Browse the library

Persistent local memory for Claude Code, Cursor and Codex over MCP or CLI that stores typed, sourced facts and retires old ones when they change.

A universal package manager for AI coding tools, enabling discovery and installation of prompts, rules, skills, and agents across various AI platforms.

Enables AI coding agents to learn and improve over time by remembering past successes and failures from their trajectories.

Sets up a multi-agent AI coding factory in Claude Code, enabling an AI PM to orchestrate various writer agents and automate merging to main.

This skill enables asynchronous Pi subagents and agent fleet orchestration, allowing parallel coding with nested delegation, background work, and supervision in herdr.

This plugin helps Claude Code and Codex agents remember decisions, rules, and past approaches across sessions by saving them to a JEVMEM.md file in your repository.

This plugin helps AI coding agents like Claude Code and Codex produce more focused output by applying an "attention control" output style for users with ADHD.

A local-first MCP virtual pet that persists across sessions and clients, gives personality-driven in-context feedback on your work, and levels up over time.

claude-code-mods

hamzafer

A collection of Claude Code plugins offering live feedback, context visualization, and monitoring tools to enhance the agent's coding environment.

A set of Claude Code skills that provides a complete Agent Development Life Cycle for building, deploying, testing, and optimizing Agentforce agents using Agent Script DSL.

A lightweight loop harness for Codex, Claude Code and Antigravity where the agent must leave real evidence artifacts for each piece of work before claiming it is done.

An open-source dashboard that provides real-time monitoring, cost tracking, and visibility into multiple Claude Code sessions and sub-agents.

A Claude Code skill that enables any Claude model to exhibit Fable 5-grade work discipline through plan-gating, self-verification, and sub-agent routing mechanisms.

Runs Claude Code as a pipeline of specialist agents for brief, architecture, build, review and security, with a second model checking each stage and you approving key decisions.

A Claude Code plugin that hides large tool results the judge model deems irrelevant behind short stubs, restorable on demand, to save context tokens.

A comprehensive collection of over 165 specialized AI subagents for Claude Code, designed to cover the entire software development lifecycle with domain-specific expertise.

A local plugin that opens a browser UI when the agent finishes a plan so you can strike, replace, insert or comment, then approve or send structured feedback back.

An MCP server that allows defining and running task-specific AI sub-agents from Markdown files across any MCP-compatible coding tool.

A marketplace and collection of 28 plugins and MCP servers for Claude Code, offering tools for TDD, multi-agent orchestration, and iterative refinement.

A Claude Code sub-agent and custom commands implementing the RIPER-5 workflow (Research, Innovate, Plan, Execute, Review) for structured development.

A curated collection of tools and resources for Cursor AI code editor, including agent teams, advanced skills, cost analytics, and session diagnostics.

A set of Agent Skills for orchestrating sub-agents written in Markdown, allowing tasks to be routed to different AI coding backends like Claude Code or Cursor.

A collection of 140+ skills, subagents, saved workflows and rules for Claude Code and Codex, installable as a plugin, including multi-reviewer adversarial diff review.

A CLI and catalog for installing production-ready agent profiles, skills, and configurations across various AI coding agents like Claude Code and Cursor.