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 yuanruichen/MetForgenpx agentmods add plugins/yuanruichen/metforge/marketplacegit clone --depth 1 https://github.com/yuanruichen/MetForgeGrade A, and why
metforge marketplace 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": "metforge",
"owner": {
"name": "Yuanrui Chen",
"url": "https://github.com/yuanruichen"
},
"description": "Atmospheric science skills for Claude Code.",
"version": "2026.8.10",
"plugins": [
{
"name": "metforge",
"displayName": "MetForge",
"source": {
"source": "github",
"repo": "yuanruichen/MetForge"
},
"description": "Atmospheric science skills for data acquisition, scientific analysis, publication-ready figures, and model diagnostics.",
"version": "2026.8.10",
"author": {
"name": "Yuanrui Chen",
"url": "https://github.com/yuanruichen"
},
"homepage": "https://github.com/yuanruichen/MetForge",
"repository": "https://github.com/yuanruichen/MetForge",
"license": "MIT",
"category": "science",
"tags": [
"atmospheric-science",
"climate-science",
"meteorology",
"scientific-computing",
"ai-for-science"
]
}
]
}
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 · 37 lines scan A 1e29d8e8005b
metforge marketplace is a plugin published in the GitHub repository yuanruichen/MetForge (4 stars, last pushed 20d 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
ai-science-toolkit
Claude Code skills and domain-expert reviewer subagents for AI-assisted scientific computing.
antimicrobial-resistance-scientist
Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…
protein-design-skills marketplace
Claude Code skills for computational protein design - backbone generation, sequence design, structure prediction, and experimental validation.
msds-chain
Chemical safety intelligence for AI-assisted experiment design — 23 tools for compatibility, hazard, PPE, storage, waste disposal, mixing order, exposure limits, transport classification, regulatory compliance (23 lists, 8 jurisdictions), SDS version diff, PDF upload, chemical substitution, first aid, GHS labels…
ar
ar — autoresearch: a skill-only autonomous experiment loop. Propose → measure → keep winners → repeat, against any numeric objective, with noise-floor gating so nothing is banked on noise. Five skills: /ar:start opens a run (dedicated branch + baseline noise floor), /ar:resume advances it, /ar:status prints read-only…
biorxiv-mcp-server
Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP. STDIO or Streamable HTTP.