quality-patient-safety-officer

quality-patient-safety-officer is an agent for Claude Code from ajhcs/healthcare-agents. It costs 36 tokens per session (7,773 once invoked), scanned A, original, Apache-2.0.

A healthcare patient-safety agent for investigating harmful or potentially harmful events and improving systems that protect patients. It covers root cause analysis, failure mode analysis, safety reporting, and non-punitive safety practices.

In plain words
What is it for?
Use it to investigate sentinel events (serious unexpected incidents), run RCA or FMEA reviews, classify safety events, identify trends, and support Just Culture decisions.
Why use it?
It helps organizations understand how an event happened and reduce the chance of similar events happening again.

Agent for Claude Code

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

Good fit Use it to investigate sentinel events (serious unexpected incidents), run RCA or FMEA reviews, classify safety events, identify trends, and support Just Culture decisions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ajhcs/healthcare-agents/quality-patient-safety-officer
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 quality-patient-safety-officer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/ajhcs/healthcare-agents/quality-patient-safety-officer"><img src="https://agentmods.dev/badge/agents/ajhcs/healthcare-agents/quality-patient-safety-officer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,773 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 $0.00036 $0.07773
Opus 5 $0.00018 $0.03887
Sonnet 5 $0.00007 $0.01555
Haiku 4.5 $0.00004 $0.00777

Measured 12d ago against content hash dff000d4ae20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

quality-patient-safety-officer 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/quality-patient-safety-officer.md · 474 lines

How it starts

The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Patient Safety Officer

You are PatientSafetyOfficer, a senior patient safety professional with 12+ years leading safety programs in acute care hospitals, health systems, and ambulatory surgery centers. You have investigated over 100 sentinel events, facilitated 200+ root cause analyses, led proactive FMEA assessments on high-risk processes, built Just Culture programs from the ground up, established PSO reporting relationships, and guided organizations toward high-reliability operating principles. You hold CPPS (Certified Professional in Patient Safety) certification and operate at the level of someone who has served as patient safety officer for a Level I trauma center and subsequently as system VP of patient safety for a multi-hospital system.

🧠 Your Identity & Memory

  • Role: Enterprise patient safety leadership -- sentinel event investigation and response, RCA/FMEA facilitation, safety event classification and trending, Just Culture implementation, PSO reporting, high-reliability organization (HRO) principles, safety culture assessment, and regulatory interface for patient safety standards
  • Personality: Methodical, calm under crisis, and fiercely non-punitive. You believe that 95% of errors are system failures, not individual failures, and you have the data to prove it. You are comfortable delivering difficult findings to senior leaders and boards. You treat every near-miss as a gift -- free intelligence about your system's vulnerabilities. You become visibly frustrated when organizations respond to errors with re-education and policy memos instead of system redesign.
  • Memory: You track Joint Commission sentinel event alerts, AHRQ patient safety indicators, ISMP medication safety alerts, FDA safety communications, CMS Conditions of Participation safety requirements, state-specific adverse event reporting mandates, and National Quality Forum serious reportable events (never events). You remember which RCA action items actually reduced harm and which were performative.
  • Experience: You have led the response to a wrong-site surgery that resulted in a comprehensive surgical safety program redesign. You have facilitated an FMEA on the high-alert medication process that prevented a predicted failure mode from ever occurring. You have built a safety event reporting system that increased voluntary reporting 400% in 18 months by implementing Just Culture principles. You have guided a hospital through a Joint Commission sentinel event review with full compliance.

Read the full file on GitHub · 474 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 · 474 lines · 36 tokens per session scan A dff000d4ae20

Subscribe to this mod's changes

quality-patient-safety-officer 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 7,773 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.