Plugins

A plugin is a ready-made bundle for an agent: a set of commands, skills and settings installed in one step. This section collects plugins for Claude Code and compatible agents, with a description of what is inside, an install command and a risk level.

Match with Foxx AI

Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.

Found: 82

Shared semantic memory for agents: conversations are saved as markdown and recalled by search across Claude Code, Codex and other agents

Medium risk2.7KRepository stars

Softaworks Agent Toolkit

Softaworks Agent Skills

A marketplace of skills, subagents and commands for coding agents: development, documentation, planning and workplace communication

Medium risk2.5KRepository stars

A tool that builds tested skills from a real workflow and governs their lifecycle through your own marketplace

Medium risk2.4KRepository stars

A skill plus hooks that keep a coding agent on task and cut speculative defenses, unread checksums and scope creep

Medium risk2.4KRepository stars

A Claude Code plugin with four working-method skills: classify the task, act in steps, verify the result and generate domain adapters

Low risk2.3KRepository stars

A set of business, marketing, UX and code skills based on well-known books, plus step-by-step metaskill journeys

Low risk2.3KRepository stars

A plugin set for enterprise architecture: the agent runs strategy, requirements, risk, reviews and compliance through commands in Claude Code and others

Low risk2.3KRepository stars

A plugin marketplace for agents: reflexion, code and PR review, git, TDD, DDD, specs and subagent-driven development

Medium risk1.7KRepository stars

A set of agent skills organized as a company: 16 departments and well over a hundred specializations, each installed as its own plugin

Medium risk1.7KRepository stars

A layer over coding agents that assembles a temporary specialist team per task inside Claude Code, Codex, Cursor and Gemini

Medium risk1.6KRepository stars

A guard for coding agents: blocks destructive Git and file system commands and attempts to read sensitive files before they run

Low risk1.6KRepository stars

daymade Skills Marketplace

Claude Code Skills Marketplace

A plugin marketplace for Claude Code and Codex: documents, audio, GitHub, session history, finance, macOS and a hardened skill-creator

High risk1.4KRepository stars

A universal workflow plugin for Claude Code: 7 agents, 26 commands, 14 skills and 14 hooks for any project

High risk1.4KRepository stars

A large library of professional Markdown skills, from PRDs and postmortems to decoding a lease, installable in Claude Code, Cursor and Codex

Low risk1.4KRepository stars

Skills for coding agents that analyze KiCad schematics and boards, catch design mistakes and prepare boards for fabrication

Medium risk1.3KRepository stars

A method pack that makes coding agents architecture-aware: baseline first, evidence checks, drift control and safety across long tasks

Medium risk1.3KRepository stars

A set of Claude Code and Codex skills and subagents for professional .NET development: C#, Akka.NET, Aspire, EF Core, testing and performance

Low risk1.2KRepository stars

A set of skills, agents and commands for iOS, iPadOS, watchOS and tvOS development: Swift 6, SwiftUI, Liquid Glass and Apple Intelligence

Medium risk1.2KRepository stars

Claude Codex Settings

claude-codex-settings

A marketplace of dozens of plugins for Claude Code, Codex, Cursor and Gemini: skills, commands, hooks, subagents and configs for many tasks

Medium risk1.2KRepository stars

A plugin with output styles for coding agents: short, human answers instead of verbose walls of text

Low risk1.1KRepository stars

A Claude Code and Codex plugin that builds, validates and signs Apple Shortcuts from a plain-language description

Medium risk1.1KRepository stars

A skill set for math modeling contests: problem parsing, method selection, Python and MATLAB code, and paper writing

Medium risk1.1KRepository stars

Skills that turn a coding agent's output into plain language: honest reports, straight verdicts, followable steps

Medium risk1KRepository stars

An operating layer for Claude Code and Codex: one /do entry point, project memory across sessions, safety hooks, cost telemetry and parallel agents

High risk923Repository stars