Havuz

Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory

Put your idea on trial in front of a jury of 12 Claudes. A free Claude Code skill.

Your Claude Code, Codex and Mistral Vibe sessions as a live, animated team call: who is working, who waits on whom, who needs you. VS Code e

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent ca

Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315

Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dep

Orchestrator mode for Claude Code: the main session plans and delegates the work to subagents.

Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision

A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan

clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves

Tu dis ce que tu veux, une équipe de vrais agents Claude Code se met au travail sous tes yeux, dans un bureau en pixel art. Gratuit et open

Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT v

A free pit crew for your expensive coding agent: the superpowers development workflow, run by cheap workers.

Claude skill + plugin that picks the right model and effort for every task: Opus plans, Haiku/Sonnet build, every step is verified, and it e

Pitch your idea to a Shark Tank-style panel of Claude sharks who want to say no. A free Claude Code skill.

See what your coding agent actually did. A desktop pal and notch for Claude Code, Codex, Cursor, Gemini CLI and any agent: test results read

Local dashboard for Claude Code, Codex, OpenCode, OpenClaw and Qoder session history, token usage, cost tracking, tool calls and subagent re

29 Claude Code skills, 4 subagents and 3 hooks: grilling, handoffs, a kanban workflow, an unattended orchestrator with a merge gate, multi-a

让主对话一直跑：把 Claude Code 子 Agent 派到你自己的其他 Pro 账号上，按余量选号、撞限额自动换号续跑 | Dispatch Claude Code sub-agents across your own Pro/Max accounts

Local dashboard for Claude Code and Codex CLI: which Claude Code session needs input, every tool call and Claude Code subagent live, cost an

协调探索、执行和独立评审，让复杂任务按明确职责并行推进，由主 Agent 统一验收。

The Agency — a roster of 200+ specialist AI agent personas (engineering, design, marketing, sales, security, GIS, game-dev & more) for Claud

Agents, skills and plugins I use daily to code with AI. A living Claude Code marketplace, also compatible with Codex.

Multi-model routing for any AI coding agent: send each task to the cheapest model that can do it well. Works with Claude Code, Codex, Cursor

A Claude Code skill that delegates coding, review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents — save tokens, use

Two Claude Code subagents that start at about 7.5k tokens instead of 131k: no CLAUDE.md, no skills list, no MCP tools.

Terminal side pane for Claude Code that shows a session's agents as a live tree. Stop a running sub-agent, send it new instructions mid-task

Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, de

Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plug

How to use pstack without Cursor: universal workflow for Claude Code (pstack-claude), Pi (pi-pstack), Codex, & Gemini. Zero dependencies, v0

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming)

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

从零手搓的 Coding Agent（ReAct + 工具 + 记忆 + 权限 + 上下文压缩 + 子agent + MCP），纯 Python/asyncio

Agent Reliability Analyzer MCP server for Cursor: find agent reliability issues in MCP servers

LLM Council for Claude Code with zero API keys — parallel Claude subagents debate, anonymously peer-review, and synthesize an answer, all on

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flag

Run many Claude Code sessions on one machine safely: no killed dev servers, port clashes, RAM or disk freezes, or mixed-up commits. Zero-dep

Claude Code plugin: automatic Claude model routing. Picks Haiku, Sonnet or Opus and the reasoning effort per prompt, step and subagent; effo

Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main

Multi-agent Claude Code skill for building apps and stuff

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

Kimi for Claude Code, Codex, and DeepSeek Harness: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a

An open-source skill for running parallel implementations, reviewing them independently, and selecting or synthesizing the best result.

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release

Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

Your engineering crew for Claude Code — 12 specialists plan, build, review and ship in any stack; the rules that matter are enforced, not re