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 tondevrel/scientific-agent-skills --skill pydicomgit clone --depth 1 https://github.com/tondevrel/scientific-agent-skillsWrote 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/tondevrel/scientific-agent-skills/pydicom)<a href="https://agentmods.dev/skills/tondevrel/scientific-agent-skills/pydicom"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/pydicom/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/tondevrel/scientific-agent-skills/pydicom"><img src="https://agentmods.dev/badge/skills/tondevrel/scientific-agent-skills/pydicom.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 | $0.00048 | $0.00777 |
| Opus 5 | $0.00024 | $0.00388 |
| Sonnet 5 | $0.00010 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
pydicom 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 11d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pydicom - Medical Imaging Standards
DICOM is more than an image; it's a rich data structure containing patient info, spatial orientation, and pixel data. Pydicom provides access to all these tags.
When to Use
- Processing medical imaging data (CT, MRI, X-ray, ultrasound).
- Extracting patient metadata and clinical information from DICOM files.
- Building AI models for radiology that require both image and metadata.
- Converting DICOM to other formats for analysis.
- Quality assurance and compliance checking in medical imaging workflows.
Core Principles
Datasets as Dicts
Access tags by name (e.g., ds.PatientName) or ID (ds[0x0010, 0x0010]).
Pixel Data
Raw pixel data is stored in PixelData, but should be accessed via pixel_array for NumPy integration.
VR (Value Representation)
Strict typing for dates, ages, and decimals ensures data integrity.
Quick Reference
Standard Imports
import pydicom
from pydicom.data import get_testdata_files
import matplotlib.pyplot as plt
import numpy as np
Basic Patterns
# 1. Read file
ds = pydicom.dcmread("scan.dcm")
# 2. Access Metadata
print(f"Patient: {ds.PatientName}, ID: {ds.PatientID}")
print(f"Modality: {ds.Modality}") # CT, MR, DX
print(f"Study Date: {ds.StudyDate}")
print(f"Slice Thickness: {ds.SliceThickness}")
# 3. Access Image
plt.imshow(ds.pixel_array, cmap="gray")
plt.title(f"{ds.Modality} - {ds.PatientName}")
Critical Rules
✅ DO
- Use pixel_array property - Always access pixel data via
ds.pixel_arrayrather thands.PixelDatafor proper NumPy integration. - Check for missing tags - Use
hasattr(ds, 'TagName')before accessing optional tags. - Respect patient privacy - DICOM files contain PHI (Protected Health Information). Always anonymize before sharing.
- Handle different photometric interpretations - Some images may be inverted or use different color spaces.
❌ DON'T
- Don't modify DICOM files in place - Always create a copy when modifying to preserve original data.
- Don't ignore VR types - DICOM has strict data types. Converting incorrectly can corrupt data.
- Don't assume all DICOM files have images - Some contain only metadata (structured reports).
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.
- 11d ago First seen · 105 lines · 48 tokens per session scan A 7ef18fe0ae2c
pydicom is a skill published in the GitHub repository tondevrel/scientific-agent-skills (21 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 777 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
bioservices
Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use…
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…