Coding agents & developer tools

Claude Code, Codex & Cursor extensions

8,960 agents · most starred first

Claude Code, Codex & Cursor extensions, page 46 of 90

industrial-design-portfolio-skill★ 10

Evidence-first industrial design portfolio Skill for Codex, Claude Code, Cursor, Gemini CLI, and OpenCode.

agent-personalizer★ 10

AI custom instructions from approved entries: a profile and rules for Claude Code, Codex, Cursor, Gemini CLI and ChatGPT, kept in sync from one source.

two-claude-accounts-mac★ 10

Run two Claude accounts at the same time on a Mac — a branded, isolated second Claude Desktop app. Companion to melkon.tech/blog/two-claude-accounts-mac

jev-advisor★ 10

A private, local decision-advice Skill for Codex that ranks tool choices, estimates risks, guides recovery, and checks completion evidence.

tally★ 10

Free, open-source macOS menu bar app showing AI usage limits (5-hour, weekly, top model) for multiple Claude Pro/Max and Codex accounts side by side, plus a launcher that starts each Claude Code session on the account with the most room. Read-only, on your own paid subscriptions.

workbuddy-dual-edition★ 10

WorkBuddy 国内版(workbuddy.cn)与国际版(workbuddy.ai)同机共存方案:双开失败、装国内版却变国际版、重启后被自动更新覆盖 —— 根因定位与完整修复。Windows 5.8.x 实测通过,附可直接加载的 Agent Skill。

repo-seed★ 10

Seed agent-native, self-governing repos: AGENTS.md, MADR decision logs, deterministic gates & pre-commit hooks. Upgradeable — never overwrites your edits.

agent-skills★ 10

Meteor-maintained Agent Skills for building, migrating, testing, securing, and deploying Meteor 3 applications.

since-cutoff★ 10

Find which APIs of your pinned Python dependencies changed after your coding model's training cutoff, and give the agent short AGENTS.md / CLAUDE.md notes from a static API diff. No model calls, no API key. CLI, MCP server, Claude Code plugin, GitHub Action.

ai-dossier★ 10

An open standard for signed, versioned agent skills. Model-driven orchestration with a deterministic shell — host anywhere, verify who wrote it. CLI, registry, MCP, VS Code.

den★ 10

See, approve and steer all your Claude Code agents from one terminal screen.

trae-superpowers★ 10

Install obra/superpowers skills into the Trae IDE, activated from the first message via User Rules.

claudeBuddy★ 10

A desktop pet that knocks when your AI coding agent (Claude Code, Codex) is done or needs you. Windows, built with Tauri.

superpowers★ 10

Jesse Vincent's Superpowers skills (brainstorm, plan, TDD, debug, verify, review) adapted for GitHub Copilot agent mode, with project-scoped installers. MIT, adapted from obra/superpowers.

AgentDomains-skill★ 10

Free subdomains under makes.fyi / agentdomains.co, as a Claude Code skill: agents claim a name and set DNS records, auto-HTTPS proxy or forwarding.

critical-decisions★ 10

Claude Code mod: shows the critical decisions your agent made without being asked, so you can rethink them. Works in any kind of project.

agentic-awesome-kits★ 10

A universal collection of reusable Loop Engineering kits for AI coding agents—not just prompts. Each kit combines Skills, Rules, Templates, workflows, and validation loops to help agents autonomously plan, execute, verify, fix, and improve engineering tasks.

engineering-review-board★ 10

A collection of AI agent skills I have written

project-handoff-skill★ 10

Codex skill for evidence-backed project handoffs across fresh tasks

ste-writing-style★ 10

Simplified Technical English (ASD-STE100) skills for AI coding assistants, featuring extensible dictionaries and automated vocabulary discovery.

skills-hub★ 10

Agent Skills for real engineering work: impact maps, proof-driven development, production gates, investigations and more. For Claude Code and any Agent Skills-compatible agent.

skills★ 10

Agent Skills to help developers using AI agents with Lingui

skills★ 10

You say the job; the playbook runs. 161 agent skills + 63 slash commands for Claude Code, Cursor, Codex, and Gemini CLI. Tuned for React / Next.js / Supabase.

skills★ 10

Agent skills and guardrails for designers who ship production code: Figma fidelity, review gates and the full change workflow.

paddock★ 10

Self-hosted web UI for Claude Code. Persistent, resumable chats on your own server — fork, rewind, and reach them from any browser.

claude-code-handoff★ 10

Stop paying to replay old Claude Code sessions. A summary file is saved after every reply, and a new session picks up from it for ~5x less.

200-agent★ 10

200 个面向中国市场的 AI agent,单源转译适配 Claude Code / Codex / OpenClaw

RepoMagpie★ 10

RepoMagpie: your coding agent remembers the repos you’ve tried, and what you thought of them.

claude-code-ui★ 10

A web UI for Claude Code: run and steer many sessions from your browser or phone. Local daemon, no cloud.

pi-agent-portrait★ 10

Animated pixel-art portrait for the pi coding agent. It reacts to thinking, tools, failures and idle time, and draws a custom character for each agent from a one-line brief or a photo.

skills★ 10

Agent skills that make coding agents show their work: read a Jam, prove a change, point at the problem, test a flow. Works with Claude Code, Cursor, Codex, Copilot and Gemini CLI.

alchemist-coder★ 10

Free, open-source desktop app for Claude Code and Codex: follow every agent and subagent live, run your own agent organization and automate routines. Also searches your Gemini CLI and Grok history. macOS, Windows, Linux.

claudecode.nvim★ 10

Claude Code in Neovim with Cursor-style hunk review: keep or revert each change Claude makes, review proposals before they are written, and run Claude full screen in zen mode. The up-to-date claudecode.nvim.

claude-code-mods★ 10

Six Claude Code mods: plan limits and context above the prompt, an allowlist coach for permission prompts, subagent tokens, tests in the status line, one-click actions and a quiet transcript

codex-themes★ 10

Interactive gallery of 1000+ customizable themes for Codex with live preview and export

offsite★ 10

Claude Code, Codex and OpenCode in your browser. Shares sessions with their CLIs, so you can start in one and resume in the other. Includes a terminal, file previews and git diffs.

claude-code-export-import★ 10

Export & import Claude Code sessions between machines, accounts (email) and app builds (Win32/MSIX). Reverse-engineered, unofficial, MIT.

cache-maxxer★ 10

A Claude Code mod that keeps your cache warm, so you pay 96% less to re-read your conversation

paneline★ 10

Claude Code mod (plugin) that adds a side pane with Activity, Files, Agents, Context and MCP tabs, a status line above the prompt, a restyled chat, Mermaid diagrams in the terminal, tables, and code and diff panels. Colours follow both /color and the /theme (dark, light and others).

ai-native-sdlc★ 10

An AI-native SDLC as a Claude Code and Codex plugin: six stages, one committed Markdown artifact each, a human gate at every handoff. Implements Anthropic's AI-Native SDLC playbook.

claude-switcher★ 10

Switch Claude Desktop accounts without signing in again, and keep every Claude Code chat with you. Windows, macOS and Linux: full-screen app and CLI, chat recovery, undo.

orca-claude-accounts★ 10

Orca plugin: switch Claude Code between multiple accounts (setup-token), with token checks and per-account usage

claude-account-switcher★ 10

Bill each Claude Code session to a different Claude subscription, per project or on demand, inside one Claude Desktop app. Loopback relay + hooks plugin. Windows and Linux tested, macOS installer included.

dsh-forge-studio★ 10

Aggregated dsh plugins for daily use — a dsh-plugin rewrite of Forge Studio.

autoharness★ 10

Engineering discipline for coding agents: prepare before building, check against the original, let an independent critic judge the result.

managents★ 10

USB desk display showing what your AI coding agents (Claude Code, OpenCode) are doing — ESP32 firmware, Go helper, 3D-printable 45° enclosure

TAXOVELA★ 10

AI-native enterprise architecture design and validation skill pack for Claude Code, OpenCode, Codex, Copilot, and Cursor.

shepherdr★ 10

Shepherd delegated coding agents into visible, auditable herdr panes you can watch, resume, and take over — a herdr plugin.

triathlon-agent-public★ 10

Multi-agent AI coach that plans one training week at a time for triathlon, running and trail: reads Intervals.icu data, applies Friel/Daniels/Coggan doctrine with deterministic load checks and audits, and pushes approved structured workouts back to Intervals.icu. Python, stdlib only.

family-office-ai-skills★ 10

Reusable AI skills, prompts, and workflow templates for lean family offices, RIAs, and wealth operators. Read-only, human-in-the-loop, non-advisory.

tmux-canopy★ 10

A tmux workspace tree and AI-agent monitor in one sidebar, with no daemon. Tracks Claude Code, Codex, OpenCode, Gemini, Cursor and more.

wherdr★ 10

Use Herdr from anywhere — your iPhone, Android phone or any browser. Watch your coding agents, answer them and run your herdr-projects, privately and securely.

sdd★ 10

Spec-driven development (SDD) workflows and AI coding agent skills for Claude Code, Codex, Cursor, and OpenCode. Plan, implement, and verify features, bug fixes, and enhancements.

kindle-token-panel★ 10

免越狱将闲置 Kindle(含咪咕版)改造成 AI 实时墨水屏看板:投影 Token Monitor 用量/费用/模型榜 + 全渠道在途 Agent 任务进度条(零依赖标准库 · Agent Skill)

dsh-step-pause★ 10

DeepSeek Harness 插件:每 N 步(可配)自动停下汇报一次进度——正在做什么 / 已完成什么 / 接下来做什么 / 卡点——说完立刻继续,不占额外回合、不等你回复。默认只在主智能体汇报,可在设置里调整。

agent-valley★ 10

Every Claude Code agent and sub-agent at a glance, in the notch of your Mac.

codex-long-jobs★ 10

Long-running background jobs for OpenAI Codex CLI that run detached without model polling and wake the original Codex session on completion via tmux.

claude-referee★ 10

Evidence over eloquence. Unofficial Claude Code plugin that checks "done" claims and small judgement calls with TypeSafe Jev, and keeps receipts.

herdr-assist★ 10

Physical desk panel for Herdr, the terminal multiplexer for AI coding agents — shows session state in color and rings a bell when an agent stops to ask for a decision. ESP32-S3 + LVGL, prebuilt firmware.

nerviz★ 10

Nerviz — an agent harness for Spring Boot. Claude Code skills, agents and hooks that generate Spring Boot projects and keep AI-written code on-architecture: DDD, dependency direction and naming enforced from domain to tests.

Handoff★ 10

Portable working context for AI coding agents: save your state once, and every agent (Claude Code, Codex, Cursor, Copilot, Gemini CLI) picks it up.

codex-agent-bar★ 10

a lightweight macOS menu bar app for monitoring your Codex quota at a glance

resume-claude-codex-grok★ 10

Pick up in-progress work from one CLI agent inside another: Claude Code, Codex, Grok Build, OpenCode, oh-my-pi, Cursor. Inspired by Grok Build (xAI).

nongeneric★ 10

Anti-slop design + GSAP motion skill pack for AI coding agents, with an 82-rule UI detector.

selected-model-is-at-capacity-tmuxer★ 10

Auto-continue the Codex CLI when it stops with 'Selected model is at capacity. Please try a different model.' — a tmux watchdog.

kabmo★ 10

Web console and diagnostic workbench for AI coding agents — omp by default, with Claude Code, Codex, OpenCode and any ACP agent beside it. Elysia + Preact on Bun.

rigorkit★ 10

Tool-neutral skills and workflows for rigorous AI-assisted development.

koto★ 10

Move conversations between Claude Code, Codex, Cursor, and more. Keep your conversation history, branch into different agents, and compare what happens next.

context-hub★ 10

Local library for Claude Code and Codex skills, prompts, MCP servers, plugins, and environment variables. Desktop app, CLI, and local web UI; delivers each asset into the agent's own workspace or global directory.

shepherd★ 10

Native macOS and Linux app for running many Claude Code and Codex agents side by side — see which one is waiting on you. A GPU-rendered client for herdr.

agents-dont-sleep★ 10

Close the lid, let your agents cook. A tiny tray app that keeps your laptop awake (lid shut, in your bag) only while Claude Code, Codex & friends are working, then lets it sleep. macOS · Windows · Linux.

hearting★ 10

Keep your coding agents on your intent. One way of working across Claude Code, Codex, and OpenCode — a capable model plans, lower-cost workers carry it out in checked steps, and Fleet shows every session live.

cc-desktop-mod★ 10

Claude Code plugin (mod) that makes the Claude Code terminal UI look like the Claude desktop app: prompt bubbles, markdown tables, mermaid diagrams, folded tool calls, subagent cards, diff pane and context meter.

glanceflow★ 10

GlanceFlow for Claude Code: a calm checklist above the prompt showing the plan, progress and when Claude needs you. Simple view for everyone, Details for engineers.

codex-switch★ 10

Local Codex account switching, quota history, Windows model providers and recovery. Windows/macOS; Linux preview.

Skillry★ 10

Installable, permission-bounded agent skills & subagents for Claude Code, Codex, Cursor, Copilot & Antigravity: 65 skills + 122 agents across 18 departments, dry-run-first installer, full upstream attribution. MIT, by FluxonLab.

codex-runtime-repair★ 10

Conservative Windows repair tool for Codex desktop runtime cache startup failures

domain-driven-kit★ 10

Executable DDD for Spring Boot 4: domain building blocks, architecture guards, reliable events, and Maven archetypes for humans and AI coding agents. Available on Maven Central.

Public-Agent-Kit★ 10

Agent-independent skills, rules and hooks for Claude Code, Antigravity and Qwen Code: blast-radius change-impact analysis, prompt expansion, yt-dlp video/audio downloads, transcripts via captions or Groq Whisper, offline web page copies, a PII and credential guard hook, plus reply and ticket rules. Every folder is self-contained, no shared code.

agent-workbench★ 10

One local UI for the Claude Code, Codex, OpenCode and Antigravity CLIs: tabs, browsable history, conversations as cards, handoff between CLIs, global search, context meter, git and file tree. Never touches your credentials.

dsh-plugin-debugging★ 10

A DSH plugin debugging toolkit. Your agent inspects, diagnoses, and fixes its own runtime. | DSH 插件排障工具箱。让 Agent 自检自修身处的运行时。

RuleForge★ 9

Auto-generate AI assistant rules (CLAUDE.md, .cursorrules, copilot-instructions) from codebase analysis

intern-clawd★ 9

A Personal Secretary OS for Claude Code — persistent memory, rituals, dual-domain wiki. $0 extra cost on your existing subscription.

conclave★ 9

A Claude Code skill that makes multiple LLMs debate, critique each other anonymously, and synthesize a single superior answer.

UltraCodeAI★ 9

UltraCodeAI is an innovative AI-powered IntelliJ plugin that transforms coding with seamless assistance. It supports local/cloud LLMs like Ollama, OpenAI, and Groq for context-aware prompts, auto code error analysis, and RAG-enhanced insights. Features includes tabbed UI for chat, diagnostics, and recommendations; hover explanations; design pattern

mneme★ 9

Enforce architectural decisions in AI-assisted development.

cascade★ 9

AI-native coordination for multi-service development. Claude Code plugin.

livetap★ 9

Push live data streams into your AI coding agent. MQTT, WebSocket, file tailing → expression watchers → Claude Code Channels alerts.

reins★ 9

Harness Engineering CLI — scaffold, audit, evolve, and doctor agent-readiness for any repo

onion-architecture★ 9

The Onion Architecture: 8-layer diagnostic and scaffold for production AI systems. npx onion-check to scan. npx create-onion-stack to build.

claude★ 9

Personal Claude Code configuration - global rules, 15+ expert agents, reusable skills, hooks, and coding standards for consistent AI-assisted development.

Claude-Code-Dev-Agents★ 9

A comprehensive collection of specialized Claude Code subagents for software development lifecycle. Domain-agnostic experts covering backend, frontend, cloud infrastructure, AI/ML, security, DevOps and project management.

rolling-wave-engineering★ 9

Rolling-wave Codex skills for shaping, implementing, reviewing, and completing one concrete slice at a time.

rules-for-ai★ 9

Rules and guidelines for optimizing AI coding assistant interactions in Windsurf and Cursor IDEs.

claude-dev-kit★ 9

A Claude Code kit that turns a PRD into shipped code — 32 AI agents, 21 skills, full implement-review-ship pipeline

jido_harness★ 9

Normalized Elixir protocol for CLI AI coding agent adapters.

karimo-overview★ 9

Interactive Overview of how KARIMO works - Autonomous development framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and designers shipping real features. Phased adoption from PRD execution to automated review, code review, and CI-friendly agent teams

meta-skills★ 9

43 composable skills that turn an AI coding agent into a product team — research, marketing, product, and meta-process. Install via npx plugins add hungv47/meta-skills (also works with npx skills add) or the Claude Code plugin marketplace.

ftw★ 9

First Try Works — vibecoding takes 47 tries, FTW takes one. Multi-agent validation workflow for Claude Code and OpenClaw.

ampalibe-extension★ 9

VSCode extension for Ampalibe framework 🥝

More in Coding agents & developer tools