Browse the library

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.

Lets Claude Code or Codex run or build agents for browser use, computer use, robotics and games on fast System 1 decision models like Jev, Laya and Cua-S1.

Nine skills that write tweets, threads and replies in your voice, strip AI tells, plan content and publish to X via Publora after you approve.

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.

This Claude Code plugin helps you verify agent-generated code by booting your application, driving changes against approved acceptance criteria, and providing a detailed report.

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 modular, evidence-driven Claude Code agent skill set designed for writing academic papers in CS/AI/ML fields, progressing section by section with hard gates.

Provides 90 standalone AI agent skills for commercial real estate underwriting, due diligence, financing, brokerage, legal, and closing workflows.

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.

A Claude Code plugin that enhances code quality by enforcing pre-coding questions, independent review, and proofing mechanisms, ensuring agents look beyond immediate changes.

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 plugin or portable skill that turns technical ideas into patent disclosures using specialist agents for research, ideation, drafting, review and diagrams.

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

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.

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 Claude Code skill set that generates a complete set of e-commerce product visuals, like main images and A+ content, from a single product photo.

A Claude Code plugin that tracks AI usage, lines of code generated, and time spent prompting AI, integrating with WakaTime.

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

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 skill that reviews short videos and posts before publishing across Douyin, Xiaohongshu, Bilibili and others, outputting a Pass-to-Blocker risk report with fix suggestions.

A comprehensive set of Cursor AI rules to enhance efficiency, enforce coding standards, and automate best practices across multiple languages and frameworks.