Coding agents & developer tools

Claude Code, Codex & Cursor extensions

8,960 agents · most starred first

Claude Code, Codex & Cursor extensions, page 88 of 90

@cronus-ui/ai-kit

The Cronus UI AI Kit — an engineering doctrine, skills, and per-assistant config, scaffolded into your project.

life-ai-enhancer

+30–50% higher Copilot acceptance rate. 291+ installs, 297% Marketplace conversion rate. Neuroadaptive optimisation layer for GitHub Copilot, OpenAI, Claude, Gemini & Cursor — auto-activates instantly, no API key needed. Self-learns from your accept/rejec

@gtrabanco/pi-agentic-workflow

Pi package: canonical agentic-workflow skills, friendly slash commands, and per-command model routing.

@propermotion/virgo-cli

Independently agentic, CLI-first Virgo repository setup

agentic-discipline-kit

Evidence-backed engineering controls for AI coding agents.

agentmeld

One AI context, every agent. One source of truth for instructions, rules, skills, agents, commands and MCP config, mirrored into every AI coding tool, with per-tool overlays for what genuinely differs.

claude-deadweight

Find the parts of your Claude Code setup that cost context on every session and never do any work.

mk-agent-harness-kit

Portable contracts and loop gates for AI coding agents

pydantic-claude-code

Use your Claude Code subscription from a Pydantic AI Agent or CLAI2, with full tool support

animotion-skills

Install AnimotionJS AI agent skills directly into Copilot, Cursor, Claude, Windsurf, and more

personal-skills

Install personal AI agent skills from a private GitHub repository

@yhong91/vibetime

vibetime CLI — install AI-agent hooks (Claude Code, Codex, OpenCode, Pi, Cursor) and report activity to vibetime.

@agentfile/cli

Find what is wrong with the AI agent configuration your repository already has — doctor, check, lint, audit, adopt, compile, eval

@tidyfactor/cli

TidyFactor — Universal Architecture Ecosystem & Multi-Platform CLI for AI Agent Skills

@d.qanglap/agent-kit

Initialize or update a project with markdown AI Agent instructions, workflows, and config.

@ask-llm/plugin

Ask LLM review, comparison, brainstorming, image, verification, and pairing workflows for Claude Code, Cursor Agent, and Pi

@geohar/un-bien

Mobile remote control and local agent mesh for the Pi coding agent. Pair your phone via QR over a relay, watch tool calls in real time, run multi-Pi sessions over a local Unix Domain Socket broker, and let agents talk to each other through structured requ

@post-print/agent-harness

Configured coding agents and isolated Cursor, Claude Code, and OpenAI Codex sessions

@yottameta/yotta-skills-plugin

YuanGe (元阁) — orchestration and routing for the YottaMeta skill family, packaged as a YottaMeta Agent Plugin and DeepSeek Harness profile bundle.

@emmaneugene/pi-cursor-sdk

pi provider extension backed by @cursor/sdk local agents

usebeeline

Connect an AI coding agent to Beeline with one command.

pi-extension-nvidia-nim

Model-aware NVIDIA NIM reasoning compatibility for the pi coding agent

pi-blitz-handoff

This extension is designed for one purpose: to capture a session’s continuation context more precisely than compaction and pass it to a fresh, natively linked Pi session as the first prompt that starts the replacement. How work continues is determined by

@esso0428/pi-subagents

A pi extension that brings smart Claude Code-style autonomous sub-agents to pi, with npm:pi-subagents-style JSON agent overrides.

@goodandready/dsh-goal

Core Goal Addon (Token Budget, Milestones, Git Snapshots & Retrospective Reports) for DeepSeek Harness

ornn-forge

Portable skill library, knowledge base and deterministic tooling for AI coding agents.

@ai-sdk/harness-cursor

AI SDK harness adapter for Cursor

@simmalugnt-se/payload-editor-assistant

Context-aware editor assistant plugin for Payload Admin

@ai-sdk/harness-fx

AI SDK harness adapter for FX

opencode-gitlab-auth

GitLab OAuth authentication plugin for OpenCode

opencode-qoder-bridge

Qoder provider plugin for OpenCode powered by the official Qoder Agent SDK, with streaming, tools, MCP, sessions, multimodal input, and quota tracking.

@wnzzer/agentdock-linux-arm64

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

@wnzzer/agentdock-linux-x64

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

@wnzzer/agentdock-darwin-arm64

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

@wnzzer/agentdock-darwin-x64

Remote multi-agent development workspace for the official Claude Code and Codex CLIs

@darkmagicstudios/hocus

A multi-agent harness generator: one persona spec (SOUL.md) compiled into Claude Code, OpenCode, Cursor, and Antigravity native agent/rule formats.

goatcode-sh

Enterprise-grade OpenCode plugin with micro-plugin architecture, multi-agent orchestration, and professional naming

@jasonfreelab/dsh-superpowers

A DSH port of obra/superpowers — the full multi-agent software-development methodology (TDD, planning, debugging, review) as native DSH skills

adaptive-director-skill

Adaptive Director Skill — Skill-first adaptive multi-agent orchestration for AI coding agents

@dongfanglin/openspec-agentic

OpenSpec agentic workflow extension: schema, role models, installation and migration.

@rudevich/agentic-flow

Scaffolds an agentic/ directory (skills, agents, hooks, tasks) with .claude and CLAUDE.md symlinks, and seeds a ticket-to-subtasks pipeline

update-agentic-workspace

One command to bring an installed Agentic Foundry workspace current: refresh the plugin marketplace (migrating a pre-v1.7.0 tag-pinned registration if found), update the plugin in every scope that enables it, and re-run the workspace + permission-floor re

@execuro-sw-ecosystem/sw-ecosystem-agentic-harness

Shopware 6 agentic harness: sw-* skills and sub-agents, plus an installer that writes them into Claude Code, Codex, GitHub Copilot and Cursor.

abstract-gpt

Codex session manager: login, launch, rollover, and a shared web console via abstract-serve-core.

agent-loop-tool

Checkpoint-gated developer/reviewer loop across Claude Code, Codex, Grok, and Antigravity CLIs.

agent-marketplace-versioner

Keep agent plugin and marketplace versions in sync.

agent-sdlc

Diff-scoped mutation gate for pre-commit and agent Stop hooks

agent-session-relay

Git staging as the human review surface for collaborative agent sessions

agent-sessions-cli

Share coding-agent sessions (Claude Code, Codex CLI, OpenCode, Gemini CLI) with your team through git.

agent-skill-sync

Scan, classify and sync AI-agent skills (SKILL.md) across toolchains like OpenAI Codex, Claude Code and WorkBuddy.

agent-statusline

A dense, width-aware status line for coding agents

agent-sync-sh

Canonical configs, fanned out to all your AI coding agents from the Commons, the canonical ~/.agents directory

agent-yadogae

Move a project directory and take its Claude Code, Codex and Antigravity CLI history with it.

agentbus-cli

Cross-session messaging between coding agents on the same machine (Claude Code, pi, opencode, kiro, codex, antigravity, hermes, and any MCP host).

agenthud

Cross-tool agent session HUD for Cursor, OpenCode, Freebuff, Codex, and more

agentic-workspace

Persistent operating context and dynamic control for coding agents.

agentic_init

Bootstrap any repository with a lean, best-practice agentic development setup for Claude Code.

agents-md-gen

Generate a solid AGENTS.md / CLAUDE.md for any repo by detecting its stack, commands, and structure

agents-tool

CLI tool for managing AI agents, skills and harness

agentstreamdeck

Local AI coding-agent status, alerts and focus for Stream Deck Mini, MK.2 and XL

agenttaskflow

Persistent task workflows inside your existing Claude Code or Codex session (placeholder, coming soon)

canopy-agent-factory

Stamp out a new Claude Code agent from the canopy operating model — a self-contained, zero-runtime-dependency factory. Pip-installable into canopy / canopy-web / any second consumer.

ccagent

Reserved name. No functionality is provided by this distribution.

ccagentkernel

Reserved name. No functionality is provided by this distribution.

claude-auth-manager

Switch Claude subscriptions and API-provider keys from Claude Code

claude-calc

Price your Claude Code session logs and view the spend in a local dashboard

claude-code-statusline-designer

Design, preview and install a themed statusline for Claude Code

claude-fleet

One local page showing every Claude Code session on your machine, and where they overwrite each other's memory

claude-kiosk

Local kiosk display for Claude usage and system resource stats.

claude-orc

A personal control plane for a Claude Code setup that spans multiple accounts and machines — memory sync, skill registry, usage reporting, and a terminal dashboard.

claude-pace

Pace your Claude plan limits across the week: daily budget, 5-hour and weekly meters, sessions per week.

claude-usage-dashboard

Local dashboard for Claude Code usage: hours, tokens, project split, and a weekly-limit gauge calibrated from your own /usage readings

claudeglass

Are you using Claude Code well? Finds the habits and settings that waste tokens, from the transcripts on your machine.

claudenator

Hasta la vista, Claude sessions!

claudewatch-usage

Live Claude Code rate-limit view for the ClaudeWatch GNOME Shell extension

claudexer

Browse, resume, and export Codex and Claude Code sessions with a Textual picker

deltachat-claude-code

Access Claude Code from your phone — full CLI sessions over Delta Chat

gpt-oss-azure-opencode-shim

Compatibility shim that fixes silent API failures when using Azure-hosted GPT-OSS models with OpenCode.

maat16-agentlint

Design-rule governance for agent projects: skills, CLAUDE.md, MCP configuration and each project's own rules, with levels, exemptions and reports for CI.

multi-agent-prompt

A crash-proof, autosaving prompt editor for AI coding agent CLIs — compose in your real editor, hand off with a slash command

pyclaudecli

Python library wrapping the Claude Code CLI: prompts, background agents, auth, MCP, plugins, and more

skillmeld

Discover existing community skills and merge the best into one tailored, security-scanned skill set.

tack-agents

Keep your agent skills deployed identically to Claude Code and Codex from one manifest, and audit projects so either agent sees the same instructions, skills and hooks.

@explyt/acp-adapter

ACP adapter for the Explyt AI Agent (derived from pi-acp)

@platform-kit-next/cli

Platform Kit - AI-Agent Rules and Skills for Software Projects

@meyverick/agentic

AI agent skills and prompts for pi.dev

major-ai-skills

Installable agentic skills / AI agent skills (SKILL.md) for Claude Code, Cursor, Codex CLI, Gemini CLI & Antigravity - 412+ professional app, token-efficiency, and common-sense skills. SEO/GEO ready.

skl-x

Audit and manage AI agent skills for Claude Code and Codex

@veai-ru/acp-adapter

ACP adapter for the Veai AI Agent (derived from pi-acp)

ai-agent-bell

AI Agent Bell: a loud alarm when your AI coding agent finishes, fails, or needs your input. Works with OpenCode, Claude Code, Codex CLI and any terminal tool. Global-only: zero project impact, never ships in your build. Local-only: no network, no usage tr

cortex-agent

AI Agent Governance Framework for Cursor, Claude Code, Windsurf, Gemini CLI, and Antigravity

getprimer

Install once. Every AI agent knows your project — Cursor, Claude Code, Windsurf, Aider, Goose. Zero config.

0bridge

One bridge for all your AI agent tooling — MCP servers, skills, and AGENTS.md synced across Claude Code, Codex, Cursor, and more.

ai-rulez

Author, generate, validate and govern rules, skills, plugins and MCP configuration for 52 AI coding assistants from one .ai-rulez/ source. Lock, sign and SBOM your agent configuration, review it with verified model evidence, and publish plugin bundles. CL

jev-use

Claude Code / Codex / pi plugin that hands the agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

clerk

The official Clerk CLI. Add authentication to your app with npx -y clerk@latest init (Next.js, React Router, Astro, Nuxt, TanStack Start, Expo, and more). No Clerk account needed to start. Manage users, instances, keys, and deploys from the terminal or a

@ory/claude-code

Ory plugin for Claude Code: scaffolding skills, a local Ory instance, and authentication, authorization, and audit for every tool call

codex-channel-bgos

HOAI channel for OpenAI Codex: silent desktop setup, native tools, persistent chats and background agents

ceulen

Ceulen — the Pi coding agent, fully dressed: one bundle extension carrying the full toolkit with a single /ceulen config command.

@maxiaochao/pi-toolkit

Personal pi coding agent toolkit: background tasks, scheduler, /btw, /cache_export, apply_patch, browser automation, and bundled theme/skills.

More in Coding agents & developer tools