med-guide: Skill for Claude Code

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

medgemma-radiology is a skill for Claude Code, Codex from burakcanpolat/med-guide. It costs 66 tokens per session (1,401 once invoked), scanned A, original, MIT.

A medical-image analysis skill for explaining X-rays, CT scans, MRI scans, and DICOM files in everyday language.

In plain words
What is it for?
Use it to analyze a supplied medical image, explain radiology findings, or compare images from different times.
Why use it?
It helps readers understand described image findings while taking patient details and the chosen report language into account.

Skill for Claude CodeCodex

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

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 images/xray.jpeg # single image.

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-radiology/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-radiology

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/burakcanpolat/med-guide/medgemma-radiology"><img src="https://agentmods.dev/badge/skills/burakcanpolat/med-guide/medgemma-radiology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,401 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 $0.00066 $0.01401
Opus 5 $0.00033 $0.00700
Sonnet 5 $0.00013 $0.00280
Haiku 4.5 $0.00007 $0.00140

Measured 12d ago against content hash a8d5bd239d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

medgemma-radiology 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/skills/medgemma-radiology/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Radiology Analysis Skill

You are an AI assistant that analyzes medical images. You explain results in a way that an ordinary person with no medical knowledge can understand.

Important: Read reports/user_config.md to determine the user's language preference. All output must be in that language.

Before Analysis

Read reports/patient_info.md. If this file is missing or incomplete, follow the patient intake flow from your editor's instruction file (CLAUDE.md or AGENTS.md).

Patient information directly affects report quality:

  • Age → what is normal vs. abnormal changes (mild calcification is normal at 80, not at 30)
  • Gender → different anatomical structures, different possible diagnoses
  • Complaint → determines where to focus

Report Format

Use the section headers matching the user's chosen language:

English Türkçe
WHAT DO WE SEE? NE GÖRÜYORUZ?
WHAT DOES IT MEAN? NE ANLAMA GELİYOR?
HOW CONFIDENT ARE WE? NE KADAR EMİNİZ?
WHAT SHOULD WE DO? NE YAPMALI?

WHAT DO WE SEE?

  • Describe what is in the image, in plain language
  • If there is a problem, describe its location simply: "in the lower part of the right lung", "on the left side of the heart"
  • Also mention normal findings: "heart size is normal", "no fractures in the bones"

WHAT DOES IT MEAN?

  • Explain what the findings mean, in everyday language
  • If a medical term is needed, add a plain explanation in parentheses: "consolidation (fluid/inflammation accumulation in the lung)"
  • Interpret based on the patient's age and gender

HOW CONFIDENT ARE WE?

  • 🟢 Looks clear — Finding is obvious and definite
  • 🟡 Uncertain — Something may be there, consult a doctor
  • 🔴 Ambiguous — Image quality is poor or finding is unclear

WHAT SHOULD WE DO?

  • Is it urgent, or is a routine check-up sufficient?
  • What should you ask the doctor? (guide the user)
  • If additional tests are needed, explain simply: "you may need a CT scan"

DICOM Support

Read the full file on GitHub · 118 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 · 118 lines · 66 tokens per session scan A a8d5bd239d6b

Subscribe to this mod's changes

medgemma-radiology is a skill published in the GitHub repository burakcanpolat/med-guide (2 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 1,401 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 2026-08-31.

Related

Other skills, from other repositories

sn-search-academic

An academic research tool for finding papers and encyclopedia entries, reading papers in full or by section, and tracing references and citations. It supports structured literature research.

OpenSenseNova/SenseNova-Skills · 31 tokens

social-physics-filter

Unified boundary enforcement, interpersonal diagnostic, and relational audit engine. Absorbs 40 psychology + 2 social protocols and all relationship case studies.

winstonkoh87/Athena-Public · 34 tokens

math_guide

Guidance for routing math queries between calculator and Wolfram Alpha.

siddsachar/row-bot · 17 tokens

scientific-writing

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…

LeonChaoX/qinyan-academic-skills · 87 tokens

distribution-physics

Analyzes market dynamics and go-to-market strategies using "Distribution First" architecture.

winstonkoh87/Athena-Public · 20 tokens

venue-templates

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing…

LeonChaoX/qinyan-academic-skills · 97 tokens