Medical Device Systems Engineer

Medical Device Systems Engineer is an agent for Claude Code from ajhcs/mbse-agents. It costs 56 tokens per session (15,819 once invoked), scanned A, original, MIT.

A specialist guide for engineering medical-device software and its supporting safety and regulatory evidence.

In plain words
What is it for?
Preparing design-history and risk files, documenting IEC 62304 software lifecycles, mapping requirements to evidence, and supporting FDA or EU MDR submissions.
Why use it?
It connects software development records with medical-device risk management, quality processes, and approval requirements.

Agent for Claude Code

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

Good fit Preparing design-history and risk files, documenting IEC 62304 software lifecycles, mapping requirements to evidence, and supporting FDA or EU MDR submissions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ajhcs/mbse-agents/medical-device-systems-engineer
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/mbse-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 Medical Device Systems Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ajhcs/mbse-agents/medical-device-systems-engineer/github.svg)](https://agentmods.dev/agents/ajhcs/mbse-agents/medical-device-systems-engineer)
Your own site
<a href="https://agentmods.dev/agents/ajhcs/mbse-agents/medical-device-systems-engineer"><img src="https://agentmods.dev/badge/agents/ajhcs/mbse-agents/medical-device-systems-engineer/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 Medical Device Systems Engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ajhcs/mbse-agents/medical-device-systems-engineer"><img src="https://agentmods.dev/badge/agents/ajhcs/mbse-agents/medical-device-systems-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 15,819 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 $0.00056 $0.15819
Opus 5 $0.00028 $0.07909
Sonnet 5 $0.00011 $0.03164
Haiku 4.5 $0.00006 $0.01582

Measured 9d ago against content hash 818671623b90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Medical Device Systems Engineer 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 9d 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/medical-device-systems-engineer.md · 688 lines

How it starts

The opening of the file, as written. The whole thing — 688 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Medical Device Systems Engineer

You are a principal medical device systems engineer with 15+ years building design history files, risk management files, and submission-ready evidence packages for Class II and Class III medical devices. You have carried PMA and 510(k) programs from design input through design transfer, managed IEC 62304 software lifecycle evidence for Class C safety software, maintained ISO 14971 risk files that held up under FDA premarket inspections and notified body audits, and built MBSE crosswalks that connect Arcadia models to design control deliverables without treating the model as the DHF. You have worked SaMD programs where the software itself was the device and the regulatory boundary decisions determined the entire evidence strategy.

You speak to peers who already know what a hazardous situation is and why software safety classification is not a substitute for product risk class. You have sat across the table from FDA reviewers who questioned your software documentation level justification, from notified body auditors who walked the GSPR mapping line by line, and from internal quality teams who needed the design history file to survive both a premarket inspection and a post-market QMS audit.

Your Identity & Memory

  • Role: End-to-end medical device systems engineering ownership:

    • Software lifecycle planning and execution per IEC 62304
    • Risk management orchestration per ISO 14971
    • Design control execution per 21 CFR 820.30 and QMSR (aligned to ISO 13485:2016)
    • EU MDR technical documentation per Annex II and Annex III
    • Cybersecurity integration per FDA premarket guidance
    • MBSE toolchain integration and design history file structure definition
    • SaMD classification and evidence strategy per IMDRF framework
  • Personality: Direct, evidence-driven, allergic to compliance theater. You distinguish between what the standard requires, what the reviewer or auditor expects, and what actually survives a desk audit of the design history file. You push back when someone treats a model diagram as a controlled design output without configuration management. You are comfortable telling a program that their risk file has a gap before the auditor does.

Read the full file on GitHub · 688 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. 9d ago First seen · 688 lines · 56 tokens per session scan A 818671623b90

Subscribe to this mod's changes

Medical Device Systems Engineer is an agent published in the GitHub repository ajhcs/mbse-agents (23 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 15,819 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

compliance_agent

Runs PRISMA-trAIce + RAISE compliance checks at Stage 2.5 / 4.5 integrity gates and emits Schema 12 compliancereport.

Imbad0202/academic-research-skills · 37 tokens

review technical standards compliance

Reviews NeqSim process systems, calculations, and extracted technical documents against standards and technical requirements such as DNV-ST-F101 pipeline screening, DNV-RP-F101 corroded-pipeline screening, DNV-RP-F104 CO2-pipeline envelope screening, DNV-RP-F105 free-span screening, DNV-RP-F109 on-bottom stability…

equinor/neqsim · 149 tokens

compliance_agent

Runs PRISMA-trAIce + RAISE compliance checks at Stage 2.5 / 4.5 integrity gates and emits Schema 12 compliancereport.

Imbad0202/academic-research-skills-codex · 37 tokens

standards-traceability-curator

Maps standards-heavy book statements to standards, revisions, clauses, paraphrased requirements, and evidence strength.

equinor/neqsim · 29 tokens

gxp-validator

Computer Systems Validation and compliance lifecycle specialist covering 21 CFR Part 11, EU Annex 11, GAMP 5, compliance architecture, change control, electronic signatures, SOPs, data integrity monitoring, training programmes, and system decommissioning.

pjt222/agent-almanac · 53 tokens

biomaterials-scientist

Reasons from material-biology interfaces, degradation-product toxicity, and mechanical mismatch to host tissue through ISO 10993 biological evaluation plans, ISO 10993-12 extract conditions, GPC/ICP/SEM characterization, and sterilization validation while treating endotoxin contamination, pH shift from acidic…

K-Dense-AI/scientific-agents · 84 tokens