14,252 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.
Plugin Claude Code
Bundles 1 skill, 1 hook · 55 tokens together
A cute terminal pet that refines your rough prompts using your current session's context, memory, and model. No API key.
Plugin Claude Code
Bundles 4 skills, 5 hooks · 783 tokens together
Self-evolving prompt meta-compiler for the Fable 5 / Opus 4.8 era (Mythos-class aware) with xhigh/max effort, adaptive thinking, task budgets, dual-layer memory (ROSETTA.md + auto-memory), AND skill-level meta-refinement. v4.4: FABLE-5-ERA RETARGET — complexity map gains a model dimension (Opus 4.8 workhorse default…
Plugin Claude Code
Bundles 2 commands, 1 hook · 22 tokens together
Rewrites your prompt before the model sees it, on your Claude subscription - no API key. Shapes nothing else about the answer.
NewJerseyStyle/plugin-logic-llm
Plugin Claude Code
Bundles 4 skills, 1 command, 2 hooks, 6 MCP servers · 0 tokens together
Logic-LLM integration for Claude Code - enables symbolic reasoning with Prolog, Clingo/ASP solvers. Converts documents to logic programs for complex reasoning, legal document processing, and multi-turn inference.
assist-software/claude-code-repository
Plugin Claude Code
Bundles 1 skill, 4 commands, 5 agents · 448 tokens together
Audit, author, fix, and initialise LLM prompts in any codebase against a shared best-practices rubric. Architecture-aware: understands where prompts belong in layered/clean architectures. Creates a persistent docs/prompt-engineering/ workspace per project.
Skill Codex
Provides the official Protobuf specifications and gRPC/REST service definitions for the Gemini API (Google Generative Language API v1beta). Use this skill when you need precise schema definitions for requests/responses (e.g., GenerateContent, Tools, FunctionCalling), multimodal content structures (Content, Part)…
MCP server Claude CodeCodexCursor +2
MCP server "knowledge" as configured in caitao-ct/knowledge-base. Launched with bash -lc cd /path/to/knowledge && ./bin/knowledge-mcp --transport stdio. Needs 5 environment variables to run.
Cursor rule Cursor
When we are creating prompts that will be used by an LLM for agents.
MCP server Claude CodeCodexCursor +2
MCP server "discord-archive" as configured in wdwdev/discord-archive. Runs locally from the rag Python package.
Skill Claude CodeCodex needs its repo
Develop/iterate on the MidMem middleware core (this repo's packages/core — the shared "LLM Wiki" knowledge layer). Use when adding or changing MidMem capability — retrieval lanes, tiers/lifecycle, work-memory events, concept routing, claims, grounding, the MCP/CLI/hook surfaces, or its tests. Encodes the…
responsible-genai-hackweek/nicer-nisar
Skill Claude CodeCodex
Fit, evaluate, and freeze a Mores Creek snow-depth-change model — matched InSAR/LiDAR pair selection, target aggregation, the holdout scheme that is actually honest, the feature ablation, the challenger rule, and what must go in the model card before an id is pinned. Use when adding a training pair, refitting after a…
MCP server Claude CodeCodexCursor +2
MCP server "lightrag" as configured in Ricardo-Kaminski/local-rag. Launched with C:\Users\ricar\miniconda3\envs\local-rag\python.exe C:\workspace\pessoal\local-r.
Skill Claude CodeCodex
Use TypeCast to turn LLM output into validated, typed JVM values. Reach for it whenever code calls an LLM and then parses/validates the response by hand: extraction of case classes or Java records from text, classification/routing via sealed traits, constraint enforcement with retry, streaming partial JSON into a UI…
Skill Claude Code
Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any…
Cursor rule Cursor
GraphRAG pipeline domain knowledge — entity extraction, community detection, summarisation, embedding.
0xCyberBerserker/token-rat-esp
Skill Codex
Aggressive token and output minimization for coding agents. Use when the user wants concise technical Spanish, minimal useful output, small patches, and strict scope control.
may215/antigravity-awesome-group-skills
Skill Claude CodeCodex
Group skill: AI/LLM application — provider selection, app patterns, RAG, agents, prompts, evaluation, safety, and monitoring.
Skill Codex
Build high-quality benchmark items, embedded scoring contracts, review examples, rubrics, evaluators, and release protocols for model and agent evaluation. Use when prompts mention benchmark construction, item writing, rubric design, score-boundary design, checker design, review examples, benchmark health…
Skill Claude CodeCodex
Complete reference for the Portkey AI Gateway Python SDK with unified API access to 200+ LLMs, automatic fallbacks, caching, and full observability. Use when building Python applications that need LLM integration with production-grade reliability.
dgallitelli/claude-code-skill-for-sagemaker-ai
Skill Claude Code
Comprehensive SOP for Amazon SageMaker AI — SDK v3 code generation, serverless model customization (SFT, DPO, RLVR, RLAIF), LLM inference endpoints, model training (classical ML + LLM fine-tuning), HyperPod clusters (training + inference), Model Monitor, and AutoML with AutoGluon. Generates correct, working code every…
Plugin Claude Code
Bundles 9 skills · 1,350 tokens together
Oxy platform skills for coding agents: custom apps and Oxy Functions, semantic models, agents, automations, Airway pipelines, evals, and the oxyc CLI.
Skill Claude CodeCodex
Turn video into LLM-ready data with the Cloudglue JS SDK — upload, describe, extract, search, and chat over video collections using the @cloudglue/cloudglue-js package.
Skill Claude CodeCodex
Reasoning-guided pipeline planner that generates standard DataFlow-KG pipeline code for knowledge-graph extraction and KG-based QA generation.
Skill Claude CodeCodex
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
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: