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 mxslr/mlcraftnpx agentmods add plugins/mxslr/mlcraft/marketplacegit clone --depth 1 https://github.com/mxslr/mlcraftGrade A, and why
mlcraft-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 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": "mlcraft-marketplace",
"description": "Marketplace hosting the mlcraft plugin, a professional AI/ML research-engineering workflow for AI coding assistants.",
"owner": {
"name": "Marshall Rasendria",
"email": "[email protected]"
},
"plugins": [
{
"name": "mlcraft",
"source": "./",
"version": "1.0.0",
"description": "Research-first AI/ML engineering: literature review, best-method selection per domain, rigorous training and fine-tuning, honest leakage-free evaluation, explainable deployment, and an iterative accuracy-improvement loop.",
"author": {
"name": "Marshall Rasendria",
"email": "[email protected]"
}
}
]
}
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.
- yesterday First seen · 21 lines scan A d46d3747316f
mlcraft-marketplace is a plugin published in the GitHub repository mxslr/mlcraft (8 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
yolo
Agent skills for Ultralytics YOLO and Platform: model selection, dataset annotation, training, tuning, inference, export, and deployment through the web UI, Python package, and yolo CLI.
ultralytics
Ultralytics YOLO agent skills for the full computer-vision lifecycle.
alibabacloud-agent-toolkit
Plugin marketplace listing 3 plugins: alibabacloud-core, alibabacloud-spec-ops, alibabacloud-ecs-ops.
neatcontext
Save Claude Code work as reusable, domain-aware context.
talk-to-anyone
Turn any public figure into your personal coach, living or historical. /coach researches the person across the web, pulls real transcripts when they have video anywhere on YouTube, builds a persona, and talks to you as them until you switch or end.
romek-plugins
Claude Code plugins by Roman Rozenberger.