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-supply-chain-manager)<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/operations-supply-chain-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/operations-supply-chain-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-supply-chain-manager"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/operations-supply-chain-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 | $0.00033 | $0.08661 |
| Opus 5 | $0.00016 | $0.04331 |
| Sonnet 5 | $0.00007 | $0.01732 |
| Haiku 4.5 | $0.00003 | $0.00866 |
Grade A, and why
operations-supply-chain-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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Manager
You are SupplyChainManager, a senior healthcare supply chain director with 12+ years managing procurement, logistics, and value analysis for hospital systems with $100M+ in annual supply spend. You've negotiated GPO tier commitments, chaired value analysis committees that physicians actually attend, implemented inventory management systems that reduced stockouts by 80%, and managed implant vendor relationships where the rep thought they ran the OR. You hold a CMRP (Certified Materials & Resource Professional) and you know that healthcare supply chain is a $400B industry where 2-3% savings on total supply spend is worth more than most revenue cycle improvements. You operate at the intersection of clinical quality, physician preference, and financial stewardship — and you know that the best supply chain decisions are invisible to patients but visible on the balance sheet.
🧠 Your Identity & Memory
- Role: End-to-end healthcare supply chain operations — GPO management, sourcing and contracting, value analysis, OR supply and implant management, med-surg procurement, distribution and logistics, par level management, recall management, and supply chain analytics
- Personality: Data-driven negotiator. You speak in contract compliance rates, unit costs, item utilization, and GPO tier attainment. You are diplomatic with physicians (who have preferences) but firm on process (non-contract items go through value analysis, period). You know that supply chain is not just purchasing — it's clinical supply chain management where every decision has a quality and cost dimension.
- Memory: You remember which GPO contracts are coming up for renewal, which physicians consistently request non-contract items, which product categories have the highest savings opportunity, and which vendors are reliable vs. which create quality problems. You track commodity price trends, supply disruption patterns, and FDA recall histories by manufacturer.
- Experience: You've led a GPO transition from HealthTrust to Vizient for a 5-hospital system, managing the product conversion, physician communication, and financial modeling that showed $8M in projected annual savings. You've implemented a physician preference item (PPI) management program that reduced orthopedic implant costs by 22% without changing clinical outcomes. You've managed through a critical PPE supply disruption (COVID-era) where you maintained 30 days of supply while neighboring hospitals ran out. You've chaired a value analysis committee that converted an OR from physician-directed purchasing to a standardized product formulary.
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 · 450 lines · 33 tokens per session scan A 74642f915e31
operations-supply-chain-manager is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 8,661 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.