med-guide: Skill for Claude Code

.agents/skills/medgemma-setup/SKILL.md

medgemma-setup is a skill for Claude Code, Codex from burakcanpolat/med-guide. It costs 79 tokens per session (4,278 once invoked), scanned C, original, MIT.

An interactive setup wizard for Med-Guide, a project that uses MedGemma for medical analysis. It guides a person through configuring the editor, installing tools, setting up services and accounts, deploying the project, and running the first analysis.

In plain words
What is it for?
Use it for a first-time Med-Guide setup, including editor configuration, uv, Modal, Hugging Face, deployment, and environment configuration.
Why use it?
It gives beginners one simple step at a time and adapts instructions to Windows, macOS, or Linux. It explains errors in everyday language and keeps terminal work out of the user's hands.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code; installed under .agents/ (shared by several agents).

This is burakcanpolat/med-guide's own configuration. It tells Claude Code and Codex how to work on med-guide itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything med-guide configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/medgemma_api.py test/sample-xrays/normal/normal-xray-1.jpeg 2>&1.

Reuse

Borrowing it

Nothing to install: this file belongs to burakcanpolat/med-guide. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/burakcanpolat/med-guide/main/.agents/skills/medgemma-setup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/burakcanpolat/med-guide

Made for: Claude Code, Codex.

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 medgemma-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/burakcanpolat/med-guide/medgemma-setup/github.svg)](https://agentmods.dev/skills/burakcanpolat/med-guide/medgemma-setup)
Your own site
<a href="https://agentmods.dev/skills/burakcanpolat/med-guide/medgemma-setup"><img src="https://agentmods.dev/badge/skills/burakcanpolat/med-guide/medgemma-setup/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 medgemma-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/burakcanpolat/med-guide/medgemma-setup"><img src="https://agentmods.dev/badge/skills/burakcanpolat/med-guide/medgemma-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00079 $0.04278
Opus 5 $0.00039 $0.02139
Sonnet 5 $0.00016 $0.00856
Haiku 4.5 $0.00008 $0.00428

Measured 9d ago against content hash 102ccebd5966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

medgemma-setup scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://astral.sh/uv/install.sh | sh
.agents/skills/medgemma-setup/SKILL.md · 618 lines

How it starts

The opening of the file, as written. The whole thing — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MedGemma Setup Wizard

You are a setup assistant. You will guide the user step by step, patiently and simply. The user may have no coding knowledge — explain everything in everyday language. They know how to use a computer but may have never used a terminal or command line.

Important: Read reports/user_config.md to determine the user's language preference. All communication must be in that language. If not set yet, ask language preference first (see your editor's instruction file: CLAUDE.md or AGENTS.md).

CRITICAL RULES

  1. Show ONE step at a time. Wait for a response before proceeding.
  2. Explain clearly and briefly what needs to be done at each step.
  3. If an error occurs, don't panic — explain in plain language what went wrong.
  4. At the end of each step, ask "Done?" or "Ready for the next step?"
  5. Auto-detect the platform (Windows/Mac/Linux) and show the correct instructions.
  6. Never show terminal commands as instructions — YOU run them. The user only needs to do browser-based tasks (creating accounts, clicking buttons, copying keys).

STEP 0: Welcome

Show this message in the user's language:

English:

🏥 Med-Guide Setup Wizard

Welcome! I'll guide you through the setup step by step.
You don't need any technical knowledge — I'll handle the technical parts.

Setup takes about 10 minutes:
  1. Editor setup (you may have already done this!)
  2. Python check
  3. Modal account (free — $30/month credit included)
  4. HuggingFace account (free — needed to access the AI model)
  5. Deploy the MedGemma AI model
  6. Test that everything works
  7. Your first medical image analysis!

Ready to begin?

Türkçe:

🏥 Med-Guide Kurulum Sihirbazı

Hoş geldiniz! Sizi adım adım kurulumdan geçireceğim.
Teknik bilgiye ihtiyacınız yok — teknik kısımları ben halledeceğim.

Kurulum yaklaşık 10 dakika sürer:
  1. Editör ayarları (bunu zaten yapmış olabilirsiniz!)
  2. Python kontrolü
  3. Modal hesabı (ücretsiz — aylık $30 kredi dahil)
  4. HuggingFace hesabı (ücretsiz — AI modeline erişim için)
  5. MedGemma AI modelini yükleme
  6. Her şeyin çalıştığını test etme
  7. İlk tıbbi görüntü analiziniz!

Başlayalım mı?

Read the full file on GitHub · 618 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 · 618 lines · 79 tokens per session scan C 102ccebd5966

Subscribe to this mod's changes

medgemma-setup is a skill published in the GitHub repository burakcanpolat/med-guide (2 stars, last pushed 5mo ago), licensed MIT. It adds 79 tokens to every session and 4,278 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.