Havuz

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

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

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

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

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

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

Pixir: supervised subagents and workflows for coding agents

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

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

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

Subagent Verification for Claude AI Code Networks 2026

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

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

Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper

Claude as subagents in Codex — scoped workers, resumable sessions, git-ignored logs.

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

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

Project-local agent harness skill for traceable AI workflows

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

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

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

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

Automatic model+effort routing for Claude Code: tiered subagents, escalation ladder, independent verifier

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

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, upda

🐱 MiNerva·咪涅瓦 — 替你干活的赛博猫｜An autonomous AI agent that actually does the work.

omo for Claude Code — native Claude Code plugin marketplace (Sisyphus Labs / omo): rules, comment-checker, LSP, ultrawork, ultragoal, start-

🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / G

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

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

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

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

Agent PI - Agent Development Environment (ADE)

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

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

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

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

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

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

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

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

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。

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

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

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

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

Multi-agent Claude Code skill for building apps and stuff

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