model-sourcing

model-sourcing is a skill for Claude Code from Aperivue/medsci-skills. It costs 169 tokens per session (2,182 once invoked), scanned A, original, MIT.

A verification record for the exact third-party machine-learning model used in a study, including its repository, version, checkpoint, licence, source file, and training background. A checkpoint is a saved set of model weights.

In plain words
What is it for?
Use it to check model provenance, licensing, intended use, pretrained-weight history, and possible overlap between the model's development data and your evaluation data.
Why use it?
It helps prevent evaluation results from looking like independent validation when the model was developed or tuned on related data. It also separates the model's original task from the study's task.

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 model provenance, licensing, intended use, pretrained-weight history, and possible overlap between the model's development data and your evaluation data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aperivue/medsci-skills/model-sourcing
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-sourcing
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-sourcing

README.md
[![agentmods](https://agentmods.dev/badge/skills/aperivue/medsci-skills/model-sourcing/github.svg)](https://agentmods.dev/skills/aperivue/medsci-skills/model-sourcing)
Your own site
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/model-sourcing"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/model-sourcing/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 model-sourcing

Your own site · 80×15
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/model-sourcing"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/model-sourcing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,182 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 $0.00169 $0.02182
Opus 5 $0.00084 $0.01091
Sonnet 5 $0.00034 $0.00436
Haiku 4.5 $0.00017 $0.00218

Measured 10d ago against content hash b2e27cafc578, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

model-sourcing 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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check_model_provenance_challenge/verify.sh, scripts/check_model_provenance.py, tests/test_model_provenance.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-sourcing/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model-Sourcing Skill

Purpose

/architecture-zoo answers a literature question — which family of model suits this task. That question has a stable answer. The next question does not: which concrete artifact do I run? A repository, a revision, a checkpoint. That is a provenance question, and the two facts a careful researcher usually checks are the two that cannot answer it.

The licence tells you whether you may use it. The citation count tells you whether others did. Neither tells you whether the number you are about to report means what you will say it means.

The failure this skill exists for is the quietest one in the lane. A method developed and tuned against a benchmark family gets evaluated by the next person on that same family, and the resulting figure reads like validation while sitting much closer to a training-set score. Nothing in the repository says so. The licence is clean, the paper is peer-reviewed and highly cited, the task matches, the code runs on your GPU. The conflict lives in the relationship between two facts that are documented in different places — what the model was developed on, and what you are about to evaluate it on — and it becomes visible only when they are written down side by side.

Writing them down side by side is what the dossier is for.

When to use

  • You have a concrete candidate (a GitHub repo, a Hugging Face checkpoint, a paper's released weights) and are about to build a study on it.
  • You are writing the Methods paragraph that says which model you used, and it has to survive a reviewer asking what it was trained on.
  • You inherited a pipeline whose model came from somewhere nobody recorded.

When NOT to use

  • Choosing an architecture family/architecture-zoo (archetypes and the task-to-architecture logic; deliberately not a live leaderboard).
  • Building the training repo → /model-scaffold. Designing the validation study → /model-validation. Computing held-out metrics → /model-evaluation.
  • Documenting a model you built → /model-card (Model Card + Datasheet).
  • Auditing your own dataset before modelling → /profile-imaging.
  • Evaluating an LLM/multimodal system on a clinical task → /mllm-eval (which owns pretraining-contamination of public benchmarks for that setting).

Read the full file on GitHub · 167 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. 10d ago First seen · 167 lines · 169 tokens per session scan A b2e27cafc578

Subscribe to this mod's changes

model-sourcing is a skill published in the GitHub repository Aperivue/medsci-skills (291 stars, last pushed 3d ago), licensed MIT. It adds 169 tokens to every session and 2,182 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

torch-geometric

PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torchgeometric, not for general NetworkX analytics or non-graph PyTorch models.

K-Dense-AI/scientific-agent-skills · 71 tokens

bids

Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars…

K-Dense-AI/scientific-agent-skills · 80 tokens

bulk-rnaseq

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…

K-Dense-AI/scientific-agent-skills · 218 tokens

aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…

K-Dense-AI/scientific-agent-skills · 74 tokens

esm

Use when working directly with the esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

K-Dense-AI/scientific-agent-skills · 39 tokens

geniml

Use Geniml for audited local genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.

K-Dense-AI/scientific-agent-skills · 43 tokens