Coding agents & developer tools
Claude Code, Codex & Cursor extensions
8,960 agents · most starred first
Claude Code, Codex & Cursor extensions, page 89 of 90
An OpenCode plugin that trains a Tracen Academy roster of specialist coding agents to research, build, and review.
OpenCode plugin providing DataRobot skills for AI/ML workflows and a DataRobot-branded theme.
Delegating task/subagent extension for Pi: foreground/background subagents, widgets, tmux observability, SDK fallback.
V2 remote compaction and imagegen for Pi; independently maintained lightweight toolkit
Your Claude Code, Codex and Mistral Vibe agents as a live video call, from the terminal: a local page in your browser, plus one-line status for status bars. Free, open source, zero token cost.
Did it push straight to main? Touch a file you told it never to? RuleReceipt checks the finished session against your CLAUDE.md / AGENTS.md rules and marks each followed, broken, or can't-tell, with the exact line as proof. Reads sessions from Claude Code
Opens Claude Code, Codex, Copilot CLI, VS Code and the Copilot app in your projects through any model provider: LiteLLM, 9router, OmniRoute, OpenRouter, Anthropic, OpenAI or any compatible host. Ships only the launcher; each tool installs on demand from i
OpenCode plugin that brings Antigravity-style multi-agent teamwork (/teamwork) to OpenCode: scoping interview, milestone state machine, adversarial verification gates, and a TUI status sidebar.
One harness, eight agents, zero trust in "done" — cross-agent coding harness for Claude Code, Codex CLI, Gemini CLI, Qwen Code, OpenCode, Kilo, Pi and Hermes: one skill canon, mechanical safety gates, an autonomous loop with screenshot/video proofs.
SOFTURE agent skills: a spec-driven delivery workflow (shape → prd → roadmap → plan → implement → review) plus parallel worktree orchestration
Codex brain + Antigravity worker orchestration kit with deterministic file-state workflow
Ultra-compact autonomous supercoder OS & verified AI agent skills for Claude Code, Cursor, Codex, Windsurf, and 20+ coding agents
Vite plugin for assistant-ui: the "use generative" directive compiler that colocates a tool's schema, server-only execute, and client-only render in one file. Works with Vite apps and TanStack Start.
Interactive multi-agent skills manager and anti-slop engineering toolkit. Installs modular SKILL.md-based skill packs into supported AI coding agents.
Multi-agent build & test command deduplicator for Antigravity and Claude Code
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
A minimal multi-agent skill+cli for pi. It adds no extension or tools, so it uses only a few dozen tokens of the context window until the main agent delegates, yet it gives the same controls as a subagent extension. Background agents keep running after th
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
Remote multi-agent development workspace for the official Claude Code and Codex CLIs
oh-my-dsh: DeepSeek Harness multi-agent orchestration layer — OMC-style workflow skills, slash commands, and an agent preset.
Safe project-scoped multi-agent autopilot for Codex with interactive setup, diff, doctor, and reusable Goal contracts
pi package of agentic-bundle: A portable agentic harness: shared instructions, skills, commands, subagents and MCP servers.
Claude Code package of agentic-bundle: A portable agentic harness: shared instructions, skills, commands, subagents and MCP servers.
OpenCode package of agentic-bundle: A portable agentic harness: shared instructions, skills, commands, subagents and MCP servers.
Codex CLI package of agentic-bundle: A portable agentic harness: shared instructions, skills, commands, subagents and MCP servers.
Write your agentic harness once (instructions, skills, commands, subagents, MCP servers) and ship it to Claude Code, OpenCode, pi, Codex and more.
Agentic Coding Framework - Multi-assistant configuration system with OpenSpec workflows
Interactive CLI for scaffolding and managing Agentic Engineering Suite in any repository
Agentic Spec-Driven Development framework for Gemini/Antigravity
Agentic AI SDLC kit — agents, skills, rules and slash commands (/spec, /plan, /build, /test, /code-review, /deploy) with multi-tool support (Claude, OpenCode, Codex, Gemini, GitHub Copilot).
Canonical skill catalog and activation management for agentic CLIs.
Install the Gantry harness-neutral agentic SDLC skill pack.
Agentic coding system for Claude Code — CLI for global rules + permissions (plugin available via /plugin marketplace add HOPLAtools/claude-setup)
Read-only file viewer that turns a coding agent's file paths into links you can open on your phone over Tailscale
Curated runtime skill orchestrator for AI coding assistants: plan, execute, verify.
Behavior-guardrail hooks for Claude Code, Codex CLI and Gemini CLI: test-tampering + outbound-action guards, gate-liveness verification, and mutation test-honesty
A multi-agent setup for Claude Code, Cursor and Codex (orchestrator + architect, coder, grader, utility subagents) with memory-bank, jevmem and Spec-Driven Development wired in, installed into a project with one command.
Inventory and clean up what coding-agent CLIs (Codex, Claude Code, Cursor, Gemini, ...) leave behind on macOS and Linux.
Runtime-grounded control plane for durable Codex Agent and Operator sessions.
A project launcher and shared context for Codex, Claude Code, and GitHub Copilot CLI.
Free, open-source Agent Skills generation and management for Claude Code, Cursor, Codex, Antigravity, Windsurf, Continue, Cline, and Copilot.
Universal package manager, security auditor, and MCP server for portable agent skills (SKILL.md).
103 curated bilingual (EN+RU) skills in the universal Agent Skills format for Claude Code, OpenCode, Cursor, Windsurf and every LLM/GLM agent. Python SDK + CLI with CI-enforced validation and quality scoring.
Temporarily disable / re-enable AI-agent skills, agents, commands, rules, plugins and MCP servers across harnesses (Claude Code, Codex, Grok, OpenCode, OpenClaw, Copilot, Vibe, Devin, Antigravity)
Local-first CLI + MCP server that bridges session context across AI coding agents.
Coding-agent runtime supervisor, CLI, and Model Context Protocol server
Approve, steer, and stop every Claude Code agent from one page.
Make repositories agent-ready and prepare safe, reproducible development environments for coding agents
Replay your coding-agent sessions (Claude Code, Codex, Cursor, Copilot, OpenCode, Kiro) as a map and a timeline. Local only.
A plug-in backup layer for coding agents: preserves state before every tool call modifies it
Bridge AGENTS.md to every AI coding tool's rules file - one source of truth for Claude Code, Copilot, Cursor, Windsurf, Cline, Aider, Roo Code, Kilo Code, Junie, and Amazon Q.
Find edits a coding agent made against a stale view of a file, and keep agents' views current with a write-through hook (Claude Code, any hook system, any MCP client, mini-swe-agent)
Linux-only CLI/TUI to manage, measure, and swap Claude Code OAuth subscription accounts.
Local dashboard for your Claude accounts: usage limits, sessions, projects and chat handoff between accounts.
A top-style live view of your Claude Code background sessions and plan usage
Publish, update, list and inspect Claude Artifacts from the terminal, using the Claude Code login already on your machine.
Audit Claude Code's prompt-cache usage from local transcripts: subagents, cache rebuilds by cause, idle compactions.
Claude China: AI coding profiles and a desktop launcher
Store and address several Claude Code accounts on one machine (library for the claude-code-multi-account spec).
Import your Codex CLI sessions for the current repository into Claude Code, so they open with /resume.
How much each source (CLAUDE.md, rules, skills, memory, tool results) costs in the context of a Claude Code session, counted from the API usage in its transcript. Also a context budget for CI, and the git version of each file a session loaded.
Import your GitHub Copilot CLI sessions for the current repository into Claude Code, so they open with /resume.
Bring Claude Code CLI sessions into the Claude Desktop sidebar, with real titles and the right order.
Convert a Claude.ai data export into a browsable static HTML archive
One priority queue over all your running Claude Code sessions in herdr (macOS, Windows) or iTerm2
Import your opencode sessions for the current repository into Claude Code, so they open with /resume.
Tools for running many Claude Code chats on one machine: find any chat, send a message into a running one, start chats in tmux, wake a chat from a scheduled job, and a few hooks
Teleport sessions between Claude and Codex, across Claude accounts, and between WSL and Windows
Use Claude Code's native /voice over SSH by bridging your local microphone to the remote server.
Hardened Python wrapper for the local Claude Code CLI (claude -p): sync/async, streaming, cache. Stdlib-only.
A self-hosted browser workbench for Claude CLI; requires Node.js 22+
Stream text from the signed-in Claude Code CLI
Name reservation
Move visible conversation history between local AI coding agents.
Windows-first patch tool for the native Claude Code CLI: apply, verify and diagnose community patches across releases.
A configurable, stateful Claude Code status line for Linux, Windows and macOS
Drive Claude Code with a Logitech G923 wheel, pedals and shifter
Unofficial migration helper for the sunset langchain-community: finds every langchain_community import, the standalone package that replaces it, rewrites 1:1 moves and vendors orphaned classes.
OpenCode agent handler for LaunchDarkly AI SDK
Claude Code for the livery workshop: CLAUDE.md, the delivered guidance, .claude/ and the hook verbs the agent's tooling runs.
Isolated secure launcher for LoopGrid's Claude Code plugin
mediapane plugin: show images Claude Code writes or reads, and an MCP tool so any agent can show media.
Run several Claude Code accounts side by side: separate CLAUDE_CONFIG_DIR directories, launchers, proxies, environment variables and arguments.
Centralized hub to manage and distribute skills, rules, and subagents across multiple AI coding assistants
Install Claude Code delivery and code-review skills with focused custom agents.
Move AI conversations between Claude Code, Codex, ChatGPT, Claude and tavya, and resume them natively
Put your engineering best practices into practice, across every AI coding agent.
Multi-account switcher for Claude Code
Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.
Initialize a repository with the TacT developer and agent collaboration kit.
Deterministic, team-aware AI workbench configuration auditor
Cursor ve Claude Code'u Telveguard'a bağlayan hook'lar ve kurum hesabıyla giriş (telve)
Autonomous Standalone Specialist Fleet & Multi-Agent Architecture (70 Agents) for Pi Coding Agent
Create, lint, security scan, test, share and export agent skills (SKILL.md) for Claude Code, Cursor, Codex, Hermes and more.
Installs the Agentville plugin of skills and agents into Claude Code.
Agno Model adapter for persistent Cursor CLI ACP sessions
Keep Claude Code sessions working on their artifacts after cswap switches claude.ai accounts