40,000 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.
xu-xiang/everything-claude-code-zh
Plugin Claude Code
Bundles 17 skills, 26 commands, 13 agents · 1,980 tokens together
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use.
glittercowboy/taches-cc-resources
Plugin Claude Code
Bundles 12 skills, 19 commands, 3 agents · 989 tokens together
Curated Claude Code skills and commands for prompt engineering, MCP servers, subagents, hooks, and productivity workflows.
severity1/claude-code-prompt-improver
Plugin Claude Code
Bundles 1 skill, 3 hooks · 42 tokens together
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability…
Skill Claude CodeCodex
Refine, create, or retire your own skills based on recurring patterns from past sessions.
Skill Claude CodeCodex
Use this skill whenever a user wants to run, install, configure, or understand open-ralph-wiggum (ralph). This skill can be used by any AI assistant or IDE agent (GitHub Copilot, Claude Code, Cursor, Windsurf, etc.). Triggers on: "ralph", "ralph wiggum", "agentic loop", "iterative AI loop", "autonomous coding loop"…
Skill Claude CodeCodex
Scaffold a NEW file-defined OpenCode agent for the Open Mercato Agent Orchestrator (the agent assembled from an agents/ / directory of Markdown files and run on the OpenCode runtime / Playground). Creates AGENT.md + OUTCOME.md (+ optional skills/, sub-agents/, tools/), enforces the propose-only hard gates, runs yarn…
Skill Claude Code
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
Plugin Claude Code
Bundles 1 skill · 220 tokens together
Troubleshooter + machine-readable corpus for reinforcement-learning training, evaluation, and experiment design on LLM agents (single/multi-agent, multi-turn, tool-augmented). Distilled from the AgentsMeetRL awesome list (378 projects).
Skill Claude Code
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
Skill Claude CodeCodex needs its repo
Collaborate with other agents in OpenOPC company mode via the opc-collab CLI — send messages, request user input, delegate work, read the manager board, respond in meetings, propose task adjustments.
TencentEdgeOne/edgeone-makers-tools
Cursor rule Cursor needs its repo
This skill guides building AI agent endpoints on EdgeOne Makers — five framework routes (DeepAgents, LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK), platform-injected context.store / context.tools / context.sandbox, conversationid dual-channel routing, SSE streaming, and agents/ vs cloud-functions/…
Plugin Claude Code
Bundles 1 skill · 133 tokens together
State what an agent must accomplish and which requirements it must satisfy. Reuse and combine Markdown contracts.
Skill Claude CodeCodex
Use this skill whenever an Agent needs to query, find, install, deploy, update, tag, adopt, diagnose, or safely remove Skills Hub content, including natural-language requests to manage Skills for Codex, Claude Code, Cursor, or another Agent. Always use the Skills Hub CLI workflow instead of editing Skill directories…
Cursor rule Cursor
Always-loaded project anchor. Read this first. Contains project identity, non-negotiables, commands, and pointer to ROUTER.md for full context.
Skill Codex
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up dependencies, download WeaveBench assets, prepare the 120G VM, configure Qwen/Anthropic-compatible APIs, run smoke tests, launch full or subset evaluations, inspect logs, or summarize scores for…
Skill Claude CodeCodex
Authoring guide for Halo digital humans (automation apps). Read before calling createautomationapp or updateautomationapp.
Skill Claude CodeCodex
Bring up, standardise or debug a GPU-backed ToolUniverse remote tool in src/tooluniverse/remote/ / — the provider.toml manifest, the resident model worker, wrapping a third-party optimization kit, and reading what tu remote setup refuses. Use when adding a self-hosted model provider, converting one from per-request…
MCP server Claude CodeCodexCursor +2
MCP server "agent-kit" as configured in sendaifun/solana-agent-kit. Runs /absolute/path/to/build/index.js with node. Needs 3 environment variables to run.
stanford-iris-lab/meta-harness
Skill Claude Code
Run one iteration of AgentHarness evolution for Terminal-Bench 2.
Agent Claude Code
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…
tjboudreaux/cc-thinking-skills
Plugin Claude Code
Bundles 28 skills · 1,028 tokens together
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools.
Plugin Claude Code
Bundles 31 skills, 1 hook · 1,529 tokens together
Make AI coding agents follow a repeatable engineering workflow with memory, verification, skills, and multi-agent setup.
Skill Claude CodeCodex
Use when the user explicitly wants to create, edit, validate, sync, or troubleshoot n8n workflows, asks about n8n nodes or automation, or wants to use n8n-as-code in the current context root.
universal-tool-calling-protocol/code-mode
Skill Claude CodeCodex
Call external APIs, MCP servers, and CLI tools by writing TypeScript code that runs in a sandbox — without MCP. Use when the user wants the agent to use a tool/API/integration (e.g. "search Open Library", "read my Notion", "call this REST API") in an environment that has a shell but no MCP config and no settable…
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: