13,728 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
H-Ali13381/recursive-agent-improvement
Skill Claude CodeCodex
Use when an agent repeatedly fails at a narrow measurable subtask, the user wants a trainable specialist tool instead of more prompting, or the task needs an evaluator, reranker, classifier, detector, verifier, or small PyTorch model exposed to an agent.
Agent Claude Code
ML engineering specialist sub-agent. Designs and implements inference pipelines, provider selection, quantization strategies, and hardware abstraction for ONNX models. Benchmark-driven — measures before optimizing.
Plugin Claude Code
A guided data-science lifecycle for Claude Code, with leakage and honesty checks built into every stage.
Plugin Claude Code
Bundles 15 skills · 1,409 tokens together
Skills for machine learning workflows: monitoring training runs, debugging models, and managing experiments.
Codeblockz/langchain-community-plugin
Plugin Claude Code
Bundles 3 skills, 5 commands, 2 agents, 1 MCP server · 334 tokens together
Unofficial Claude Code plugin for LangChain and LangGraph. Agents, RAG pipelines, and LCEL chains with best practices.
Liu-MingH/Scientific-research-SKILL
Skill Claude CodeCodex
Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).
Skill Claude CodeCodex
Convert any rough, casual, or unstructured human prompt into a clean, professional, well-architected prompt. Use this whenever a user pastes a messy instruction, a brain-dump, a bullet list, or a vague request and wants it rewritten as a structured prompt — for an AI agent, a coding assistant, a writing task, or a…
XingjianTao/Cursor-Rules-for-PyTorch-DeepLearning-Beginner
Cursor rule Cursor
A Chinese-language set of best practices for PyTorch, a Python framework used to build and train machine-learning models. It describes suggested folders for data, models, source code, experiments, tests, scripts, and configuration files.
Cursor rule Cursor
Use for RAG app design, document copilots, vector-search chatbots, ingestion pipelines, source-grounded QA, retrieval evaluation, citations, OCR, reranking, GraphRAG, agentic RAG, multimodal RAG, structured-data RAG, AWS/Azure/local deployment, or production RAG architecture.
Skill Claude CodeCodex
Listen in with a human in the field and turn their direct frequency-readings into GOLD — the strongest label the body's freq-sense learns from. A human catches the nuanced fear a frontier model slips past, so when they name a response as clear or fear-caught AND name WHERE the fear sat, that reading is gold and must…
MCP server Claude CodeCodexCursor +2
MCP server "dify-mcp-server" as configured in teddylee777/dify-mcp-server. Runs locally from the dify-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP server that proxies image analysis to OpenRouter vision models. Runs locally from the @forloopcodes/visionmcp npm package.
wang-junjian/ragflow-mcp-server
MCP server Claude CodeCodexCursor +2
RAGFlow MCP Server - A Model Context Protocol server integrating with RAGFlow APIs. Runs locally from the ragflow-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
A Python library for relational learning on knowledge graphs. Runs locally from the kgraph Python package.
MCP server Claude CodeCodexCursor +2
Fast PyAirbyte - Generate data pipelines as code using PyAirbyte and AI. Runs locally from the fast-pyairbyte npm package.
MCP server Claude CodeCodexCursor +2
Pure Node.js MCP server for downloading HuggingFace models with enhanced HTTP API and smart filtering. Runs locally from the mcp-huggingfetch npm package.
MCP server Claude CodeCodexCursor +2
Universal prompt loader MCP server. Runs locally from the shinkuro Python package.
MCP server Claude CodeCodexCursor +2
A standalone backend server for the Notemd Obsidian plugin, providing AI-powered text processing and knowledge management. Runs locally from the notemd-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
MCP server "ml-lab-mcp" as configured in PushPullCommitPush/ml-mcp. Runs locally from the ml-lab-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server providing multimodal vision capabilities via OpenAI-compatible APIs. Runs locally from the vision-mcp npm package.
Skill Claude CodeCodex
This repository exposes a headless Google Colab MCP server. Use it when you need an AI agent to control a live Colab notebook through MCP without browser automation.
MCP server Claude CodeCodexCursor +2
MCP server for managing AI-friendly document collections — convert PDFs, split by chapter, index for chat projects. Runs locally from the docshelf-mcp Python package.
MCP server Claude CodeCodexCursor +2
Point it at a video, image, or PDF — get structured JSON. Runs local (Ollama, LM Studio, oMLX) or cloud (OpenRouter). CLI + MCP server for Claude Code, Cursor, and Claude Desktop. Runs locally from the vidlizer Python package.
MCP server Claude CodeCodexCursor +2
MCP server for TOON (Token-Oriented Object Notation) - Reduce LLM token usage by 50-70%. Runs locally from the toon-mcp-server npm package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: