model-validation

model-validation is a skill for Claude Code from Aperivue/medsci-skills. It costs 149 tokens per session (2,674 once invoked), scanned A, original, MIT.

A review and audit guide for clinical studies that test medical-imaging models, such as systems that segment, classify, or detect findings in scans.

In plain words
What is it for?
Use it to check data splits, reproducibility, study design, and metric choices before writing a validation report or paper.
Why use it?
It helps identify patient overlap, data leakage, test-set tuning, and other design problems that can make reported results untrustworthy.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: model in frontmatter.

Part of the medsci-modeling plugin — 12 skills shipped together

Good fit Use it to check data splits, reproducibility, study design, and metric choices before writing a validation report or paper.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aperivue/medsci-skills/model-validation
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 Aperivue/medsci-skills --skill model-validation
Clone the repo
git clone --depth 1 https://github.com/Aperivue/medsci-skills

Made for: Claude Code.

Or install medsci-modeling, the plugin that ships this one along with the rest of its 12 skills.

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 model-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/aperivue/medsci-skills/model-validation.svg)](https://agentmods.dev/skills/aperivue/medsci-skills/model-validation)
Your own site
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/model-validation"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/model-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,674 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.
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 $0.00149 $0.02674
Opus 5 $0.00075 $0.01337
Sonnet 5 $0.00030 $0.00535
Haiku 4.5 $0.00015 $0.00267

Measured 7d ago against content hash be75cfcf232c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

model-validation 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 7d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check_split_leakage_challenge/verify.sh, scripts/check_split_leakage.py, tests/test_split_leakage.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/model-validation/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model-Validation Skill

Purpose

This skill pressure-tests the validation study for an engineer-built medical-imaging model — the common case where a clinical team receives a trained segmentation / classification / detection model from an engineering collaborator and must validate it and write it up. It is the imaging-model specialization of /design-study: where design-study covers general validity and design-ai-benchmarking covers AI-versus-human-expert reader studies, this skill owns the partition, leakage, reproducibility, and metric-selection mechanics that decide whether a reported Dice / AUROC / sensitivity is trustworthy.

It is advisory and deterministic-audit only. It writes decision notes and runs a stdlib gate on the split table; it never builds, trains, or alters the model, and it never replaces MONAI / nnU-Net / TorchIO — those produce the model, this validates and publishes it.

When to use

  • A trained imaging model (in-house, vendor, or open-weights) needs a clinical-validation study designed or audited before submission.
  • You have, or can produce, the split-assignment table (which patient went to train / val / test).

When NOT to use

  • Building or training the model → out of scope (integrate MONAI / nnU-Net).
  • AI-versus-human-expert reader study → /design-ai-benchmarking.
  • LLM / MLLM evaluation → /mllm-eval (when available).
  • General study/validity review → /design-study.
  • Statistical execution (DeLong, ICC, bootstrap CIs, calibration tables) → /analyze-stats.
  • Item-by-item reporting-guideline audit of a finished manuscript → /check-reporting.
  • Reviewing a finished manuscript → /self-review or /peer-review (which load the MD0–MD11 reviewer-side probe).

Workflow

The design/audit rationale behind Phases 2–7 — the full data-leakage taxonomy, the internal-vs-genuine-external validation ladder, comparator design, single-run vs multi-seed variance, test-set sizing, and the CLAIM 2024 / TRIPOD+AI / STARD-AI reporting map — is in ${CLAUDE_SKILL_DIR}/references/validation_design.md (load on demand). The patient-disjointness verdict itself is proven by scripts/check_split_leakage.py (Phase 2), not from that prose.

Read the full file on GitHub · 173 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. 7d ago First seen · 173 lines · 149 tokens per session scan A be75cfcf232c

Subscribe to this mod's changes

model-validation is a skill published in the GitHub repository Aperivue/medsci-skills (283 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 2,674 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 2026-08-30.