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/CHENyiru3/AI-Skills-CollectionsWrote 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/chenyiru3/ai-skills-collections/compbio)<a href="https://agentmods.dev/plugins/chenyiru3/ai-skills-collections/compbio"><img src="https://agentmods.dev/badge/plugins/chenyiru3/ai-skills-collections/compbio/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/chenyiru3/ai-skills-collections/compbio"><img src="https://agentmods.dev/badge/plugins/chenyiru3/ai-skills-collections/compbio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
compbio 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": "compbio",
"description": "Computational biology — perturbation analysis, single-cell, spatial omics, databases, project continuity",
"source": "./skills-market/compbio",
"strict": false,
"skills": [
"./databases/ensembl",
"./databases/geo",
"./databases/human-cell-atlas",
"./databases/kegg",
"./databases/reactome",
"./expert-workflows/computational-biology-project-manager",
"./expert-workflows/computational-biology-retrospective",
"./expert-workflows/critique-bio-manuscript",
"./expert-workflows/draft-spatial-methods",
"./expert-workflows/explain-bio-dl-model",
"./multiomics/integration-tools/scribble",
"./multiomics/metabolomics/metabolomics-workbench",
"./multiomics/proteomics/uniprot",
"./multiomics/scATAC-seq/archr",
"./multiomics/scATAC-seq/signac",
"./multiomics/scRNA-seq/pydeseq2",
"./single-cell/analysis/anndata",
"./single-cell/analysis/anndatar",
"./single-cell/analysis/monocle3",
"./single-cell/analysis/pertpy",
"./single-cell/analysis/scanpy",
"./single-cell/analysis/schard",
"./single-cell/analysis/scvi-tools",
"./single-cell/analysis/seurat",
"./single-cell/integration/bbknn",
"./single-cell/integration/harmony",
"./single-cell/integration/scanorama",
"./single-cell/integration/seurat-v5",
"./single-cell/visualization/cellxgene",
"./single-cell/visualization/cellxgene-census",
"./spatial-omics/analysis/giotto",
"./spatial-omics/analysis/spatialdata",
"./spatial-omics/analysis/squidpy",
"./spatial-omics/platforms/stereo-seq",
"./spatial-omics/visualization/vitessce",
"./structural-biology/chimerax-mcp",
"./workflows/nextflow",
"./workflows/snakemake"
]
}What it installs
The manifest is a name and a version. 38 skills travel with it, and installing the plugin installs all of them — 1,681 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill computational-biology-project-manager A 47 tokens
- Skill anndatar A 46 tokens
- Skill signac A 45 tokens
- Skill computational-biology-retrospective A 80 tokens
- Skill chimerax-mcp A 61 tokens
- Skill pertpy A 40 tokens
- Skill archr A 40 tokens
- Skill monocle3 A 39 tokens
- Skill nextflow A 38 tokens
- Skill seurat A 38 tokens
- Skill seurat-v5 A 53 tokens
- Skill squidpy A 36 tokens
- Skill bbknn A 43 tokens
- Skill cellxgene A 47 tokens
- Skill giotto A 36 tokens
- Skill harmony A 31 tokens
- Skill human-cell-atlas A 44 tokens
- Skill scanorama A 34 tokens
- Skill schard A 42 tokens
- Skill snakemake A 34 tokens
- Skill spatialdata A 44 tokens
- Skill stereo-seq A 39 tokens
- Skill vitessce A 41 tokens
- Skill critique-bio-manuscript A 51 tokens
- Skill draft-spatial-methods A 49 tokens
- Skill scribble A 50 tokens
- Skill explain-bio-dl-model A 44 tokens
- Skill scvi-tools A 45 tokens
- Skill metabolomics-workbench-database A 46 tokens
- Skill reactome-database A 38 tokens
- Skill anndata A 53 tokens
- Skill ensembl-database A 47 tokens
- Skill geo-database A 43 tokens
- Skill uniprot-database A 41 tokens
- Skill cellxgene-census A 46 tokens
- Skill kegg-database A 40 tokens
- Skill pydeseq2 A 49 tokens
- Skill scanpy A 41 tokens
What ships with it
1 file beside marketplace.json#compbio 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.
- yesterday Changed · +2 lines 3445abac18b9
- 3d ago Changed · +34 lines e770b35a26db
- 8d ago Changed · +1 lines cb0270d3b4cf
- 1mo ago First seen · 9 lines scan A ad97ce58539b
compbio is a plugin published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 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 2026-10-02.
compbio compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compbioCHENyiru3/AI-Skills-Collections | Plugin | 2 | 3d ago | MIT | A | — | Claude Code |
| catalysis-scientistK-Dense-AI/scientific-agents | Plugin | 246 | 1mo ago | MIT | A | — | Claude Code |
| hyphamycelium-cmbse/mycelium-hypha | Plugin | 12 | yesterday | Apache-2.0 | A | — | Claude Code |
| r2g-skillsShenShan123/r2g-skills | Plugin | 44 | 16d ago | MIT | B | — | Claude Code |
| aremaballarin/ccplugins | Plugin | 4 | 19d ago | MIT | A | — | Claude Code |
| physical-sciencesKalarisLabs/research-agent-skills | Plugin | 133 | today | none | A | — | Claude Code |
| biorxiv-mcp-servercyanheads/biorxiv-mcp-server | Plugin | 4 | yesterday | none | A | — | Claude Code |