Coding agents & developer tools
Claude Code, Codex & Cursor extensions
8,960 agents · most starred first
Claude Code, Codex & Cursor extensions, page 51 of 90
Unofficial minimal Windows launcher for Codex Desktop Control other devices
🔍 A beautiful web viewer for AI agent session files. Browse Claude Code & OpenClaw conversations with chat-style UI, timeline visualization, and zero setup.
Multi-agent context firewall, MCP schema tree-shaker, and token budget guard for Claude Code (CLAUDE.md), OpenAI Codex (AGENTS.md), and Cursor.
Unofficial Windows always-on-top widget for remaining Codex and Claude usage
Production-grade genpark-recursive-descent-ast-parser-skill skill for AI agents
Production-grade genpark-cky-probabilistic-grammar-parser-skill skill for AI agents
Deployable agent harness for Cursor, Claude, and AGENTS.md playbooks—with MCP tools, AG-UI, durable pause/resume, and any LiteLLM model.
CLI to pick and safely combine AI coding agent skill packs
TITAN - Technical Intelligence, Tasking & AI Navigation. A Codex AI development methodology by NETELITE.
[截至2026-07-23] 新账号不可用(403);已授权无影响 · Codex Agent Identity · no SMS for already-authorized only
面向非技术产品经理的 Codex Skill:设计、实现、调试和审查可靠的 Agent 工作流,主动识别架构风险。
Claude Code + Codex harness engineering — scaffold, upgrade, and run opinionated agent harnesses with deterministic hooks, evidence-backed review pipelines, and an autonomous multi-seat org runtime.
为 Codex Desktop / CLI 配置 GPT-6.1 Sol + GPT-6 Luna 子代理:按任务选档,支持可回滚安装与升级。
Switch between multiple Codex accounts without signing out. No server-side revocation, no browser re-authentication.
A Cockpit plugin that turns the web console into a full file manager — browse, edit, preview, search, terminals, and Git — with integrated Claude & Codex AI CLI tabs showing a live git diff, plus fstab/mounts, SMB & NFS shares, and a GRUB editor.
A Codex plugin for choosing subagent models, letting them finish, and checking their work.
Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.
桌面悬浮会话窗:一眼看见 Codex、WorkBuddy、CodeBuddy、Codeg 的运行 / 待确认 / 完成状态,点击跳回原会话。
LLM quota monitor plugin for the DeepSeek Harness web GUI: breathing indicator, rolling / weekly / monthly usage panel · by Xu Yuanshan
Your coding agents, in your pocket. Control Claude Code, Codex, Cursor or any ACP agent on your computer from your phone. End-to-end encrypted, self-hostable relay.
🤖 零报错在 Windows 10/11 安装 OpenAI 官方 ChatGPT / Codex 桌面客户端的 AI Skill & PowerShell 自动化脚本。OpenAI 官方 CDN 直链下载、跳过微软商店卡死、彻底解决 0x80070005 / 0x80073CF9 报错与双击闪退。
pi 扩展包:多 agent 协作(Board/spawn/storm/physarum)+ 分层长期知识 + runtime 强制工程纪律 · A pi extension: multi-agent collaboration, tiered knowledge, engineering discipline — runtime-agnostic core
Automatic model routing + live agent dashboard for Claude Code. Haiku for lookups, Sonnet for daily work, Opus to orchestrate - watch every agent, model and dollar in real time.
The Axis Workflow - a simple, disciplined way to run real projects with AI. A folder of markdown files your Agent follows: plan, delegate, remember between sessions, verify the work. Portable across Cowork, Claude Code, Codex, Cursor, and Gemini CLI.
A Codex Agent Skill for long-horizon reasoning, context synthesis, root-cause persistence, verification, and completion discipline.
Several AI coding agents (Claude, Codex, Gemini, Copilot, Cursor) in one room inside VS Code, with rooms, DMs and project guardrails.
Two-level coordination and auditing skill for OpenCode agents and sessions
Source-only Linux packaging for OpenAI Codex Desktop — local DEB, AppImage, and Wayland builds
Current Codex instructions, 39 engineering skills, and portable settings with Windows and Linux installers.
Reusable skills and plugins for AI agents: development workflows, writing, and automation.
the best all-in-one mod pack for Claude Code
A native macOS and Windows heads-up display for every Claude Code session: live status, costs, rate-limit forecasts, and permission answers from the edge of your screen.
A Claude mod for Claude Desktop and Claude Code: switch Claude accounts in place, see live usage per account, and auto switch to the account whose weekly quota runs out first.
GLM (Zhipu/Z.ai) as a cheap, full-capability subagent for the Claude Code app — works on a subscription Claude (no API key for the main agent), auto-routes between Opus and GLM, file-editing agent with diff/dry-run/git-revert, one-command npx install.
A simple and reliable auto account switcher for Claude Code: rotates to a fresh account before the 5-hour or weekly rate limit hits, so no pane ever stops at the usage quota. A Herdr plugin.
Reverse-Engineered Claude Code Remote Control / Sessions API
iCline - Cline fork with xAI Grok OAuth & Subscription, ZenMux, safe dual-channel updates, and hardened agent harness.
catnap: Claude naps at a clean break, not mid-task. A Claude Code mod that lets Claude compact its own conversation and carry on by itself.
A local Windows account switcher for Codex Desktop with encrypted profiles, safe manual switching, quota snapshots, bilingual UI, and multiple themes.
Context pre-loader and workspace manager for AI coding agents.
GenPark AI Agent Skill - Deterministic conversation turn archiver and session ledger with automated Git indexing and clean Markdown export.
Fast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
Agent Exchange: local messaging between Claude Code, Codex, Grok Build, Pi and OpenCode. CLI: ax.
Claude Code skill: working habits to get the most out of Claude Opus 5.5 in development
Will your code survive the bump to Claude Opus 5.5? Catch breaking changes in code, deps, and what your framework actually sends. No API key.
Advisor Strategy skill for AI coding agents, spawns a stronger model as strategic advisor for architecture, security, debugging, and performance. Works with Claude Code, Cursor, Gemini CLI, Cline, Codex, and more.
SpecAgent Pro Template: a project template, not a plugin. Special agents for hard multi-package software: every role a full Claude Code session run by a manager chat, not a subagent; gates in code, proof for every finding, one unit per session, cost measured per role. A private vault per user, one p
DeepSeek Harness(DSH)插件:对话内右键 Agent 文件,预览图片和视频缩略图,打开、定位、复制路径与引用。
Let Claude work while you play with the cats. Approve or reject Claude Code commands from your Apple Watch, iPhone, or Android — from anywhere, with a single tap.
Claude Code plugin for Ruby, Rails, Grape, PostgreSQL, Redis, and Sidekiq development
Parzival Oversight Agent - Technical PM & Quality Gatekeeper for Claude Code multi-agent projects. Oversight templates, session management, and verification workflows.
Agent harness for Claude Code — one screen for all your sessions, across all your machines.
The cockpit for operators running AI at scale. Local-first Discord-style dashboard for Claude Code sessions across many projects.
LLM-generated voice notifications for Claude Code, Cursor, OpenAI Codex, pi, and OpenClaw, spoken by game characters like the StarCraft Adjutant, Kerrigan, C&C EVA, SHODAN, and more.
Generate a complete project rules system for GitHub Copilot, Cursor, OpenAI Codex, and any AI coding agent — instructions, prompts, rules, skills, task tracking, documentation scaffolding, and observation logs — from a single prompt.
A Codex skill that forces Claude to plan first (PRD, specs, 30-500 question requirements interview) before Codex writes code. Two-stage AI coding workflow on top of Trellis. Bilingual EN/ZH.
Extend Claude Code to remote machines, containers, and servers via WebSocket. Read, write, and manage files anywhere.
Comprehensive toolkit extending Claude Code with 70+ slash commands, specialized AI agents, and automation workflows. Features hybrid parallel-scanning architecture, intelligent problem routing, and automated code quality improvements. One-command pipelines for security audits, performance optimization, and refactoring.
Claude Code plugins for spec-driven development workflows: SPECLAN integration, BMAD-METHOD interop, and SDD automation skills.
Stop prompting your editor from scratch. Cursor rules built for AI engineers.
Lint and optimize your CLAUDE.md / AGENTS.md — find dead rules, token waste, and structural issues. One command, one score, one report.
10 AI agents with persistent memory, professional knowledge, and file-based coordination. Built for Claude Code.
Official collection of Descope authentication skills for AI coding agents
Personal OpenCode configuration featuring custom agents, skills, and commands to streamline AI-assisted coding and repository analysis.
MINTORAIN 바이브코딩 - Claude Code 팀 에이전트 tmux 5분할 자동화 키트
I run a 4-person startup and code part-time. This .claude folder is how I turn 4 hours into 40. 6 AI agents that write code, review PRs, plan sprints, auto-merge, take screenshots, and watch logs. Each one has rules about what it's banned from doing.
Combine agents, vibe coding, custom tools, and desktop apps to create a privacy-first Analyst AI using Claude Code and Amazon Bedrock
AIM — a structured operating method for AI-assisted software delivery. Clear roles, hard gates, done increments that ship. Works with GitHub Copilot, Claude Code, and Codex.
Custom modes for AI agents
TAS: Tracking, Automation, and Skills - An operational harness for Claude Code. Session tracking, token budgeting, slash-command skills, and maintenance cadence.
Stay informed about your Claude Code sessions with real-time Discord notifications - know what Claude is working on even when you're away from your computer
Neovim plugin for Cursor Agent CLI integration
🌟 A Visual Studio Code extension that displays the count of OpenAI GPT-3 tokens for the current document in the status bar. 🎯
A structured Claude Code workspace template with /prime, /create-plan, and /implement commands for persistent AI-assisted workflows
Open-source library of AI superpowers — 59 skills, 34 commands, 10 agents + 24 GSD subagents, 3 system bundles. An entire team, wherever your AI lives. Vendor-neutral across Claude Code, Cursor, Codex, and any AGENTS.md tool.
Your agent docs lie. Nerviq finds the lies in 30 seconds — stale references, permission exposure, and cross-platform drift in CLAUDE.md / AGENTS.md / Cursor rules. Deterministic, zero dependencies, MIT.
Claude Code plugin to spawn and manage autonomous background agents with persistent state, worktree isolation, and auto-completion hooks
Plan card interaction enhancement plugin for OpenCode
Agent Skill for creating and maintaining TYPO3 extension documentation | Claude Code compatible
itdog.cn 网络测速工具 - Clawdbot Skill | Batch Ping / HTTP 测速 / 全国多节点
Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests. Zero core deps.
Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills, 26 agents, quality gates, knowledge store, adversarial review, content writing & optimization.
Bolt-on agentic team layer for Claude Code (claude-code-plugins / claude-code-subagents) — Plane × Mattermost × TDD × Design × DB × Ratatui Monitor. Single Rust binary, MCP-friendly, en/ko.
Modular skills for AI coding agents.
A Neovim plugin for seamless integration with AI CLIs (Claude, Copilot, OpenCode, etc.) using tmux.
Native macOS menu bar app for Claude Code — unifies notifications, permission prompts, and hook events from all sessions in one place. Free & open source.
Autonomous spec-driven development plugin for Claude Code. Describe a feature, get merged, tested, reviewed code. Full pipeline from PRD to PR with dependency-aware task tracking, AI code review, and zero dependencies beyond bash + jq.
Claude Code + Google Antigravity için A-Z rehber (TR + EN). Slash komutlar, MCP, skills, hooks, subagents, plugins, MVP playbook ve hazır örnekler tek repoda.
Rode o Claude Code enquanto você dorme. Spec-driven development com modo autopilot: planeja, constrói, valida (segurança, qualidade, testes) e comita fase por fase sozinho — pausa ao bater o limite do plano e retoma no reset. Acorde com a feature pronta. Agnóstica de stack. PT-BR.
A completion-claim gate for Claude Code. Refuses to let the agent say done without evidence.
Claude Code on your Apple Watch. Send prompts, build apps, review diffs — all from your wrist.
Catppuccin Frappe status line for Claude Code showing model, git branch, context usage and session cost.
Native macOS menu bar app showing Claude usage limits (Swift)
Claude Code and Codex hooks kit for verification loops: file protection, post-edit lint, and stop-time checks
Personally curated and maintained collection of Claude Code plugins
nv:context > Context engineering for engineers who ship. Auto-detects, analyzes, generates configs, hooks, session management, and token budgets. 200+ research sources.
Self-evolve Gemini CLI instructions, commands, and skills via the gemini CLI itself — GA + GEPA/DSPy, with hard gates before apply.
The Universal App Store for AI Agents. Discover & Install Skills for Claude Code, Cursor, Windsurf, Aider, Codex & Gemini.
Long Long Run (LLR) is a plug-and-play Codex skill for serious long-running agent tasks: an agent-first harness runtime with INC intent-noise cancellation, ACTIVE durable mainlines, side-thread tolerance, and Codex hook-enforced stop guards.