Havuz

Autoprompt, coding-agent’ların ürettiği değişiklikleri gözden geçirip düzeltme ve yeniden kontrol etme döngüsüyle kodlama iş akışlarını güçlendiren bir araçtır.

Neden yükseliyor · 41 günlük yaşına karşın 1295 yıldız, son 28 günde 16 commit ve 7 farklı yazar dikkat çekici erken ilgi ve katkı gösteriyor. README’deki ölçümde OpenCode’un Terminal-Bench 2.1 sonucu 89 görevde 60 çözümden 73 çözüme çıkmış; ancak bu, sınırlı bir benchmark karşılaştırmasıdır ve genellenebilir etkiyi tek başına kanıtlamaz.

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

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。

Local subagent orchestration for Codex and Claude, with persistent task state, reusable teams, and interruption recovery.

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

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

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

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

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

Subagent Verification for Claude AI Code Networks 2026

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

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce

Codex 三層多代理協作 Skill：Sol 統籌與複雜推理、Terra High／XHigh 處理視覺與操作、Luna Max 執行可重複工作。

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。

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code:

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

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

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

Open-source multi-agent PM-ops team — associate PM, GTM, QA, data-analyst subagents and more, orchestrating product work end to end.

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

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

Claude Code skill + subagent for setting up guardrailed agentic loops (loop engineering): headless, evaluator-optimizer, meta/prompt-refinem

My actual Claude Code setup: a stack-agnostic engineering spine, auto-activating rule packs, 50 scoped subagents across web/Android/iOS/comp

Agent PI - Agent Development Environment (ADE)

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

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

Your coding agents get an agreed plan, a check after each round of changes and a handover to the next session. Workflow plugin for Claude Co

Multi-agent Claude Code skill for building apps and stuff

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

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

Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

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

Pixir: supervised subagents and workflows for coding agents

Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subag

Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.

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

Diverter distills Ultra’s delegation strategy into non-Ultra Codex sessions—bringing in the right native specialist while the main thread ke

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

Installable AI coding workflow for risk-based routing, scoped sub-agents, and evidence-backed completion.

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

Always-on local AI assistant and AI coding agent runtime in Go. OpenClaw, Claude Code, Codex, and OpenCode alternative with Terminal TUI, Te

5-agent AI team for Claude Code operators: Iris (design), Lyra (build), Echo (scout), Newton (research), Hypatia (critic). One-command insta