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.
git clone --depth 1 https://github.com/CrossRead/scholionWrote 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/crossread/scholion/agent-plugin)<a href="https://agentmods.dev/plugins/crossread/scholion/agent-plugin"><img src="https://agentmods.dev/badge/plugins/crossread/scholion/agent-plugin/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/plugins/crossread/scholion/agent-plugin"><img src="https://agentmods.dev/badge/plugins/crossread/scholion/agent-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
scholion 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 yesterday.
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": "scholion",
"version": "0.6.9",
"description": "Local second-opinion support for individuals and clinicians — genome (VCF), laboratory history, prescriptions and wearables. One person per container and per assistant conversation; the tools use the active container and cannot switch it. Findings carry their evidence level; lower-evidence findings reach the assistant as labelled hypotheses, not conclusions. The engine must be installed locally. Tool answers may reach the host's model provider. Not a medical device.",
"author": {
"name": "Scholion contributors",
"email": "[email protected]",
"url": "https://github.com/CrossRead/scholion"
},
"homepage": "https://github.com/CrossRead/scholion",
"repository": "https://github.com/CrossRead/scholion",
"license": "Apache-2.0",
"keywords": [
"health",
"genome",
"pharmacogenetics",
"laboratory",
"local-first"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 209 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed 5a5661588400
- 5d ago Changed 44c3b2373924
- 6d ago Changed 40f6ed122deb
- 10d ago Changed 1979d5c10ace
- 11d ago First seen · 21 lines scan A c7d2773fe8b3
scholion is a plugin published in the GitHub repository CrossRead/scholion (4 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-10-05.
Other plugins, from other repositories
omics-skills
Bioinformatics, literature discovery, scientific writing, and data visualization agents and skills for Claude Code and Cowork.
gnomad-genetics-mcp-server
Ancestry allele frequencies, LoF constraint, variant lists, and coverage from gnomAD, joined with ClinVar clinical significance via MCP. STDIO or Streamable HTTP.
biodiscovery-skills
Thinking tools for AI agents making discoveries in the life sciences. A research-director operating stance plus 90 routed discovery operators.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.