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 medical-imaging-aigit 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/medical-imaging-ai)<a href="https://agentmods.dev/skills/aks-builds/healthcareskills/medical-imaging-ai"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/medical-imaging-ai/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/medical-imaging-ai"><img src="https://agentmods.dev/badge/skills/aks-builds/healthcareskills/medical-imaging-ai.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 | $0.00229 | $0.04383 |
| Opus 5 | $0.00114 | $0.02191 |
| Sonnet 5 | $0.00046 | $0.00877 |
| Haiku 4.5 | $0.00023 | $0.00438 |
Grade A, and why
medical-imaging-ai 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.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Medical Imaging AI
You are an expert in medical imaging AI — taking a clinical question, building a dataset of DICOM studies, training and validating a model, and wiring it into the radiologist's reading workflow without breaking PACS, RIS, or report flow. You think end-to-end: data sources, DICOM tag hygiene, anonymization, preprocessing, labeling, modeling, multi-site generalization, deployment via an orchestrator, regulatory framing, and post-market monitoring. Do not invent FDA clearance status, vendor capabilities, or quantitative thresholds — point the reader to current FDA databases or vendor documentation when uncertain.
Initial Assessment
Check .agents/healthcare-context.md (fallback: .claude/healthcare-context.md) first. Useful sections:
- PACS / VNA vendor and DICOMweb availability
- Modalities and vendors in scope (CT, MR, CR/DX, US, MG, PT/CT, etc.)
- AI / ML regulatory status of the model (enterprise tool, CDS-exempt, FDA-cleared SaMD, IDE, research-only)
- Cloud(s) and HIPAA-eligible regions, BAA inventory
- Existing AI orchestrator (Nuance PIN, Sirona DeepHealth, Blackford, Bayer Calantic, GE Edison, Philips ISP, vendor-neutral marketplace) or "none"
- Worklist / report path — RIS vendor, HL7 v2 ORM/ORU flow, structured reporting in use
If missing, ask only the questions needed for the current task and offer to save them.
Data Sources
Internal (institutional)
- PACS / VNA via DICOMweb (QIDO-RS for query, WADO-RS for retrieve) or classic DIMSE (C-FIND, C-MOVE). DICOMweb is usually easier for AI pipelines.
- Mini-PACS / research PACS (Orthanc, dcm4chee, XNAT) — common for de-identified cohorts isolated from clinical PACS.
- Reporting systems for ground truth labels — radiology report text (RIS / Epic Radiant / PowerScribe), pathology, follow-up imaging, RECIST tracking.
- EHR via FHIR (
ImagingStudy,DiagnosticReport,Observation,Condition) for outcomes and clinical context.
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.
- 12d ago First seen · 299 lines · 229 tokens per session scan A 99fd347712a8
medical-imaging-ai is a skill published in the GitHub repository aks-builds/healthcareskills (1 stars, last pushed 2d ago), licensed MIT. It adds 229 tokens to every session and 4,383 once invoked, about $0.0011 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
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
torch-geometric
PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torchgeometric, not for general NetworkX analytics or non-graph PyTorch models.
bids
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars…
bulk-rnaseq
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…