Coding agents & developer tools
Claude Code, Codex & Cursor extensions
8,960 agents · most starred first
Claude Code, Codex & Cursor extensions, page 41 of 90
See your Claude limits coming, and which sessions need you: usage with pace, the state of every session and the session's context, right inside the Claude desktop app on macOS. Free, open source, notarized.
Native macOS menu bar app that notifies you when AI coding agents (Claude Code) finish tasks, need permissions, or ask questions. Privacy-first, zero dependencies, localhost-only.
Claude Code skill for building with the Claude Managed Agents API — event loops, production patterns, MCP auth, debugging, and more.
Multi-agent orchestration plugin for Claude Code — 11 AI agents with intelligent model routing, 3-layer codebase indexing, and auto skill injection
Production-ready AI dev workflow scaffold with 59 skills, 33 agents, hooks, and rules for Claude Code, Codex, Gemini CLI, Copilot CLI, Qwen Code, and OpenCode.
Self-correcting AI loops for OpenCode - feed the same prompt until completion
Neovim plugin for AI-assisted coding: Claude CLI & Codex CLI backends with MCP-powered editor control
An extension bringing the OpenAI, Anthropic and Gemini APIs to your fingertips inside of Visual Studio Code
CLI tool to discover, install, and manage Claude Code skills from a curated community registry
SvelteKit and Svelte 5 done right. Runes, load functions, form actions, SSR patterns.
Best Cursor Rules is a curated collection of 33 high-quality Cursor AI rules that actually work. Includes a Setup Wizard that analyzes your project and generates customized rules automatically.
a collection of productivity skills for claude code.
Agent Skill: Self-improving learning system - detects friction, proposes improvements | Claude Code compatible
Reusable skills and dependency graph system for Hermes Agent — bitwarden secrets, email composition, autoresearch loop
Stop Claude Code from breaking your projects. Ready-to-use CLAUDE.md templates, subagents, hooks, and anti-regression configs.
Enhance your Google AI Studio experience with a better sidebar, folders, tags, favorites, and library scanning.
Claudeculator
在 TrafficMonitor 任务栏显示 Claude 订阅用量(5h/7d),请求前校验 Cloudflare 出口节点(colo/loc),不对就跳过并通知。C++/WinHTTP,单 DLL。
CLI, MCP server, and Skill for safe local Codex session audit, cleanup, restore, and verification.
A desktop app for Claude Code with multi-tab sessions, agent observability, and usage analytics.
12 production-tested skills for Claude Code CLI — SEO/GEO, WordPress, content creation, marketing, ebook publishing, VPS management, AI agents, context engineering, token optimization, memory persistence, distribution. By TheGEOLab.net
Stop your AI agent from generating Tailwind CSS v3 code. 20+ rules for v4 syntax, CSS-first config.
Agent asset management tool across projects and coding tools.
🚨 The leaked source code of Anthropic's Claude Code. Explore 512k+ lines of TypeScript revealing multi-agent swarms, MCP integrations, Bun runtime, and a React/Ink terminal UI.
gemini cli hooks - adding voice on each hook
Multi-platform AI assistant skills and workflows. Serious engineering. Also fun.
Multi-agent social simulation as a Claude Code skill. Zero dependencies — predict anything with /crowdcast simulate.
Claude Code skill: turn raw requirements, engineering PRDs (incl. Feishu docs), or competitor analysis into a concise, coding-agent-ready PRD for vibe coding
Autonomous delivery orchestrator for Claude Code — hand it a goal and a numbered Definition of Done, it runs the whole job to completion
Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.
Claude Code plugin that makes coding agents measurably cheaper over time: collect token costs, distill candidate rules, benchmark them on a frozen golden suite, and keep only rules that earn their context rent.
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate READMEs and make a repo open-source-ready).
An unofficial orchestrator skill for Matt Pocock's agent skills. Routes you to the right skill based on your situation.
For AI enthusiasts who try every new tool and watch their skills fragment. One source of truth for AI agent skills (SKILL.md) + cross-tool sync toolkit: MCP server, shared instructions, and one-command wiring for Claude Code, Codex, Gemini, Kimi, Cursor, Kilocode, OpenCode.
Open-source meta-harness for Claude Code, OpenAI Codex, and Gemini CLI coding agents
Project-local agent harness skill for traceable AI workflows
The tool for interactively reviewing an HTML plan for Claude Code
AI reasoning skills distilled from 4,665 real Claude Fable 5 chain-of-thought traces. Mathematically tuned. Grade A (100%) emulation accuracy against MiniMax M3.
A Claude Code meta-skill that learns your writing voice from your own samples and edits, then compiles it into a reusable voice skill.
Agentic Skill for Coding with FileMaker Pro
Compile any Claude Agent Skill into a multi-agent Workflow — a meta-workflow that recovers the parallelism hidden in a skill's prose and emits a fan-out · pipeline · adversarially-verified Workflow.
A warn-only runtime layer for Claude Code agents. Keeps feature state, scope and handoffs on disk so they survive compaction, and requires an evidence path before a done claim. Never blocks a tool call. Companion to superpowers; bash + git, no MCP.
Personal Claude Code configuration versioned inside ~/.claude — agents, skills, hooks, settings, and statusline (reference, not a starter template)
A live, local dashboard to browse, search, resume & manage every Claude Code session on your machine — full conversation transcripts, an artifacts view, and usage stats. Pure Python stdlib, no dependencies.
The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/grow) + adversarial eval.
A visual editor for building ccstatusline configurations — drag, drop, pr eview, ship. 一个可视化编辑器,用来搭建 ccstatusline 状态栏配置——拖拽、预览、一键生成。
Queue research questions all day. Wake up to answers. Puts your idle Claude Code quota to work while you sleep.
Open-source physical dashboard for Codex on Stream Deck: monitor tasks, switch threads, control Effort/Fast mode, and dictate on macOS.
八荣八耻 Claude Code Skill — enforce engineering discipline: verify before assuming, align before building, reuse over redundancy. 中英双语行为约束。
Desktop pet for Claude Code on Windows — walks your taskbar, reacts to Claude sessions in real time.
Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.
Local patch + guide: make OpenAI Codex MultiAgentV2 subagent tasks work with DeepSeek and other non-OpenAI Responses providers (encrypted agent_message payload fix).
Claude Code with Hebrew, Arabic and Persian rendered correctly. Most terminals have no bidirectional text engine, so right-to-left output comes out scrambled. This runs Anthropic's AI agent in a terminal that gets it right, with a folder picker instead of commands. Windows and Linux, free and open source.
An ADE + IDE desktop workspace for multi-project, multi-agent development in the AI coding era. 面向 AI 编程时代的 ADE + IDE 桌面工作台,统一管理多项目、多 Agent 会话、Git 变更与代码开发。
A curated bundle of 38 Claude Skills for quantitative, qualitative, experimental & mixed-methods research in business, finance & social science — from framing a question to submission and replication packages (bilingual 中/EN)
Unofficial Windows desktop wrapper for DeepSeek Harness (dsh)
AI-Psychiatry is a Claude plugin that gives AI coding agents an executive-function layer to detect and control attention drift, overthinking, recursive reasoning, compulsive verification, scope drift, retry loops, deadlocks, livelocks, context waste, and failure to stop after completion.
A development pipeline your coding agent has to walk through: six phases, gates enforced outside the model, and one method wired into six tools.
🚀 SDD + ADD Starter Template — AI Coding Assistant Governance Framework. Turn your AI coding assistant into a disciplined, spec-driven development partner. This is the definitive starter template for Spec-Driven Development (SDD) + Agent-Driven Development (ADD) — production-ready governance for Claude Code
Behavior guidelines that stop your AI coding agent from overengineering, hallucinating, and breaking things
Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying the answer. Measured on Sonnet and Opus, every run published — including the ones that failed. Demote, don't delete.
Unofficial claude code api guide: Claude Code vs the Claude Developer Platform, getting a key, courses, gotchas.
Claude Code 状态栏:会话花费、上下文占用、5h/7d 限额,并区分订阅制与按量付费、预警无兜底硬停。单文件 Python,零依赖零配置。
我的 AI 编程配置,一句话装好 · My AI coding setup, installed in one message
Live instrument panel for Claude Code: context, rate limits, cost, subagents, tools, diffs and tests, plus a guard for risky commands.
A workspace inside Claude Code: task boards Claude picks up, a notebook it keeps with you, team chats — and games, books and podcasts while the agent works. Free, open-source.
A macOS menu bar app for Claude Code and Codex sessions: see which one needs you and track plan limits. Free, open source, local-only.
OpenCode 1.x and 2.x plugins that replace the built-in glob, grep and read tools: bounded output, hard search deadlines and deterministic ordering.
Curadoria em português das melhores skills pro Claude — o que instalar e por quê (Claude Code · Web · Cowork)
Reusable Claude skills (SKILL.md) with tested helper scripts, organized by category. Drop a skill into Claude.ai or Claude Code to give it a new ability.
Guard rails for Claude Code: workspace boundaries, protected branches, production targets, lost exit status, and foreground time.
Claude Code를 한국어로 자연스럽게 사용할 수 있게 해주는 플러그인
RoundTable Framework For Claude Code — A structured multi-team AI governance framework
AI-first Go development framework. Ship production CLIs that AI agents build correctly.
Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.
Validation and permission system for Claude Code
你不缺 idea, 你缺一个把 idea 想清楚的人。一场对话把想法变成可执行的软件设计 — Built for Claude Code
Smart skill router for Claude Code — auto-suggests the right skill at the right moment based on message, git state, and dev phase
AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!
Multi-agent orchestration for building production apps with Claude Code. 15 agents, 12-phase pipeline, from requirements to deployed.
Stop prompting. Start crafting. — Transforms Claude Code into 6 reactive AI agents (PO, Architect, Frontend, Backend, QA, DevOps) that collaborate to deliver clean, tested, architected React + TypeScript frontends. Hexagonal architecture, Result types, BDD tests, CI/CD — all crafted.
将 Google Gemini 网页进化成本地 IDE 的浏览器插件
Disable or adjust the width of the sidebar functionality on Claude.ai
A collection of mainly my own productivity plugins for Claude Code.
🔄 Ralph Wiggum iterative AI development loops for GitHub Copilot. Self-referential coding automation that keeps improving until done. Cross-platform Python tool.
Claude skill for building Claude skills. An interactive 9-step workflow distilled from Anthropic's complete guide — covering use cases, frontmatter, instructions, design patterns, testing, and distribution.
Package manager for AI coding assistants — manage skills, agents & MCPs across Claude Code, Codex, Copilot, and Cursor
Systematic thinking enforcement plugin for OpenClaw — task tracking, plan mode, hard gates, quality checklists, and audit logging for AI agents
AI engineering framework with quality gates, persistent memory, and multi-platform support. Works inside Claude Code, Cursor, Copilot, Codex, and Gemini.
A collection of small hooks and extensions for the Pi coding agent
A native macOS menu bar app for monitoring Claude usage limits in real-time
Switch between Claude Code accounts instantly. Per-terminal isolation, API key fallback, auto-update.
Automated governance framework for Claude Code — multi-model council, WIP lifecycle hooks, company memory, and security gates
Comprehensive skill for launching sustainable open source projects
Public skill pack for AI coding/automation/penetration-testing agents.
Make the leaked Claude Code runnable with unified local model support.