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.
/plugin marketplace add Aperivue/medsci-skillsnpx agentmods add plugins/aperivue/medsci-skills/medsci-modelinggit clone --depth 1 https://github.com/Aperivue/medsci-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/plugins/aperivue/medsci-skills/medsci-modeling)<a href="https://agentmods.dev/plugins/aperivue/medsci-skills/medsci-modeling"><img src="https://agentmods.dev/badge/plugins/aperivue/medsci-skills/medsci-modeling.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
medsci-modeling 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 2d 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.
What it actually says
{
"name": "medsci-modeling",
"description": "Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.",
"source": "./",
"strict": false,
"skills": [
"./skills/architecture-zoo",
"./skills/explainability",
"./skills/mllm-eval",
"./skills/model-card",
"./skills/model-evaluation",
"./skills/model-scaffold",
"./skills/model-sourcing",
"./skills/model-validation",
"./skills/preprocess-imaging",
"./skills/profile-imaging",
"./skills/radiomics-ml",
"./skills/uncertainty-imaging"
]
}What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 2,082 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill model-scaffold A 191 tokens
- Skill model-validation A 149 tokens
- Skill profile-imaging A 190 tokens
- Skill model-evaluation A 206 tokens
- Skill model-sourcing A 169 tokens
- Skill preprocess-imaging A 133 tokens
- Skill radiomics-ml A 223 tokens
- Skill uncertainty-imaging A 165 tokens
- Skill architecture-zoo A 233 tokens
- Skill explainability A 150 tokens
- Skill mllm-eval A 140 tokens
- Skill model-card A 133 tokens
What ships with it
1 file beside marketplace.json#medsci-modeling 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.
- 2d ago First seen · 20 lines scan A e666f18173fd
medsci-modeling is a plugin published in the GitHub repository Aperivue/medsci-skills (283 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
mechanistic-interpretability
Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.
geoai-skills
GeoAI-powered skills for Claude Code: inspect geospatial files, download satellite imagery, search STAC catalogs, fetch Overture Maps data, process rasters, run AI object detection, and search session logs.
sciagent-skills
Life sciences computational skills for scientific AI agents — 197 skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing.
tml
tuneml — a read-first advisor for training and evaluating neural networks well: the scientific method for tuning, and the speed↔quality frontier, in one place. Prices every candidate change in time-to-target-quality rather than throughput, grades the evidence behind it, and names what it would silently break. Five…
r-tidy-modeling
Expert agents for R data science and biostatistics using tidyverse and tidymodels.
tidymodels-developers
Development tools and guides for tidymodels ecosystem packages including yardstick metrics, recipes steps, dials parameters, and parsnip models.