Coding agents & developer tools

Claude Code, Codex & Cursor extensions

8,960 agents · most starred first

Claude Code, Codex & Cursor extensions, page 68 of 90

tonton-claude★ 4

Control Claude Code running on all your machines (Windows, Linux, macOS) from your Mac's notch. Live status, full chats with images, send messages, approve permissions

deterministic-design-skill★ 4

deterministic-design — a Claude Code skill that renders your UI and proves it's balanced + usable: deterministic layout audit + vision-judged usability.

platformio-dev-skill★ 4

基于PlatformIO平台的嵌入式软件开发AI技能。AI skills for developing embedded software based on PlatformIO platform.

Orchestrate-skill★ 4

Created by SANTHEESH 🚀 | Universal AI coding-agent toolkit for HackerRank Orchestrate, supporting Codex, Claude Code, Cursor & more with intelligent workflows, automated testing, evaluation, and submission validation.

skill-distill★ 4

Sharpen AI agent skills. Lint, diff, optimize, and benchmark skill descriptions for better routing accuracy.

dsh-theme-plugin★ 4

Theme studio plugin for the DeepSeek Harness agent web GUI: 5 presets, 70+ derived tokens, live apply via the official plugin API

agent-skills-validator★ 4

Validate your SKILL.md before an agent doesValidate SKILL.md files against the Agent Skills specification. Go CLI, GitHub Action and container image with stable rule IDs and JSON output.

claude-pptx-skills★ 4

19 Claude skills for the .pptx file itself: corporate templates, masters and layouts, brand compliance, font embedding, export and accessibility. Built by Oria.

delta-me13-skill★ 4

δ-me13 skill · 《崩坏:星穹铁道》δ-me13篇同人:十三黄金裔工程方法卡+总路由 skill 套件(Claude Code/Cursor),工作可交付、闲时可沙龙;附介绍页、闪卡画廊与全体会议实录

OpenAgents★ 4

Work with AI coding agents on long projects: rules, decisions and plans live as plain Markdown in your repo, so Claude Code, Codex, Gemini CLI or Cursor picks up where the last session stopped. Optional: hand subtasks to other agent CLIs with a full record, a snapshot to roll back to and a verdict on each; search past conversations.

lifecycle-guard★ 4

Full-lifecycle definition-of-done for Claude Code: forces whole-feature specs, blocks half-done work, and self-learns your style and its own misses.

agent-token-saver-skill-router★ 4

Your agent reads the few skills a task needs, not forty. Picks none, one, or a small bounded set, and leaves the rest on disk.

nextcore-skills★ 4

Skills from a real product, not a demo: Claude Code plugin marketplace with nextcore-design (UI), nextcore-dev (frontend ↔ backend contract) and nextcore-workflow (running AI agents) — every rule backed by a measured incident.

el-camello★ 4

🐪 16 AI Skills para Antigravity (Gemini). The Office, pero colombiano. Y con IA. Productividad x10 con agentes especializados.

claudash★ 4

The control room for Claude Code: every session and project on one terminal screen. See what a waiting session asks, resume or read any conversation, sign in to MCP servers, review a branch in its own worktree, run the next spec step. Rust TUI + CLI.

claudex★ 4

Query, search, and analyze Claude Code sessions.

plan-html★ 4

Interactive decision-deck planning — serve a plan.json as a live, offline HTML deck you work through in the browser.

ccusage-statusbar★ 4

VS Code status bar widget for Claude Code usage (via ccusage): active 5-hour block, today and this month

archpane★ 4

Claude Code plugin: a live architecture diagram in a side pane that Claude draws and updates while you talk

claude-code-mods★ 4

jr Claude Code mods: 43 free, open-source mods for Claude Code. Context bar, plan limits, prompt cache countdown, system monitor, billable time, safety guards, dictation fixes. One-line install each, no tokens.

skillsPanel★ 4

Agent Skills 统一管理工具 —— 跨平台统一管理 AI 编程工具的 Skills 技能包

furniture-designer-plugin★ 4

Claude Code plugin for professional furniture design — AI skill for structural validation, cut optimization, BOM generation, and FreeCAD 3D visualization.

agent-checkpoint★ 4

Zero-data-loss file snapshotting, selective rollback, and token-optimized audit trail for AI coding agents (Cursor, Claude Code, Cline, Windsurf, Antigravity).

rulereceipt★ 4

Did it push straight to main? Touch a file you told it never to? RuleReceipt checks a finished AI-agent session against your CLAUDE.md / AGENTS.md rules and marks each followed, broken, or can't-tell — with the exact line. Runs locally, nothing uploaded.

dugout★ 4

Companion repo for the talk 'From Sidebar to Sub-Agents' — leveling up AI-assisted development live, one branch per level.

cc-retry-watchdog★ 4

Auto-resume Claude Code sessions killed mid-stream. "API Error: Connection lost mid-response" finalizes the turn with no retry — this watchdog notices and types your retry prompt into that exact terminal. macOS Terminal.app, iTerm2, tmux.

emniyet★ 4

🛡 Safety net for Claude Code: explains every command in plain language, backs up before risky ones, one-command undo. Guards secrets. English & Türkçe.

Skills_Curator★ 4

Decide once. Re-decide never. A Claude Code skill that evaluates skills before installing and persists every decision.

scrape-skill★ 4

Claude Code skill: describe the data you want from any website and get a CSV — no selectors, no code. 스크래핑을 몰라도 'URL + 한 문장'으로 데이터를 CSV로 받는 Claude Code 스킬. Playwright analysis, sample-row confirmation, rate-limited collection, saved recipes; honest about bot checks, logins and robots.txt.

usage-bars★ 4

Claude Code mod: your 5-hour and 7-day usage limits as live, animated bars under the prompt — countdown, pace mark, projection, Pac-Man.

design-review-skill★ 4

A Claude Code skill that turns Claude into a design reviewer that SEES your page. Uses Playwright MCP to capture desktop/tablet/mobile screenshots, audit typography, contrast, rhythm, hierarchy — and propose concrete CSS fixes. Bilingual EN/RU.

throughline★ 4

Claude Code plugin: a PRD/TDD/ADR design-doc pipeline with phase-gate PRs, an independent design-critique gate, toolchain bootstrap, and gated unattended implementation (failing-test-first + verify + cross-model review, one PR per TDD).

agency-os★ 4

Run your work like an AI agency, from a single Notion board. Ships as a Claude Code plugin and an MCP server — runs in Cursor/Cline/any MCP host.

dsh-desktop★ 4

Unofficial macOS/Windows desktop app for DeepSeek Harness (dsh): manages the runtime, supervises the server, and puts the web UI in a real window.

dsh-session-toolbox★ 4

DeepSeek Harness 会话工具箱:图片草稿保险箱、项目分组与会话迁移、归档池、文件检查点恢复、多引用回复、后续任务联想。第三方插件,数据只存本机。

front-agent★ 3

Claude Code plugin for React/Next.js — multi-agent orchestration, Figma-to-code, TDD, Harness Engineering, RTK, Obsidian

prefer-html-output-skill★ 3

Claude Code skill: decide when to render output as HTML over Markdown — based on Thariq Shihipar's html-effectiveness examples. Bilingual (zh-CN / en).

gemini_cli_skill★ 3

🚀 Enhance Claude Code with Gemini CLI for better code generation, reviews, testing, documentation, and architecture analysis.

multi-agent-dotfiles★ 3
everything-opencode★ 3

Migrated the brilliant everything-claude-code repo to an equivalent for Opencode. As I use several different programming languages, I'll progressively add support for all of them

ai-agent-skills★ 3

Skills that help AI agents build better AI agents — prompt engineering, architecture, evaluation, and more.

chrysippus★ 3

🎭 hark / ahoy / fr no cap / mans still — Claude Code plugin that makes thy AI agent speak like Shakespeare, a pirate, Gen-Alpha, or a Toronto mans. Code stays verbatim. For fun, not for token savings.

session-recorder-skill★ 3

A Claude Code plugin that helps you turn ideas into reality. It silently records the full AI session lifecycle, automatically fetches proven solutions from the community for reuse, and compiles structured reports back — so every collaboration stands on the shoulders of those before it.

m2star★ 3

Self-learning agent system for Claude Code. Humans steer at every layer. The agent learns at every layer.

scope-lock★ 3

Claude Code skill that enforces task scope boundaries during agent execution, preventing drift beyond the approved plan.

ralph-x★ 3

Interactive AI development loop with mode selection — choose your pipeline before you start

supervis★ 3

DeepSeek drives Claude Code so you don't babysit every prompt

voriya-skills★ 3

Practical AI agent skills for Codex and Cursor, starting with website capabilities to API-first skill generation.

langchain-community-plugin★ 3

Claude Code plugin for LangChain and LangGraph development. Skills, commands, and reviewer agents for building AI agents, RAG pipelines, and LCEL chains.

cc-llm-wiki★ 3

Claude Code 중심 로컬 전용 LLM Wiki — 3층 격리 + Neo4j GraphRAG + Obsidian. Karpathy LLM Wiki 원전부터 GraphRAG PoC 까지 11가지 관련 내용 통합. /install 한 줄 셋업, 8 Skills + 5 Hooks + 4 Routines.

ai★ 3

🤖 Extend AI coding assistants with 115 skills, 16 agents, and 48 commands for structured, expert-driven development workflows.

octant-council-builder★ 3

Claude Code plugin that morphs into multi-agent evaluation councils — not just a council itself, a tool for building one

kyros-cli★ 3

Kyros multi-agent CLI for Claude Code, Codex, and OpenCode.

tandem★ 3

Real-time multi-agent collaboration for Claude Code. Connect up to 5 sessions with E2E encrypted messaging, shared task boards, and structured findings.

claude-code-macro-programming★ 3

Claude Code自然言語マクロプログラミングガイド

bridge-agentic-pipeline★ 3

BRIDGE Development Pipeline. From business requirements to delivered solutions using AI agents. Built for development agencies, consultancies, and engineering teams.

VibeCode-PlayBook★ 3

Lean multi-agent Codex workflow for vibe coding with better context control, less token waste, and stronger end-to-end validation.

cowmoo★ 3

Multi-agent Claude Code configuration for building production applications. PM, UXUI, planner, and builder agents — each in its own terminal with fresh context, coordinating through GitHub Issues.

ai-tpk★ 3

Clone-run-forget Claude Code agent toolkit — D&D-themed multi-agent workflows for planning, reviewing, investigating, and shipping code.

be-my-butler★ 3

Multi-agent pipeline for Claude Code — 12 steps with cross-model council and blind verification

agent-architect★ 3

AI-powered framework for building multi-microservice systems. Spec-driven development with Claude Code & GitHub Copilot. Plan → Spec → Contract → Build → Validate. No custom tooling — just markdown and slash commands.

EasyAgents★ 3

Multi-agent collaboration in your favorite IDE. No new apps - just npm install and your AI IDE gains multi-agent superpowers. Works with Claude Code, Cursor, Windsurf, Cline, Aider and more.

claude-sdlc★ 3

A governance layer for AI-assisted software delivery. Plan, scope, approve, build, test, release — with human sign-off at every gate.

official-claude-plugins★ 3

A curated collection of reusable AI skills, prompts, and agent configurations. Portable across AI coding assistants and agent frameworks.

pantheon★ 3

A marketplace of plugins for AI coding agents.

skillspec★ 3

SkillSpec is a DSL that adds types, contracts, composition, and tests around agent skills, then compiles back down to the same SKILL.md that existing runtimes already understand. Once a skill works and you want to make it production-ready, you codify it into a .agent file and get versioning, structural diffs, type checking, and a path to CI/CD.

dataagile-agent-kit★ 3

Plugin Claude Code para Protheus e ADVPL/TLPP — base 155k+ registros, Agent Teams, compilação TDS-CLI, testes TIR e MCP PO-UI

agent-tools★ 3

My tools for working with AI coding agents

Agentic_Engineering_Methodology★ 3

Battle-tested 7-phase methodology for shipping real software with AI coding agents (Claude Code, Cursor, Copilot) — from idea to production. The structured alternative to vibe coding.

antigravity-skills-boilerplate★ 3

Agent Skills Curator Boilerplate for Antigravity Developments

claude-spec-workflow★ 3

A structured workflow process for Claude Code with slash commands

blue-gardener★ 3

Repository to provide specialised sub-agents and skills for various AI platforms as a CLI tool

Debug-VScode-Wordpress-for-AI★ 3

WordPress plugin that allows you to "expose" wordpress debug logs to Agent LLMs avoiding manual copy and paste.

claude-code-teams★ 3

🍕 One Pizza Team [AI Agents Team ] | Claude Code Agent Squads

speci★ 3

Multi-agent implementation loop orchestrator for GitHub Copilot.

system-zero★ 3

Open protocol and CLI for installing autonomous AI behaviors into any code repository.

chiron★ 3

Teach-first mentor mode for AI coding tools.

mcp-standards★ 3

Self-learning AI standards system - learns from corrections and auto-updates CLAUDE.md

ai-agent-workspace★ 3

A production-ready meta-workspace template for AI-native development. Unify your Agent rules, memory context, and multi-repo workflows. (专为 AI 原生开发打造的元工作区模板。统一管理 Agent 规则、记忆上下文和多仓库工作流。)

flipclaw★ 3

FlipClaw — Flip the tables. Claude Code CLI is your primary interface. OpenClaw wraps around it with persistent memory, auto-skills, Dreaming, and 24/7 automation.

IDE-RoleMaster★ 3

ai coding角色插件 各司其职 辅助一人公司 目前可用于Qoder和VScode

capy-bridge-skill★ 3

HappyCapy skill: Connect any Mac in 30 seconds. Claude Code capabilities with local Mac terminal access. Zero dependencies, encrypted Cloudflare tunnel, 24/7 auto-restart.

python-optimization-skill★ 3

Claude Code skill for Python optimization using real-world benchmarks from Python 3.14. Guides code generation with concrete performance data on data structures, JSON libraries, async overhead, and more.

cline-rules-nextjs-template★ 3

Enterprise-level Cline rules for Next.js development. Generate professional applications with sophisticated AI-guided standards, TypeScript, Tailwind CSS, and complete tooling setup.

llamawhip4e★ 3

An Eclipse plugin that integrates LLM into Eclipse (focus on Ollama, LocalAI, ChatGPT and Copilot)

AutomationHelper_plugins★ 3

Skills based claude code plugins for generating automation on multiple platform.

claude-code-starter★ 3

One-click Windows setup + zero-to-expert guide for Claude Code. Includes installer, CLAUDE.md templates, example agents, slash commands, and config files. No experience required.

chace.nvim★ 3

A token efficient and less intrusive AI code completion plugin for neovim

10x-Agent-Loop★ 3

Break through Cursor / Windsurf quota limits and achieve true autonomous programming loops. 10x-Agent-Loop enables infinite interactions within a single Fast Request through file-watching technology, while providing a Consultant Mode that leverages external AI models (Gemini/Claude) to break through technical bottlenecks.

metatemplate-ai★ 3

MetaTemplate: a lightweight, file-based framework for working with AI on anything — projects, coding, daily tracking, or long-horizon goals. Includes BM25 keyword search for Claude Code.

claude-plugins★ 3

Claude Code plugin marketplace by DeBytes — AI-powered tools for productivity

claude-linguist★ 3

Claude Code plugin marketplace with plugins for improving English, Spanish, or any of your other languages

opus-compatibility-scanner★ 3

Free Claude Code skill that audits CLAUDE.md, AGENTS.md, subagents, settings.json, hooks, and Anthropic SDK call sites for Claude Opus 4.6 ⇄ 4.7 compatibility issues. 70 patterns. MIT.

ccinspect★ 3

Linter & runtime auditor for Claude Code configs — 40+ lint rules, write-blindness, agent-bypass, orphan agents, ghost MCP servers, token economics, session recovery. Fully offline.

image-uploader-claude-code★ 3

Paste clipboard images directly into Claude Code

MindForge★ 3

A comprehensive AI toolkit for Claude Code featuring multi-language agents, reusable skills, and MCP services to supercharge your development workflow

pulse★ 3

Rich statusline for Claude Code — 30+ items (context / tokens / cost / rate limits / git), color ramps, bar styles, and a live TUI editor. Runs fully offline.

chmod-777-claude★ 3

🔓 Four opinionated skills for Claude Code: rootfix (root-cause debug), rootclean (refactor only), rootbuild (feature add), rootimagine (pre-deploy simulation). Stop patching symptoms. Stop ignoring patterns. Stop merging without tests. Stop deploying without simulating.

claude-fitness-break★ 3

30-second physical micro-break suggestion for Claude Code — rule file, snippet, or hook.

ping-claude★ 3

Your local Claude Code terminal, accessible from your phone. Approve permissions, send commands, watch it work — all over Tailscale. No cloud, no relay, nothing leaves your machine.

More in Coding agents & developer tools