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 mxslr/mlcraft --skill domain-medical-imaginggit clone --depth 1 https://github.com/mxslr/mlcraftWrote 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/mxslr/mlcraft/domain-medical-imaging)<a href="https://agentmods.dev/skills/mxslr/mlcraft/domain-medical-imaging"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-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.
<a href="https://agentmods.dev/skills/mxslr/mlcraft/domain-medical-imaging"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/domain-medical-imaging.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 | $0.00139 | $0.00835 |
| Opus 5 | $0.00069 | $0.00417 |
| Sonnet 5 | $0.00028 | $0.00167 |
| Haiku 4.5 | $0.00014 | $0.00084 |
Grade A, and why
domain-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 10d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Medical Imaging - Method Selection & Rigor
High stakes + small, leaky-prone datasets. Rigor matters more than architecture.
Decision table
| Sub-task | Recommended | Notes |
|---|---|---|
| 2D scan classification (mammo, X-ray, derm, fundus) | EfficientNet(-B3..B5) / ConvNeXt, ImageNet-pretrained | Modern-but-not-huge backbones win on low/medium-quality medical data; giant models often don't transfer better. |
| Whole-image with tiny lesions | Weakly-supervised localization (GMIC-style) or patch-pretrain then whole-image (Shen-style) | Best whole-image ceiling; also yields saliency maps for clinicians. |
| Multi-view study (e.g., CC+MLO mammo) | Two-view / multi-input fusion | Biggest research-backed lever over single view. |
| 3D volumes (CT/MRI) | 3D U-Net / nnU-Net (seg), 2.5D or 3D CNN (classify) | nnU-Net is a very strong segmentation default. |
| Histopathology WSI | MIL / CLAM on tiles | Gigapixel images, so tile them and use multiple-instance learning. |
| Lesion/organ segmentation | U-Net / nnU-Net / SegFormer | Dice/IoU. |
Non-negotiable rigor (this is where most medical ML fails)
- PATIENT-LEVEL split. All images/views/slices of one patient in ONE split. Use the dataset's official split when it exists (often encoded in the ID). Add asserts (
data-rigor-and-leakage). Random per-image splitting is the classic fake-accuracy trap. - Whole-image vs ROI-crop honesty. Cropped-lesion ROI classification is an easier, different problem; ~98-99% papers are usually ROI-crop and/or leaky. Report which one you are doing and never conflate.
- Medical preprocessing: CLAHE for contrast; crop to the organ/breast (largest connected component) to drop background/labels/tape; remove confounders (e.g., pectoral muscle on mammogram MLO - verify the model isn't attending to it via Grad-CAM); intensity normalization (windowing for CT, z-score for MRI). Apply identically at inference (parity).
- Clinical operating point: report sensitivity AND specificity; prefer a high-sensitivity threshold (recall ≥ ~0.90) chosen on validation - missing cancer >> a false alarm. Don't ship a 0.5 or Youden threshold blindly.
- Calibration: temperature-scale probabilities so "78% malignant" is trustworthy for decision support.
- Framing: decision-support / second-reader, NOT autonomous diagnosis; prototype needs clinical + regulatory validation (
deployment-explainability).
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.
- 10d ago First seen · 30 lines · 139 tokens per session scan A d076bf0a0585
domain-medical-imaging is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 835 once invoked, about $0.0007 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
reinforcement-learning
Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…