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 agentmods add skills/aizech/clinical-skills/modality-detectionnpx skills add aizech/clinical-skills --skill modality-detectiongit clone --depth 1 https://github.com/aizech/clinical-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/aizech/clinical-skills/modality-detection)<a href="https://agentmods.dev/skills/aizech/clinical-skills/modality-detection"><img src="https://agentmods.dev/badge/skills/aizech/clinical-skills/modality-detection.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.02154 |
| Opus 5 | $0.00036 | $0.01077 |
| Sonnet 5 | $0.00015 | $0.00431 |
| Haiku 4.5 | $0.00007 | $0.00215 |
Grade A, and why
modality-detection 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 6d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modality Detection
You are a radiology modality detection expert. Your role is to accurately identify the imaging modality from various input formats.
Modality Categories
Primary Modalities
| Modality | Code | Description |
|---|---|---|
| Computed Tomography | CT, CT-A | X-ray cross-sections, often with contrast |
| Magnetic Resonance Imaging | MR, MR-A | Magnetic field imaging, no radiation |
| Plain Radiography | CR, DX | Projectional X-ray images |
| Ultrasound | US | Sound wave imaging, no radiation |
| Mammography | MG | Breast imaging, specialized X-ray |
| Nuclear Medicine | NM, PT, PET | Radioactive tracer imaging |
| Fluoroscopy | RF | Real-time X-ray video |
Hybrid/Advanced Modalities
| Modality | Code | Description |
|---|---|---|
| PET/CT | PT/CT | Combined PET and CT |
| PET/MR | PT/MR | Combined PET and MRI |
| SPECT/CT | NM/CT | Combined SPECT and CT |
| CT Angiography | CTA | CT with arterial contrast timing |
| MR Angiography | MRA | MRI for vessel imaging |
DICOM Modality Codes
Standard DICOM modality values:
- CT: Computed Tomography
- MR: Magnetic Resonance
- DX: Digital Radiography
- CR: Computed Radiography
- US: Ultrasound
- MG: Mammography
- NM: Nuclear Medicine
- PT: PET
- RF: Radio Fluoroscopy
- XA: X-Ray Angiography
- OP: Ophthalmic Photography
- ES: Endoscopy
Detection Patterns
From Text Input
Extract modality from clinical text using these patterns:
def detect_modality(text):
text_upper = text.upper()
# Exact matches first
if "PET/CT" in text_upper:
return "PET/CT"
if "CT ANGIOGRAPHY" in text_upper or "CTA" in text_upper:
return "CTA"
if "MR ANGIOGRAPHY" in text_upper or "MRA" in text_upper:
return "MRA"
if "DIGITAL MAMMOGRAPHY" in text_upper or "SCREENING MAMMO" in text_upper:
return "Mammography"
# Pattern matching
if "CT " in text_upper or text_upper.startswith("CT"):
return "CT"
if "MRI " in text_upper or text_upper.startswith("MR ") or "MAGNETIC RESONANCE" in text_upper:
return "MRI"
if "X-RAY" in text_upper or "CHEST X" in text_upper or "DX " in text_upper:
return "X-ray"
if "ULTRASOUND" in text_upper or "SONOGRAPHY" in text_upper or "US " in text_upper:
return "Ultrasound"
if "MAMMO" in text_upper or "BREAST" in text_upper:
return "Mammography"
if "PET " in text_upper or "PET-" in text_upper:
return "PET/CT"
return None # Unknown
What ships with it
2 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.
- 6d ago First seen · 276 lines · 73 tokens per session scan A 308bc6dd2642
modality-detection is a skill published in the GitHub repository aizech/clinical-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 2,154 once invoked, about $0.0004 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
quantum-qiskit
Reference qiskit 2.x patterns for variational quantum machine learning. Covers data-encoding feature maps, variational quantum classifier (VQC) training, variational quantum eigensolver (VQE) for chemistry, matrix-product-state circuits, and noise model integration. Use when writing Python code that imports qiskit…
fba-simulator
Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
gsmm-validator
Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.
metabolic-study-planner
Plan publishable constraint-based metabolic modelling studies when the user has a broad biological or metabolic-engineering topic but no concrete dataset, organism, model, or hypothesis. Selects feasible BiGG/COBRA models, objectives, perturbations, analyses, metrics, figures, and risk controls before FBA code is…
gsmm-builder
Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.