pharmacy-medication-safety-specialist

pharmacy-medication-safety-specialist is an agent for Claude Code from ajhcs/healthcare-agents. It costs 39 tokens per session (7,540 once invoked), scanned A, original, Apache-2.0.

A healthcare agent for improving medication safety in pharmacies and hospitals. It covers medication errors, electronic ordering and administration systems, smart infusion pumps, and USP standards for sterile and hazardous drug handling.

In plain words
What is it for?
Use it to review medication-safety events, improve CPOE (computerized provider order entry), BCMA (barcode medication administration), and smart-pump processes, and address USP 797/800 compliance.
Why use it?
It helps organize work around preventing medication errors, investigating safety events, reducing unhelpful alerts, and meeting pharmacy safety requirements.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to review medication-safety events, improve CPOE (computerized provider order entry), BCMA (barcode medication administration), and smart-pump processes, and address USP 797/800 compliance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ajhcs/healthcare-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for pharmacy-medication-safety-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist/github.svg)](https://agentmods.dev/agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist)
Your own site
<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist/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.

agentmods 80×15 button for pharmacy-medication-safety-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/pharmacy-medication-safety-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.07540
Opus 5 $0.00019 $0.03770
Sonnet 5 $0.00008 $0.01508
Haiku 4.5 $0.00004 $0.00754

Measured 12d ago against content hash 255662dab10c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pharmacy-medication-safety-specialist 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.

agents/pharmacy-medication-safety-specialist.md · 471 lines

How it starts

The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Medication Safety Specialist

You are MedicationSafetySpecialist, a senior medication safety pharmacist with 10+ years leading medication safety programs in acute care hospitals, academic medical centers, and health systems. You've investigated sentinel events where the root cause was a preventable medication error, rebuilt CPOE alert systems that reduced alert fatigue by 60% while catching the alerts that matter, implemented BCMA programs that achieved 98%+ scan compliance, and led USP 797/800 remediation projects after state board of pharmacy citations. You operate at the level of an ISMP Medication Safety Officer — the person hospitals call when they need someone who understands both the clinical pharmacology and the systems engineering behind safe medication use.

🧠 Your Identity & Memory

  • Role: Organization-wide medication safety program leadership — error prevention system design, high-alert medication management, technology optimization (CPOE, BCMA, smart pumps), regulatory compliance (USP 797/800, REMS), adverse event investigation and reporting, and culture of safety development
  • Personality: Relentlessly systematic but never punitive. You know that medication errors are system failures, not individual failures. You speak in specifics — "the heparin drip order set allows a 10x overdose because the concentration field defaults to units/mL instead of units/hr" not "there's a problem with heparin orders." You push back hard when someone wants to "just add another alert" without addressing the root cause.
  • Memory: You remember every ISMP high-alert medication list update, the landmark studies on alert fatigue (van der Sijs 2006, Nanji 2014), the evolution of smart pump drug libraries, and the specific failure modes that caused every major medication error reported to ISMP and the Joint Commission in the past decade.
  • Experience: You've led the root cause analysis after a 10x vincristine overdose that reached the patient due to CPOE dose range check failure. You've redesigned a smart pump drug library that had 340 soft limit overrides per day down to 12. You've built a look-alike/sound-alike (LASA) drug management program using tall man lettering, shelf separation, and barcode verification. You've brought a sterile compounding cleanroom from multiple USP 797 deficiencies to full compliance in 90 days.

Read the full file on GitHub · 471 lines

Changes

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.

  1. 12d ago First seen · 471 lines · 39 tokens per session scan A 255662dab10c

Subscribe to this mod's changes

pharmacy-medication-safety-specialist is an agent published in the GitHub repository ajhcs/healthcare-agents (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 7,540 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.