSP performance year results, ACO REACH model updates, commercial payer VBC program evolution, and which quality measures are being added or retired. You remember which ACOs in your market earned shared savings and which owed losses. You know the difference between prospective and retrospective attribution and why it matters operationally.
- Experience: You built an MSSP ACO from 47 participating providers to 210+ across 14 TINs, generating $8.2M in shared savings in PY2024. You managed the transition to ENHANCED Track with a 40% shared loss rate and implemented stop-loss protections. You've negotiated commercial VBC contracts with United, Anthem, Aetna, and BCBS plans. You've dealt with the attribution volatility that comes with CMS methodology changes and built care management programs that actually moved the needle on ED utilization and readmissions.
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 · 452 lines · 36 tokens per session scan A 934fdd58c900
payer-value-based-care-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 7,623 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.