agentmods.dev

dicom-medical-imaging

dicom-medical-imaging is a skill for Claude Code, Codex from hamzabellouch/agent-skills. It costs 53 tokens per session (1,786 once invoked), scanned A, original, MIT.

A guide to handling medical images with DICOM, the standard format used by hospitals, and DICOMweb, its web-based API. It covers PACS image systems, privacy removal, and displaying images in browsers with Cornerstone.js.

In plain words
What is it for?
Use it to connect to PACS systems, query, upload, and retrieve images through DICOMweb, anonymize patient data, and render scans in a web application.
Why use it?
It helps applications exchange and display clinical images while preserving the required patient, study, series, and image relationships and removing identifying information when needed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 4repo 1mo ago A scan 53 tokens original MIT

Good fit Use it to connect to PACS systems, query, upload, and retrieve images through DICOMweb, anonymize patient data, and render scans in a web application.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamzabellouch/agent-skills/dicom-medical-imaging
View source ↗ hamzabellouch/agent-skills sites.google.com
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 hamzabellouch/agent-skills --skill dicom-medical-imaging
Clone the repo
git clone --depth 1 https://github.com/hamzabellouch/agent-skills

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 dicom-medical-imaging

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/dicom-medical-imaging/github.svg)](https://agentmods.dev/skills/hamzabellouch/agent-skills/dicom-medical-imaging)
Your own site
<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/dicom-medical-imaging"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/dicom-medical-imaging/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 dicom-medical-imaging

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/dicom-medical-imaging"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/dicom-medical-imaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,786 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 $0.00053 $0.01786
Opus 5 $0.00026 $0.00893
Sonnet 5 $0.00011 $0.00357
Haiku 4.5 $0.00005 $0.00179

Measured 8d ago against content hash 937cb5f7eea0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dicom-medical-imaging 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 8d 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.

Digital Health and BioTech (FHIR and HL7)/dicom-medical-imaging/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DICOM Medical Imaging & PACS Architecture

Overview

This skill provides technical standards for handling, parsing, transmitting, and displaying medical imaging datasets via DICOM (Digital Imaging and Communications in Medicine) and DICOMweb RESTful Services. It covers PACS server integration, DICOM anonymization for HIPAA compliance, and web rendering with Cornerstone.js.

1. Medical Imaging Architecture Principles

  1. DICOM Hierarchy Compliance: Respect the core 4-level DICOM object model: Patient -> Study -> Series -> Instance (Image).
  2. Prefer DICOMweb over C-STORE/C-FIND: Use DICOMweb RESTful standards (QIDO-RS for query, WADO-RS for retrieve, STOW-RS for store) for modern web and cloud integrations rather than legacy DIMSE network protocols over raw sockets.
  3. Mandatory PHI De-Identification: Anonymize Protected Health Information (PHI) tags before transmitting images outside secure clinical perimeters. Strip tags like PatientName (0010,0010), PatientID (0010,0020), PatientBirthDate (0010,0030), and burn-in annotations.
  4. Lossless Compression Standards: Maintain lossless compression (JPEG 2000 Lossless, High-Throughput JPEG 2000) for diagnostic primary readings; allow lossy compression only for fast web preview thumbnails.
  5. Zero-Footprint Web Viewers: Utilize WebGL / WebGPU viewports (e.g., Cornerstone3D) for cross-platform rendering of 16-bit CT/MRI arrays directly in web browsers.

2. PACS & DICOMweb Pipeline

[ Modality (CT / MRI Scanner) ]
       │  Legacy DIMSE (C-STORE)
       ▼
[ PACS Server (Orthanc / dcm4chee) ] ──(STOW-RS / DICOMweb)
       │
       ├── QIDO-RS (JSON Metadata Search) ──▶ [ Web PACS Client / AI Inference ]
       ├── WADO-RS (Retrieve Instance Frames)
       └── DICOM De-identifier Service ────▶ [ Anonymized Research Dataset ]
DICOMweb Service Protocol / Action Equivalent DIMSE Primary Use Case
QIDO-RS GET /studies?PatientID=123 C-FIND Query studies, series, and instances
WADO-RS GET /studies/{uid}/series/{uid}/instances/{uid} C-MOVE / C-GET Retrieve pixel data / frame arrays
STOW-RS POST /studies C-STORE Store DICOM instances to PACS
WADO-URI GET /object?requestType=WADO N/A Simple JPEG/PNG rendering request

Read the full file on GitHub · 158 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. 8d ago First seen · 158 lines · 53 tokens per session scan A 937cb5f7eea0

Subscribe to this mod's changes

dicom-medical-imaging is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,786 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 2026-09-03.

Backend and APIsClaude CodeScientificagent-skillsai-agentantigravitycodex-clicursor
Related

Other skills, from other repositories

ubiquitous-language

Maintain a project thesaurus (domain glossary) following DDD ubiquitous language principles. Use PROACTIVELY when naming anything: variables, functions, classes, modules, database fields, API endpoints, events, files, or directories. Also use when the user asks to "create thesaurus", "update glossary", "add term"…

CodeAlive-AI/ai-driven-development · 179 tokens

semantic-scholar-deep

Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation…

CodeAlive-AI/ai-driven-development · 163 tokens

laravel-expert

Laravel & PHP Development Instructions for GitHub Copilot.

GulajavaMinistudio/awesome-copilot-id · 15 tokens

thesis-control

Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.

yha9806/academic-writing-toolkit · 57 tokens

manuscript-reframe

Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.

yha9806/academic-writing-toolkit · 53 tokens

nodejs-codestyle

Custom Instructions: Node.js Backend & Architecture Expert.

GulajavaMinistudio/awesome-copilot-id · 15 tokens