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 jvogan/proteusnpx agentmods add plugins/jvogan/proteus/marketplacegit clone --depth 1 https://github.com/jvogan/proteusGrade A, and why
proteus 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": "proteus",
"owner": {
"name": "Jacob Vogan"
},
"metadata": {
"version": "0.1.0",
"description": "Public-safe structural biology automation skills."
},
"plugins": [
{
"name": "proteus",
"displayName": "Proteus",
"source": "./",
"description": "Run structural biology automation workflows.",
"category": "life-sciences",
"tags": ["structural-biology", "pymol", "chimerax"],
"strict": false,
"skills": ["./skills/proteus"]
}
]
}
What ships with it
1 file beside marketplace.json 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 · 23 lines scan A 8dd5fd9406a0
proteus is a plugin published in the GitHub repository jvogan/proteus (10 stars, last pushed 1mo 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 2026-08-31.
Other plugins, from other repositories
motif-for-claude-science
Motif creates a portable molecular-biology workbench with alignment, Sanger review, cloning design, typed results, and recovery workflows.
ClawBio
Bioinformatics-native AI agent skill library — pharmacogenomics, ancestry, scRNA-seq, metagenomics, variant annotation, genome comparison, and more. 24 skills with deterministic Python execution, reproducibility bundles, and local-first privacy.
asb-skill-collections
Curated, evidence-grounded scientific-agent skill and tool collections from the AgenticScienceBuilder pipeline.
SciAgent-Skills
Plugin marketplace listing 1 plugin: sciagent-skills.
SciAgent-Skills
Life sciences computational skills for scientific AI agents — 197 skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing.
omics-skills
Bioinformatics, literature discovery, scientific writing, and data visualization agents and skills for Claude Code and Cowork.