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 aizech/clinical-skills --skill radiology-report-analysisgit 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/radiology-report-analysis)<a href="https://agentmods.dev/skills/aizech/clinical-skills/radiology-report-analysis"><img src="https://agentmods.dev/badge/skills/aizech/clinical-skills/radiology-report-analysis/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/aizech/clinical-skills/radiology-report-analysis"><img src="https://agentmods.dev/badge/skills/aizech/clinical-skills/radiology-report-analysis.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 | $0.00057 | $0.02810 |
| Opus 5 | $0.00028 | $0.01405 |
| Sonnet 5 | $0.00011 | $0.00562 |
| Haiku 4.5 | $0.00006 | $0.00281 |
Grade A, and why
radiology-report-analysis 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radiology Report Analysis
You are a radiology report analysis expert. Your role is to extract, interpret, and structure information from radiology reports.
Report Structure
Standard Report Sections
RADIOLOGY REPORT
├── Header Information
│ ├── Patient ID
│ ├── Study Date
│ ├── Modality
│ ├── Referring Physician
│ └── Accession Number
├── Clinical History
├── Examination/Study Description
├── Findings
│ ├── Organ System 1
│ ├── Organ System 2
│ └── ...
└── Impression
├── Primary Finding (numbered)
├── Secondary Finding
└── Recommendations
Extraction Patterns
Findings Extraction
Extract findings from free-text reports:
def extract_findings(report_text):
sections = parse_report_sections(report_text)
findings = []
# Pattern: Finding descriptions often start with bullets, numbers, or organ names
finding_patterns = [
r'[-•]\s*(.+)', # Bullet points
r'\d+\.\s+([A-Z][^:]+):\s*(.+)', # Numbered with colon
r'([A-Z][a-z]+(?:\s+[a-z]+)?):\s*(.+)', # Organ: description
]
for pattern in finding_patterns:
matches = re.finditer(pattern, report_text)
for match in matches:
findings.append({
'organ': extract_organ(match),
'description': match.group(1) if match.lastindex else match.group(0),
'severity': classify_severity(match)
})
return findings
Impression Extraction
def extract_impression(report_text):
# Look for IMPRESSION section
impression_pattern = r'IMPRESSION[:\s]+(.+?)(?:\n\n|\Z)'
match = re.search(impression_pattern, report_text, re.DOTALL | re.IGNORECASE)
if match:
impression_text = match.group(1)
# Parse numbered impressions
impressions = re.findall(r'\d+\.\s*(.+?)(?=\n\d+\.|\Z)', impression_text)
return impressions
# Fallback: last paragraph is often impression
paragraphs = report_text.split('\n\n')
return [paragraphs[-1]] if paragraphs else []
What ships with it
1 file 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.
- 11d ago First seen · 371 lines · 57 tokens per session scan A aaf66b5a0ba9
radiology-report-analysis is a skill published in the GitHub repository aizech/clinical-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 2,810 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 2026-08-31.
Other skills, from other repositories
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.
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.
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.
stat-research-orchestrator
Orchestrate a statistical research pipeline centered on formal problem formulation, method proposal, theoretical analysis, experimental evaluation, comparison, and final result synthesis.