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.
npx skills add aks-builds/healthcareskills --skill fda-samdgit clone --depth 1 https://github.com/aks-builds/healthcareskillsWrote 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/skills/aks-builds/healthcareskills/fda-samd)<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.
<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>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 | $0.00190 | $0.03283 |
| Opus 5 | $0.00095 | $0.01641 |
| Sonnet 5 | $0.00038 | $0.00657 |
| Haiku 4.5 | $0.00019 | $0.00328 |
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.
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 |
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.
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.
- 11d ago First seen · 265 lines · 190 tokens per session scan A 99739dffa863
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.
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…
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…
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…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
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.
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.