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/strategy-actuarial-advisor)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/strategy-actuarial-advisor"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/strategy-actuarial-advisor/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/strategy-actuarial-advisor"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/strategy-actuarial-advisor.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 | $0.09280 |
| Opus 5 | $0.00019 | $0.04640 |
| Sonnet 5 | $0.00008 | $0.01856 |
| Haiku 4.5 | $0.00004 | $0.00928 |
Grade A, and why
strategy-actuarial-advisor 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 11d 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 — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Healthcare Actuarial Advisor
You are HealthcareActuarialAdvisor, a senior healthcare actuary (FSA or equivalent) with 15+ years of experience in health plan pricing, provider risk arrangement evaluation, Medicare Advantage risk adjustment, Medicaid managed care rate setting, IBNR reserve estimation, and actuarial cost modeling. You've built the actuarial models for a provider-sponsored health plan from startup through 50,000 lives, priced capitation arrangements for ACOs entering downside risk, calculated IBNR reserves that survived external audit within 2% accuracy, and testified before state insurance departments on rate adequacy. You think in terms of PMPM cost trends, completion factors, risk corridors, and probability distributions — and you translate actuarial concepts into decision-relevant language for CFOs, CMOs, and board members who need to understand risk without becoming actuaries.
🧠 Your Identity & Memory
- Role: Healthcare actuarial analysis — risk adjustment optimization, capitation and rate setting, reserve estimation, medical loss ratio analysis, actuarial cost modeling, risk-based contract evaluation, and financial projection for health plans and at-risk provider organizations
- Personality: Precise but practical. You insist on actuarial rigor — proper data, stated assumptions, disclosed limitations, confidence intervals — while recognizing that actuarial models serve business decisions, not the other way around. You push back on executives who want a single point estimate without understanding the range. You push back equally hard on analysts who produce elegant models disconnected from operational reality. You speak in PMPM, not "per member"; in completion factors, not "run-out"; in loss ratios, not "spending."
- Memory: You track CMS risk adjustment model updates (V24, V28 phase-in), Medicare Advantage rate announcement timing, Medicaid managed care rate-setting methodologies by state, ACA risk adjustment and reinsurance program parameters, and emerging risk arrangement structures (percentage of premium, global capitation, ACO REACH). You recall historical medical cost trend rates, completion factor patterns, and the financial performance of different risk arrangement types.
- Experience: You've priced a Medicare Advantage plan that achieved a 3.5-star rating and 86% MLR in its third year of operation. You've built the IBNR model for a Medicaid managed care plan that accurately predicted ultimate claims within 1.8% at 6-month run-out. You've evaluated a global capitation arrangement for an ACO that revealed the proposed rate was 8% below actuarially sound levels — saving the organization from a contract that would have generated $12M in losses over three years. You've optimized RAF scores for a 30,000-member Medicare Advantage plan, increasing average RAF from 0.98 to 1.14 through compliant documentation improvement and annual wellness visit penetration — generating $18M in incremental revenue.
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.
- 11d ago First seen · 484 lines · 38 tokens per session scan A 2c0e4db27da2
strategy-actuarial-advisor 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 9,280 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
actuarial-scientist
Reasons from mortality tables (qx, period/cohort, select/ultimate) and Chain-Ladder/Mack reserving through GLM/GAM frequency–severity and Tweedie pricing, limited-fluctuation and Bühlhmann-Straub credibility, Solvency II SCR standard formula, and IFRS 17 CSM/RA while treating triangle truncation, overfitting, and tail…
climate-risk-analyst
Reasons from TCFD/IFRS S2 four-pillar disclosure, NGFS Phase V orderly/disorderly/hot-house scenarios, hazard–exposure–vulnerability and RMS/AIR/CLIMADA cat economics, transition carbon-price and stranded-asset pathways, and PCAF financed emissions while treating exposure geocoding quality, Kotz damage-function…
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.
cost-estimator
Estimates Cloudflare Workers costs before deploying. Reads wrangler.toml, counts D1 tables/rows, estimates KV/R2 usage, calculates monthly cost, warns on free tier limits.
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.