fda-samd

fda-samd is a skill for Claude Code from aks-builds/healthcareskills. It costs 190 tokens per session (3,283 once invoked), scanned A, original, MIT.

Guidance for assessing and managing software that may be regulated as a medical device by the U.S. Food and Drug Administration, or FDA. It covers classification, submission routes, quality processes, and ongoing maintenance.

In plain words
What is it for?
Use it to assess medical software, plan an FDA submission, design quality controls, or manage an approved or cleared device after release.
Why use it?
Software used in medical decisions may have regulatory obligations that depend on what it does, who uses it, and the risk of errors. This helps teams organize those questions without treating the guidance as legal advice.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the healthcare-skills plugin — 41 skills shipped together , and of healthcare-skills

Good fit Use it to assess medical software, plan an FDA submission, design quality controls, or manage an approved or cleared device after release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aks-builds/healthcareskills/fda-samd
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.

Any agent
npx skills add aks-builds/healthcareskills --skill fda-samd
Clone the repo
git clone --depth 1 https://github.com/aks-builds/healthcareskills

Made for: Claude Code.

Or install healthcare-skills, the plugin that ships this one along with the rest of its 41 skills.

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 fda-samd

README.md
[![agentmods](https://agentmods.dev/badge/skills/aks-builds/healthcareskills/fda-samd/github.svg)](https://agentmods.dev/skills/aks-builds/healthcareskills/fda-samd)
Your own site
<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/fda-samd"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/fda-samd/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 fda-samd

Your own site · 80×15
<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/fda-samd"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/fda-samd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,283 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 $0.00190 $0.03283
Opus 5 $0.00095 $0.01641
Sonnet 5 $0.00038 $0.00657
Haiku 4.5 $0.00019 $0.00328

Measured 11d ago against content hash 99739dffa863, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fda-samd 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.

skills/fda-samd/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDA Software as a Medical Device (SaMD)

You are an expert in FDA software regulation, with a focus on Software as a Medical Device (SaMD) and ML-enabled medical devices. Your goal is to help engineers and product owners reason about whether their software is regulated, which premarket pathway applies, how to design under quality systems, and how to maintain the device after clearance — without giving legal advice. Final regulatory determinations belong to the regulatory affairs team and FDA.

Initial Assessment

Read .agents/healthcare-context.md first (fall back to .claude/healthcare-context.md). Use it to determine:

  • Whether the user is the device manufacturer, an integrator, or a covered entity using a device.
  • Current regulatory status (research / IRB, enterprise CDS, cleared, PMA).
  • AI/ML involvement.
  • Geographies of distribution (US-only or US + EU/UK/CA/AU/JP).

If missing, ask: what does the software do, who is the user, who is the patient, what decision does it support, and what is the harm if it's wrong.


SaMD Definition (IMDRF)

The International Medical Device Regulators Forum (IMDRF) defines SaMD as software intended to be used for one or more medical purposes that performs those purposes without being part of a hardware medical device.

  • Software embedded in / required for a hardware device (e.g., infusion pump firmware) is not SaMD — it is software in a medical device.
  • Standalone clinical software that interprets images, predicts disease, or recommends treatment can be SaMD.
  • Wellness apps that do not make medical claims are generally not SaMD.

FDA aligns to the IMDRF framework but uses US-specific terminology and authorities.


IMDRF Risk Categorization

SaMD is categorized by the combination of healthcare situation and significance of information.

Healthcare situation \ Significance Inform clinical management Drive clinical management Treat or diagnose
Non-serious I I II
Serious I II III
Critical II III IV

Read the full file on GitHub · 265 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 265 lines · 190 tokens per session scan A 99739dffa863

Subscribe to this mod's changes

fda-samd is a skill published in the GitHub repository aks-builds/healthcareskills (1 stars, last pushed yesterday), licensed MIT. It adds 190 tokens to every session and 3,283 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories

fiscaliste

Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…

romainsimon/paperasse · 302 tokens

fedramp

Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · 236 tokens

eu-cra

Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · 133 tokens

aenderungsvorbehalt-308

Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 41 tokens

agb-rechtswahl-schweizer-recht-rom-i

Für AGB Rechtswahl Schweizer Recht Rom I: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-rechtswahl-schweizer-recht-rom-i.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

agb-leasingvertrag-fortwirkung-schiedsklausel

Für AGB im Leasingvertrag Fortwirkung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-leasingvertrag-fortwirkung-schiedsklausel.

Klotzkette/claude-fuer-deutsches-recht · 70 tokens