time-dependent-roc

time-dependent-roc is a skill for Claude Code, Codex from aipoch/medical-research-skills. It costs 78 tokens per session (1,650 once invoked), scanned A, original, MIT.

A statistical workflow for checking how well a numeric risk marker predicts events at different follow-up times in survival data, such as time until death or relapse.

In plain words
What is it for?
Use it with CSV, text, or Excel files containing follow-up time, event status, and a numeric marker. It calculates and plots time-dependent ROC curves and exports AUC tables and ROC points.
Why use it?
A standard ROC curve does not account for changing follow-up or censoring, where the event time is unknown for some people. This workflow produces time-specific AUC values and ROC data in consistent output folders.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with CSV, text, or Excel files containing follow-up time, event status, and a numeric marker. It calculates and plots time-dependent ROC curves and exports AUC tables and ROC points.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aipoch/medical-research-skills/time-dependent-roc
About the project

Medical Research Agent Skills is a library of agent instructions for medical and biomedical research, covering evidence analysis, study protocol design, data analysis, and academic writing. Researchers use it to guide compatible coding agents through common scientific workflows. The catalogue contains many of the library's skills and commands.

aipoch/medical-research-skills · 1,860 stars · on GitHub · aipoch.com

Install

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.

Any agent
npx skills add aipoch/medical-research-skills --skill time-dependent-roc
Clone the repo
git clone --depth 1 https://github.com/aipoch/medical-research-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for time-dependent-roc

README.md
[![agentmods](https://agentmods.dev/badge/skills/aipoch/medical-research-skills/time-dependent-roc/github.svg)](https://agentmods.dev/skills/aipoch/medical-research-skills/time-dependent-roc)
Your own site
<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/time-dependent-roc"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/time-dependent-roc/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.

agentmods 80×15 button for time-dependent-roc

Your own site · 80×15
<a href="https://agentmods.dev/skills/aipoch/medical-research-skills/time-dependent-roc"><img src="https://agentmods.dev/badge/skills/aipoch/medical-research-skills/time-dependent-roc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01650
Opus 5 $0.00039 $0.00825
Sonnet 5 $0.00016 $0.00330
Haiku 4.5 $0.00008 $0.00165

Measured 9d ago against content hash d40f27d6982a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

time-dependent-roc 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 9d 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.

awesome-med-research-skills/Data Analysis/time-dependent-roc/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source: https://github.com/aipoch/medical-research-skills

Time-Dependent ROC Analysis

Use this skill to compute and plot time-dependent ROC curves for survival outcomes.

Use This Skill When

  • You have survival data with futime and fustat columns.
  • You need time-specific ROC curves and AUC values for a numeric risk marker.
  • You want a command-line workflow with parameter validation and standardized outputs.
  • Your file contains a numeric marker column named risk_score, or you will provide another marker explicitly with --marker_col.

Primary Command

Rscript scripts/main.R \
  --data_file <input_file> \
  --times <comma_separated_times> \
  --output_dir <output_dir>

Prerequisites

  • Rscript is available in the shell.
  • Required R packages: optparse, timeROC, survival, ggplot2.
  • Optional package for Excel input: openxlsx.
  • Install missing packages with Rscript -e 'install.packages(c("optparse", "timeROC", "survival", "ggplot2", "openxlsx"), repos="https://cloud.r-project.org")'.

Core Arguments

Argument Required Description
--data_file Yes Input data file in CSV, TXT, TSV, TAB, XLS, or XLSX format
--times No Prediction time points, comma-separated. Default 1,3,5
--marker_col No Marker column name. Default risk_score; provide this option when your file uses a different marker
--output_dir No Output directory, default ./TimeROC_Results
--time_unit No Time unit label for plot/output: year, month, or day. Default year
--auto_convert_days No If TRUE, convert large futime values from days to the selected unit when appropriate. Default TRUE
--weighting No IPCW weighting method: aalen, marginal, or cox. Default aalen
--cause No Event code treated as the outcome of interest. Default 1

Input Requirements

  • The input file must contain futime and fustat columns.
  • The selected marker column must exist and be numeric or coercible to numeric.
  • If --marker_col is omitted, the input file must contain risk_score.
  • futime must be numeric or coercible to numeric.
  • fustat must be numeric or coercible to numeric.
  • Rows with missing futime, fustat, or marker values are excluded.
  • At least 5 complete rows and at least 1 event for the requested cause are required.

Read the full file on GitHub · 179 lines

Changes

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.

  1. 9d ago First seen · 179 lines · 78 tokens per session scan A d40f27d6982a

Subscribe to this mod's changes

time-dependent-roc is a skill published in the GitHub repository aipoch/medical-research-skills (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,650 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 2026-09-03.

Related

Other skills, from other repositories