Coding agents & developer tools

Claude Code, Codex & Cursor extensions

8,960 agents · most starred first

Claude Code, Codex & Cursor extensions, page 62 of 90

kit-vibecoding-pro★ 5

🤖The tools, prompts and method for coding with AI agents in Claude Code — from idea to verified project. EN / ES

ai-development-methodology★ 5

Markdown + git methodology for human and AI software teams: planning, Definition of Done, coordination, handoffs, and verification. Fourteen docs and templates. CC BY 4.0.

ux-flow-skills★ 5

Proven UX flows, user journeys, and app layout patterns packaged as agent skills for Claude Code, Codex, Gemini CLI, and any coding agent

tabby★ 5

Every Claude Code tab, at a glance, and Claude keeps working with the lid closed. AI tab names, calm colors and live status for each session; a macOS island (or menu bar) with Focus mode, tiling, history and stale-process cleanup. Install by asking Claude.

Marvin★ 5

One AGENTS.md, N thin adapters, memory versioned inside the repo. Zero-dependency scaffold for working with AI coding agents.

oeconomia★ 5

A Claude Code skill for orchestrator context economy: what the main session keeps, what it delegates to subagents, and how returned work is verified.

meta-architect★ 5

Meta-Architect (MA) is a workflow layer that adds architecture, evidence, and release-gate discipline on top of Codex, MCP, and other 55+ AI coding agents — without replacing them.

squadjs-plugin-creator-skill★ 5

Creating, writing, or scaffolding a SquadJS plugin, adding a server-side feature to a Squad server via SquadJS, or deciding whether SquadJS can support a desired behaviour

wardlume★ 5

Lock your Mac keyboard & mouse, keep the screen visible — botsit your AI agents (Claude Code, Codex, Cursor) while you step away. Touch ID & Apple Watch unlock.

DSH-Store★ 5

DSH STORE — third-party plugin marketplace and guarded lifecycle manager for DeepSeek Harness.

our-codex★ 5

From each .claude/, to each AGENTS.md — bridge Claude Code skills/agents to OpenAI Codex

plan★ 5

A control plane for trustworthy AI agents: write product judgment once, then enforce it through typed MCP tools, git gates, demolition-first stories, evidence-judged checkboxes, and zero-trust monitoring. Ships with Claude Code and Cursor plugins, Agent Skills, and a FastMCP server.

agent-skills★ 5

Shareable skills for clankers

Sdlc-ai-workflow★ 5

Claude Code plugin for end-to-end SDLC automation with role-specific agents, reusable skills, and production workflows.

vsm-harness-skills★ 5

Reusable methods, skills, and procedures for analyzing, designing, and evolving VSM-based agent harnesses.

skill-sync★ 5

❯ Open-source desktop app to sync Claude Code, Codex, and AI agent skills across computers through a private GitHub repository.

agent-manor★ 5

Local-first, privacy-focused workspace for coding agents: session history, knowledge, code activity replay, usage insights, and Skills & MCP management.

Claude-Code-Helper★ 5

🐝 Batteries-included Claude Code starter kit by HIVE AI — 114 skills, 30 agents, 56 commands, hooks, cheatsheet and configs from a heavily-customized production setup

agent-session-titles★ 5

一条命令为 Codex 与 Claude Code 安装三段式会话标题插件

claude★ 5

Anatomy of the .claude/ folder Claude Code configuration reference

claude-local-agents★ 5

Claude Code skill that delegates large reads and code writing to local models (Ollama) to save Claude tokens - with automatic checks, sandboxing and escalation. Never the cloud.

minimalist-entrepreneur★ 5

Sahil Lavingia's The Minimalist Entrepreneur as universal Agent Skills — the Claude Code startup playbook, freed to run in Cursor, Copilot, Windsurf, Zed + 68 more. One-command install.

vibectl★ 5

Manage all your agentic engineering projects (i.e., vibe coding) for Claude Code in one place. Orchestrate, deploy, manage github, and coordinate issues and feedback into your workflow.

my-agentic-skills★ 5

Collection of my current agentic skills that I've collected and used for my personal or team project.

claude-agentic-os★ 5

Claude Agentic OS: portable Claude Code setup — global rules, plugin set, per-project memory, statusline and launcher, installed by one script.

Tia-Portal-CLI★ 5

Tia Portal AI. AI PLC programming and headless TIA Portal automation. Let an AI agent program for you — 346+ CLI verbs over the Siemens Openness API, JSON in and out, dry-run by default. Offline and on-premise, no cloud copilot. S7-1500, S7-1200, SCL, ladder logic, SimaticML, SINAMICS, WinCC. Claude Code, Codex, Cursor skill.

MOAA★ 5

MOAA: Memory, Orchestration, Agents, Automation. One-command Claude Code setup: Strata layered memory with meaning search and context handoff, cache and context meters, a 60-role Specialist Council, Agent Arena with forging, War Room teams, Allies (Codex, Gemini, OpenCode), plugins, skills, MCP servers

claude-codex-journal★ 5

Peer collaboration for Claude + Codex — two memory-isolated agents co-author one shared daily journal. Not handoff.

ef-harness★ 5

Spec-driven development harness for AI coding agents. Grill the decisions, write the RFC/PRD, check every spec claim against the real code, build against named proofs, then pass one adversarial audit. Specs stay up to date with what shipped. Claude Code & omp plugin, any language.

codex-swap★ 5

Multi-account switcher for the OpenAI Codex CLI: safe switching, live usage dashboard, parallel sessions, auto-rotation before rate limits

codex-auto-retry★ 5

Automatically resume Codex tasks after recoverable provider failures, with a global Windows watchdog and embedded management panel.

codex-titlebar-meter★ 5

Live Codex quota in the title bar — 标题栏实时显示 Codex 剩余额度

claude-code-image-generation★ 5

Claude Code image generation skill: generate & edit images with GPT Image 2 (gpt-image-2) from Claude Code via Codex CLI on your ChatGPT subscription. No OpenAI API key. One-line install.

subswap★ 5

Check quota and switch Claude Code, Codex, Kimi Code, Cursor, OpenCode, and Command Code accounts without signing in again for each change.

convene★ 5

Run Claude Code headlessly as a local inference layer: named experts, multi-turn sessions, measured concurrency. Local and first-party only: no proxy, no network endpoint.

claude-accounts★ 5

Switch between multiple Claude Code logins in a single ~/.claude — no browser re-login. Arrow-key selector, cross-platform, EN/PT-BR.

shoga-speaks★ 5

🦜 Claude Code plugin that explains everything in your language, script and role: Roman-Urdu, Urdu, Hinglish, Hindi, Dutch. Plain-language approvals, failure explanations, quality checks.

eplan-scripting-skill★ 5

Agent skills for EPLAN Electric P8 and EEC Pro development: C# scripting, the EPLAN API and Remote Client automation. Works with Claude Code, Codex, Cursor and 60+ agents.

skills★ 5

Edge finds task-fit agent skills, shows available evidence, and loads pinned versions into AI agents.

tmux-claude-status-tabs★ 5

Every Claude Code session's state, live in your tmux tab bar — animated, event-driven, zero polling

better-skill-creator★ 5

Build Claude Code skills that trigger correctly — multi-angle design analysis, adversarial review, six quality gates, and a measured description optimizer.

forkoff-react-native★ 5

ForkOff mobile app: monitor, approve, and control Claude Code sessions from your phone. Real-time AI session monitoring with end-to-end encryption. iOS and Android.

claude-code-skills★ 5
claude-usage-mod★ 5

A pixel Clawd above your Claude Code prompt that shows your context, 5-hour and weekly limits, and gets nervous as you near them.

clawd-pet★ 5

Clawd lives above your prompt in Claude Code. A pet mod that reacts to what Claude is doing 🧡

claude-code-usage-limits★ 5

Claude Code usage limits, shown to Claude: every reply opens with what the remaining budget fits.

dojo★ 5

Claude Code plugin marketplace: Kaizen (Addy Osmani's agent-skills + hooks that block), Motion Studio (motion design as code → MP4/GIF) and Slide Studio (HTML decks → PDF).

OPM★ 5

Claude Code plugin: brainstorm → plan → TDD with subagents → verified done. Fewer tokens, no fake 'tests pass'.

boox-standby-token-usage★ 5

Show your Claude Code token usage on a BOOX e-ink tablet's standby screen (macOS)

nextcost★ 5

See what your next Claude Code message costs: a live band above the prompt with the prompt-cache countdown, the re-warm price, session cost, context and 5h/weekly usage limits.

claude-profiles-windows★ 5

Windows tray app for anyone juggling multiple Claude Code accounts: see every account's 5h/7d usage at a glance, switch in one click, or open a terminal bound to any of them. Local-only, built on claude-swap.

agent-skills-collection★ 5

204+ curated agent skills across 15 dev workflow categories. Multi-tool ready (Claude Code, Codex). Bilingual EN/CN. Sourced from 17 official + community repos.

claude-founder-os★ 5

An operating system for solo founders running a real business on Claude Code: persistent agent memory architecture with a recency gate, a five-gate verification loop, honesty gates for AI-generated content, and a durable skills framework. Templates + docs to make Claude a reliable AI co-founder.

comment-checker★ 5

Fast, offline Claude Code hook that flags unnecessary code comments and AI slop via Tree-sitter AST analysis across 37 languages.

agent-skills★ 5

Skills for Claude Code and Codex: durable goal loops, parallel review, research, investigation and implementation, and research grounded in your own knowledge base

product-lifecycle-templates★ 5

Best-in-class, agent-ready product-lifecycle document templates. Every type ships as a researched, cited, gate-enforced bundle (blank shape, companion, guide, worked example, machine metadata), not just a blank file.

agenttiles★ 5

Mission control for Claude Code: every running session on one screen. Approve, answer and jump to the right terminal.

laya-router-skill★ 5

Cross-platform Laya decision routing skill for Codex, Claude Code, OpenCode, Pi and other Agent Skills compatible agents.

ask-codebuddy★ 5

Agent skill: delegate scoped coding tasks to your local CodeBuddy CLI | 把边界清晰的任务交给本机 CodeBuddy CLI

agent-user-interaction★ 5

skill + plugins that let AI agents render HTML interaction pages and collect structured user input from the browser.

ads-agent-bridge★ 5

Let AI agents safely understand and operate the exact Keysight ADS context you selected.

contextOS★ 5

Task-aware AGENTS.md context injection and compliance reports for Codex, Claude Code, and Antigravity.

xl-ai-language★ 5

任务架构通用智能体能力包 ·

agy-foreman★ 5

Hand plan tasks from Claude Code to Gemini 3.8 Flash through the Antigravity CLI, and merge only what passes your tests.

thread★ 5

A local board for Claude Code: Claude records tasks and asks its questions and reviews on cards, you answer them together, and work with acceptance criteria is not marked done until you approve. Sub-agent runs, side threads and Codex, OpenCode or Claude lane work show live on their cards.

headroom-skill★ 5

Portable token-reduction skill for any coding agent (Claude Code, Codex, Cursor, Aider, Claw, Hermes, Goose, Continue, OpenHands, vibe, Copilot CLI). Distilled from chopratejas/headroom. Drop-in agent rules + pure-Python helpers. 60-95% fewer tokens, no proxy required.

hapimatic-core★ 5

The open-source core of Hapimatic: reach and resume your Claude Code, Codex, Gemini, or OpenCode sessions from any browser or PWA, served from your own machine. | Solid PD | Philadelphia, PA

superstacks★ 5

Lean MIT skill stack for coding agents: plans, TDD, verify-loop, constraints, review, PRs, and ticket pipelines.

bug-solver-pro★ 5

An agent skill to diagnose and fix software bugs across languages and frameworks using root cause analysis, targeted fixes, and regression checks. Install with npx skills for Claude Code, Codex, GitHub Copilot CLI, OpenClaw, Hermes Agent, and more

riqor★ 5

Evidence gates and session continuity for AI coding agents

dsh-workspace-hygiene★ 5

DeepSeek Harness plugin for agent workspace hygiene: artifact value assessment, metadata indexing, and auditable cleanup.

rness★ 5

One source of truth for every AI coding agent. The standards, decisions, specs and plans of your organization, written into the AGENTS.md of every repository. Claude Code, Codex, Cursor and GitHub Copilot already read it.

3d-claude-hub-remote★ 5

A 3D office that mirrors your Claude Code sessions; prompt, approve and follow them from any device over Tailscale.

arcdr★ 5

herdr mobile & web client that shows what your Claude Code mods report — answer your agents from your phone, over your own Tailscale

shipkit★ 5

Claude Code skills to build a SaaS or ecommerce in Argentina: spec-driven dev, test-first debugging, security audits, safe migrations, UI checks, plus ARCA, Rebill, Mercado Pago and Correo Argentino.

rowel★ 5

Native iOS client for DeepSeek Harness (dsh). Answer your agent from your phone — the relay only ever sees ciphertext.

nd-skills★ 5

Diagnosis-free neurodivergent support skills for AI coding agents, with executive-function scaffolds and always-on Claude/Codex behaviors.

create-research-experiment-repo★ 5

Codex skill for approval-led experiment repositories: connect reports, configurations, raw evidence, and review decisions for delegated research.

codex-claude-desktop-bridge★ 5

Local two-way messaging between Codex Desktop and Claude Desktop Code on Windows.

countersign★ 5

Native macOS approval panel for every Claude Code, Codex, Cursor and Antigravity session.

trellis★ 5

The structure a project grows on: a free starter template for AI-assisted development. One AGENTS.md every tool reads (Claude Code, Cursor, Grok Build, Codex, Gemini CLI, Copilot), TDD + bug-fix methodology, secret guardrails, optional local knowledge base. Built for founders new to vibe-coding.

dev-skills★ 5

Engineering-discipline skills for AI coding agents — /think, /tdd, /review, /debug as composable skill documents. Skill-spec compliant, no runtime: the documents are the product.

agentic-dev-kit-for-codex★ 5

GitHub-native development workflows for Codex, with reusable Skills, durable Issue/PR records, and human oversight.

agent-jobs★ 5

Agent Jobs: your main Claude Code session talks, decides and checks; everything longer than a few steps runs as a background claude -p job – own worktree, hard limits, guarded, one-line result. Cheaper context, free session.

My-Programming-Workflow★ 5

A governance and operating system for AI coding agents — controlling execution, context, verification, evidence, and project memory.

scaffold-stellar-agentic★ 5

De idea a dApp con prompts: Scaffold Stellar + escrows de Trustless Work + login con correo/Google (Cavos) + skills para cualquier agente (Claude Code, Codex, Cursor, OpenCode, Copilot, Gemini…)

SFP★ 5

Stop burning 41% of your agent's context on unused skills (96% saved). 1,065 curated skills across 24 categories, 121 bundles, and 20 AI coding tools. One local hive equipping the exact 1-3 skills you need in 3ms with 0.0% junk and adaptive taste.

ai-profile-switch★ 5

Profile switching for AI coding CLIs, starting with Claude Code — switch between work, personal, and other accounts instantly

endfield-design-skill★ 5

面向 Claude Code / Codex 的设计 Skill:把《明日方舟:终末地》的视觉语言提炼成可判断、可验证的设计方法

claude-artifact-cli★ 5

Publish, update, list and inspect Claude Artifacts from the terminal using your existing Claude Code login. Zero dependencies, scriptable, CI-friendly, ships with an agent skill.

plugins★ 5

Claude Code plugin marketplace from ogxo: cost-aware agent routing with a live board, multi-agent code review, git and PR workflows, browser debugging, guard hooks, a status line, and ThryX. The same plugins install in Grok Build.

Claude-consciousness-skills★ 5

Research-backed Claude Skills for structured thinking — consciousness-council, dhdna-profiler, what-if-oracle

fact-drift★ 5

A Claude Code skill that watches the source pages behind the facts you cite (prices, versions, limits, rules, deadlines) and updates every file that has gone out of date, once you approve.

devkeel★ 5

DevKeel 为现有项目建立 AI Agent 能读懂、会执行、可验证的工程环境:CLI 初始化跨平台协作入口,项目知识、Skills 与验证方式随代码沉淀。

halny-vibe-deck★ 5

Halny Vibe Deck — unofficial desktop client for the Mistral Vibe coding agent (formerly Mistral Vibe Nexus)

dsh-intellij-integration★ 5

DeepSeek Harness (DSH) for JetBrains IDEs — AI coding with native diffs, tool approvals, sessions, Trace analysis, and balance tracking. | IntelliJ IDEA / PyCharm AI 编程助手:原生 Diff、工具审批、会话与 Trace 分析。

tapin★ 5

An inbox for your AI coding agents. Approve, jump, done.

one-agent-harness★ 5

Universal Cross-Agent Context Bridge uniting Claude Code, Antigravity, OpenAI Codex, and Grok Build CLI across Linux, macOS, and Windows.

claujev★ 5

Jev (TypeSafe AI) as a second pair of eyes for Claude Code: request triage, automatic effort, command guard, rule review and a final check. Claude Code plugin, zero dependencies.

reverse-engineer-black★ 5

Metodo completo de engenharia reversa para agentes de IA: 2 kits (app local e SaaS thin-client), 12 fases, portao de validacao proprio e o gate SEM-TRAVA que impede o agente de parar no meio. Instala em Claude Code, Codex, Hermes ou qualquer chat com shell. MIT

More in Coding agents & developer tools