Coding agents & developer tools

Claude Code, Codex & Cursor extensions

8,960 agents · most starred first

Claude Code, Codex & Cursor extensions, page 65 of 90

claude-sage★ 4

Workflow system for Claude Code — Analyze First, Fix Later

turbo-claude★ 4

A curated, auto-updated list of CLAUDE.md rules, MCP servers, and Claude Code skills. The awesome-list companion to clauderules.net.

Bleu-Plugin★ 4

Bleu - Claude Code plugin for living blueprints. Turns ideas into a file-backed markdown wiki (vision, architecture, ADRs, action points) that survives /clear and hands off to GSD or Superpowers.

claude-code-remote-pilot★ 4
claude-conversations★ 4

Persistent conversation logging for Claude Code. Never lose context across sessions again.

claude-mechanisms★ 4

Operating mechanisms for Claude Code. Not rules. Not principles. Mechanisms with triggers, retry logic, and failure notifications. 20+ mechanisms, MIT.

agentyard-cli★ 4

Workflow orchestration for AI coding assistants. Creates isolated git worktrees & tmux sessions for Claude Code. Practical infrastructure for AI-enhanced development.

arcanum-artifex★ 4

Prompts, skills, and agents that survive contact with real workflows. No vendor loyalty. Occasionally heretical. 🧙🏻‍♀️

cli-agent-runner★ 4

Keep agent CLIs running 7×24 — supervise Claude Code / aider / any prompt-arg agent with 11-layer defenses and structured observability.

polywave★ 4

Polywave Agent Skill for Claude Code: parallel AI agents with disjoint file ownership, worktree isolation, and human-reviewed plans. Requires polywave-tools CLI.

wisp-orchestrator★ 4

Visual team-builder, plan-as-artifact, and live execution graph for autonomous Claude Code agent crews. Spawn a 3-role team, generate a DAG plan, run for hours, watch it ship in your browser.

Oh-my-ClaudeClaw★ 4

Autonomous AI assistant plugin for Claude Code — 5 MCP servers, 21 skills, 3-tier persistent memory, knowledge graph, multi-agent orchestration with Discord/Telegram integration for 24/7 Everyday working

Claude-Code-team-dashboard★ 4

Claude Code Agent Teams Dashboard - Monitor and visualize multi-agent team communication logs

jjtask★ 4

Structured task management using JJ (Jujutsu). Uses empty revisions as TODO markers with [task:*] flags, forming a DAG of plannable and executable tasks.

copilot-remote★ 4

Self-hosted web relay to use your local GitHub Copilot CLI session from any browser — phone, tablet, or second computer. Streams tool activity, supports ask_user question cards, file uploads, image attachments, model/mode selection, conversation history, and optional SSH tunnel for remote access.

GH-300-GitHub-Copilot-Demos★ 4

GH-300 live demo kit. A real Python app left intentionally immature (bugs, security gaps, low coverage) across 5 structured Copilot modules. Prompt library, Skills, AGENT.md, and a reset script included.

openclaw-mission-preflight★ 4

🎯 OpenClaw plugin: turn vague requests into execution-ready briefs. Ambiguity scan, plan stress test, brief generator. No API key needed.

codex-simplify-skill★ 4

150 lines that make Codex a senior refactoring engineer. Process + guardrails, not knowledge — because LLMs already know how to refactor.

skills★ 4

Reusable skills for AI coding agents (Claude Code, Codex, Forge) covering paper review, commit triage, GPU rentals, reference search, research logs, image-prompt composition, and more.

claude-snapshot★ 4

Portable Claude Code setup snapshots — export, diff, and apply your config across machines

intelligence-sync★ 4

Archived - replaced by the Intelligence CLI (Single source of truth for AI coding rules across Claude Code, Cursor, Copilot, Codex, and more. Write once, sync everywhere)

remote-ssh-dev★ 4

A Claude Code skill for working in large remote Linux repositories over SSH when your local machine does not have enough memory to run the project comfortably.

systemprompt-CLAUDE★ 4

Spec Driven Build 系统提示词 - 让 Claude Code / Gemini CLI 先设计再编码,通过需求→设计→任务三阶段驱动 AI 开发

wwa-transform★ 4

WWA Transform — Turn any website into an AI-powered agentfront. Claude Code plugin + Codex agent + CLI.

agent-skills★ 4

My AI agent skills for daily use. | 魔法哥开源的 AI Skills 合集。

veyraskills★ 4

VeyraSkills — A curated collection of Claude Code skills for founders, developers and AI builders

AgentHub-web★ 4

统一的 AI 编程助手 Web 平台(Claude Code、Pi Agent、Codex)。实时流式输出、分屏并行、Agent 切换 Unified web platform for AI coding assistants (Claude Code, Pi Agent, Codex). Real-time streaming, split-screen parallel mode, agent switching, dark theme

Goalkeeper-Claude-skill★ 4

Fable 5 workflow Loop; A Claude Code skill: autonomous build / audit / verify loop that runs until a machine-checkable contract passes, with ▎ deterministic anti-spin stop conditions (no-progress, retry, oscillation, budget) and on-disk human escalation.

harness-zh-release★ 4

Agent Team & Skill Architect for Claude Code (Simplified Chinese) — 面向 Claude Code 的简体中文元技能,一句话自动生成多智能体团队与技能

oh-my-Dynamic★ 4

Dynamic workflow tooling for Codex: planner/replanner orchestration, Codex CLI process swarms, broker evidence, and benchmark reports.

piv--loop-sdk★ 4

PIV Loop SDK: typed Plan/Implement/Validate agent framework for Claude Code, with independent validation loops and a full test + benchmark suite.

devflow★ 4

双 Pipeline 多 Agent 协作框架 PM + 6 个 Agent + 5 道关口 = 不会悄无声息挂掉的代码。可用于:Claude Code, Copilot, Cursor, Windsurf.

prompt-pocket★ 4

Cross-agent prompt pocket: remember your most-used prompts and pick one to run. Works on Claude Code, Codex, OpenCode, Cursor, Copilot & Gemini; auto-scans Claude/Codex/OpenCode sessions for prompts you repeat 7+ times. Forged by agent-plugin-kit.

devflow-autopilot★ 4

Make agentic coding work on real codebases. DevFlow is a Claude Code plugin that turns a request into a complete, tested, reviewed, documented pull request that's ready for your final review, and improves itself weekly.

skillscore★ 4

Lint and score any AI agent SKILL.md against the official Claude, Codex, and Antigravity authoring guides — offline Dart CLI.

forge★ 4

Agentic development framework for Claude Code, OpenCode, Codex CLI and Kiro — multi-runtime support

dev-boost★ 4

🚀 AI development accelerator toolkit - Boost efficiency by 50-100% for Claude Code, Cursor, Copilot and more

my-skill★ 4

Sanitized Codex skill for direct WeChat public-account drafting in 135 Editor.

codex-goal-control-experiment★ 4

Experimental local Codex goal-control panel and installable skill for thread goals via Codex app-server.

Teach2Claude★ 4

Distill your repeated Claude Code corrections into permanent CLAUDE.md rules. Zero dependencies, 100% local.

claude-token-inspector★ 4

Claude Code plugin with 8 skills to inspect, audit, and optimize your context window — see exactly what's eating your tokens and reclaim it.

clauditor★ 4

Audit your Claude Code instruction stack — find the rules Claude silently ignores (dead, contradictory, vague, duplicate, bloated). Zero-dep CLI + GitHub Action.

skill-forge★ 4

Turn complex AI workflows into reusable Claude skills. Capture the lessons to a tagged journal that survives context resets, then crystallize it into a validated skill.

fakoli-plugins★ 4

A curated collection of Claude Code plugins for enhanced productivity and development workflows

claude-switch★ 4

🚀 多窗口并行运行 Claude Code,每个窗口使用独立的 API 配置(官方 OAuth / 第三方),全程不污染全局 settings.json。支持 TUI 交互选择 + 参数透传 + profile 默认参数。

curdx-flow★ 4

Spec-driven development for Claude Code — turns vague feature requests into research, requirements, design, tasks, then executes them autonomously.

ai-usage-bars★ 4

Chrome extension that shows Claude.ai session (5h) and weekly usage as bars on the toolbar. Unofficial, no telemetry, 11 languages.

claude-code-plugins★ 4

My custom claude code (hopefully agentsmd soon) plugins for when I've scoured the interwebs and all the existing CC marketplaces but couldn't find anything good enough.

imagine-gemini-for-claude-codex★ 4

Imagine — bring Google Gemini into Claude Code & Codex: delegate reasoning, code review, research & automatic prompt-engineering. Runs on your Google AI Pro subscription, not your agent's tokens. MIT.

claude-code-api-watchdog★ 4

Auto-recover Claude Code sessions stuck on transient API errors. Outer-loop watchdog for unattended tmux Claude Code with usage-limit discrimination, exponential backoff, and 10-retry cap. Single file, no third-party deps.

god-mode-os-for-claude-code★ 4

Discipline hooks for Claude Code. Stops the agent from claiming 'done' without proof, blocks accidental writes to ~/.claude config, and routes prompts to skills via local pgvector with zero Anthropic tokens.

Couchbase-Skills-for-Claude.ai★ 4

This is a collection of skills I have created for Couchbase for Claude.ai

octo-cluster★ 4

All-in-one local harness for AI-assisted dev — RAG, memory, token economy, and verify gates. IDE-agnostic workspace folder; optional phase commands; extensible packs.

fables★ 4

Self-evolving skill packs that give Claude Code & Codex judgment, not knowledge — decidable rules, per-playbook regression quizzes for models, and a project harness generator. zh-TW canon + full EN mirror.

CodexOS-skills★ 4

Welcome to AI-Native Startup Codex Skills, a structured skill ecosystem designed to help founders, builders, and lean teams use Codex as a strategic startup operating layer.

agent-baton★ 4

Lightweight multi-agent relay coding skill for Claude Code(轻量级多 Agent 接力 AI Coding 框架)。旨在提供一个不同 LLM/Agent 在如何协作完成复杂企业级开发项目,如何进行断点交接。核心是一套极简的BA → Arch → Dev → TechLead 之间传递上下文和进度文档的框架。

dotnet-48-master-architect-skill★ 4

Universal multi-agent orchestrator for .NET Framework 4.8/4.8.1. 6 specialized sub-agents (Desktop, Web, Data, Security, Testing, Modernization). Works with Claude, Codex, Gemini, Cline, Copilot, Cursor. Open SKILL.md standard.

agentic-workflow★ 4

Multi-agent framework for Claude Code: tier-aware acceptance (S/M/L), acceptor/optimizer split, filesystem-isolated adversary review, cross-family second-opinion via Codex MCP, SkillOpt-style skill evolution, event ledger observability, human as supreme judge

init-multi-agent-team★ 4

Initialize a role-locked planner, developer, and QA multi-agent team for Codex projects.

crow-central-agency★ 4

Multi-instance Claude Code manager with a bundled web UI for orchestrating multiple Claude Code agents from one place.

okki-claw★ 4

Secure remote access to local OpenClaw, Claude Code, OpenCode, Codex and other AI coding agents via OKKI Claw relay.

agentic-sdlc-skills★ 4

Focused Codex/Gemini skills for agentic SDLC: specs, evals, security review, and production readiness.

ai-plugins★ 4

AI plugins for openEHR - specification authoring, review and governance skills. Claude Code marketplace.

m5stack-coding-toys★ 4

A physical status display for Claude Code — mirrors your live session (model, context, cost, rate limits, git) onto an M5Stack CoreS3 device.

personas★ 4

Portable AI personas for Claude Code and Codex.

ve-kit★ 4

VE Harness — run Claude Code for hours without babysitting it. A hosted task board that survives the session, hooks that deny the commit until a review ran, real-time shared memory for your team's agents, and a Docker worker that works your queue overnight.

desktop★ 4

Work3s - Agentic Command Center

auto-skill-finder★ 4

Universal AI skill router — auto-detects best installed skill per prompt + activates caveman mode for ~75% token reduction. Works with Claude, Codex, Cursor, OpenCode, Gemini CLI.

skills★ 4

Official MutagenT skills for AI coding agents — Claude Code plugin marketplace for prompt optimization, evaluation, and observability.

claude-design-prompter★ 4

Two Claude Code skills that turn your repo into paste-ready Claude Design prompts — brand-aware, project-type-tuned, language-aware, file-persisted.

agent-feed★ 4

Turn AI coding chats into a source-controlled workflow: AGENTS.md, rules, skills, verification gates, and adapters for Codex, Claude Code, and Cursor.

skill-bansos★ 4

Open Agent Skills for adding bansos.dev listings and developing the bansos.dev SvelteKit site.

gsd-lite★ 4

AI orchestration tool for Claude Code with MCP state management, review workflows, and plugin auto-update

claudex★ 4

Multi-account CLI companion for Claude Code that tracks usage limits, launches configured sessions, and applies skills & output styles.

VIBE-Claude-Plugin★ 4

Document-driven autonomous engineering workflow for Claude Code. 25 skills covering requirement analysis, architecture, coding, testing, security, E2E, and delivery.

opencli-skill★ 4

Agent-first OpenCLI skill with practical scenarios, desktop adapters, Chinese platform workflows, and troubleshooting guidance.

show-me-the-work★ 4

AI 코딩 비서(Claude·Codex·Gemini)가 확인도 안 하고 '다 됐어요' 하는 걸 자동으로 막아주는 품질 안전장치 — 비개발자·바이브코더를 위한 한국어 우선 하네스.

dual-gate-moa★ 4

Dual-Gate-MoA: harness-enforced dual gates for LLM agents (recon before acting, QA before shipping) + MoA multi-candidate competition. Ships as a self-contained replication PRD.

claude-shiploop★ 4

Autonomous delivery skills for Claude Code — pitch an idea, get an MVP. CEO/PO/DEV/Reviewer agent team with contracts, gates, and evidence rules.

codex-agent-governance★ 4

A deterministic, budget-aware control plane for Codex custom agents and Skills.

codex-sol-terra-luna-auto-orchestrator★ 4

Automatic risk-based task routing and multi-agent orchestration for Codex using Sol, Terra, and Luna.

multi-agent-governor★ 4

Evidence-based adaptive scaling and governance for homogeneous Codex agents.

ai-skills★ 4

Production-ready skills for Claude Code and multi-agent systems

scoop-skills★ 4

Scoop Skills: A specialized skill for the AI Agent agent to manage Windows packages using the Scoop command-line installer

codex-os★ 4

Codex-native operating layer for repeatable AI workflows with AGENTS autoload, project-isolated memory, plugin skills, and a thin ro CLI for terminal + VS Code chat.

skills★ 4

Skills collection wannabe.

Claude-Code-Wordpress-Plugin★ 4

Full AI-powered WordPress site management. Connect Claude to your dashboard and control everything with natural language.

agent-harness★ 4

A collection of Claude Code skills. First up: project-context — a self-maintaining context memory that survives session resets and context-window compaction.

design-system-skill★ 4
yoink★ 4

Switch between Claude Code accounts from your macOS menu bar or terminal, fast. Mac app + CLI · yoink.codes

cognito★ 4

Sistema operativo cognitivo para Claude Code: orquesta 7 modos de pensamiento según 5 fases de proyecto, con hooks deterministas contra el efecto ancla y la convergencia prematura.

codex-to-claude★ 4

Deprecated: development continues at Agentryx-ai/pass-the-thread.

claude-limits-gachi-soundboard★ 4

Claude Code usage limits in the macOS menu bar. Wakes Claude overnight for a fresh window by morning. Plus a gachi soundboard.

claude-rotate★ 4

Archived: replaced by Magpie (github.com/yetone/magpie), which covers all of it. Rotated across multiple Claude Code (Max/Pro) subscriptions by 5h/weekly quota headroom.

bgorkem-skills★ 4

Claude Code plugin marketplace with Agent Skills for Claude. Install via /plugin marketplace add bgorkem/bgorkem-skills

claude-code-codex-skills★ 4

Drop-in Agent Skills, subagents, output styles, hooks & config templates for Claude Code (~/.claude) and OpenAI Codex CLI (~/.codex). Copy, restart, done.

claudex★ 4

Mobile-first remote control for Claude Code — drive your local claude CLI from your phone. Self-hosted, your keys, your machine.

mini-Brain_skills★ 4

A set of Claude Code Skills modeled after distinct human thinking patterns (brainstorm, thinking, idea, explore, create, guide, study, try).

gemini-plugin-cc★ 4

Claude Code plugin to call Google's Gemini for ask, code review, adversarial review, and long-form rescue tasks. Wraps @google/gemini-cli with model pinning, env scrubbing, ANSI sanitization, and a stop-time review gate.

claude-sessions-sidekick★ 4

Windows tray sidekick for Claude Code — paste screenshots into the terminal, live usage tracking, session browser, quick launchers & more.

More in Coding agents & developer tools