multi-agent plugins

by Numman Ali

Multi-agent orchestrator for Claude Code. Track work with convoys, sling to polecats. The Cognition Engine for AI-powered software factories.

by Jeremy Longshore

Production ADK orchestrator for A2A protocol and multi-agent coordination on Vertex AI

by Jeremy Longshore

Google Agent Development Kit (ADK) SDK starter kit for building Claude-powered AI agents with React patterns, multi-agent orchestration, and tool integration

by Damien Laine

Autonomous multi-agent development framework with spec-driven sprints and convergent iteration

by Mark Laursen

Maestro Frontier model-panel fusion with Opus 5, current Codex models, validated effort control, Codex skills, and optional lifecycle hooks.

by AUN-PN

Codex skill for safer Unity AI agent workflows, runtime-owner proof, runtime numeric proof, multi-agent scope ownership, and Unity game development automation.

by Le Xuan Thang

Full product lifecycle plugin: define Vision/Mission/Core → generate workplan → execute with reviewer agents → synthesize deliverables → maintain.

by RBraga01

A complete engineering team in one folder. 26 pre-configured specialists, 20 enforced workflow skills, a lead orchestrator, and a Pipeline Auditor — for Claude Code, Codex CLI, Cursor, and OpenCode.

by nyldn

Multi-LLM orchestration with Double Diamond workflows, provider routing, safety gates, and automation. Dispatches to Codex, Antigravity, Cursor CLI, Grok, Copilot, Qwen, Perplexity, OpenRouter, OrcaRouter, Ollama, OpenCode, and Kimi Code from a single plugin.

by open-dynamic-workflows contributors

Dynamic multi-agent workflows for Codex — plan, orchestrate, and verify parallel agents via a local daemon.

by TerminallyLazy

Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for coding agents using Tree Ring Memory v0.15+.

by chernistry

Deterministic orchestrator for CLI coding agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so runs replay byte-identically.

by Mohammed Abdelhady

Eight chained slash commands turn one Claude session into a structured engineering pipeline. /hyperflow:spec asks the questions a senior engineer would. /hyperflow:scope decomposes into a batched task graph. /hyperflow:dispatch fans out persona-stitched workers under thinking-tier review. Memory compounds across sessions — yesterday's decisions are tomorrow's starting point.

by luoxianzi

Command the legion, judge the work — Claude plans, Codex executes, and a binding fresh-context judge decides what merges. Zero config.

by Syncable

Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and multi-step workflows for change impact, incident investigation, refactoring, session continuity, co-change analysis, and episode replay, Cortex decision memory (decision recall, provenance, intent verification), session bookends (daily briefing, hotspots, self-audit), and single-symbol pre-edit preflight checks.

by Yonatan Gross

The Complete AI Development Toolkit — 107 skills, 36 agents, 171 hooks for full-stack development.

by Yonatan Gross

The Complete AI Development Toolkit — 107 skills, 36 agents, 171 hooks for full-stack development.

by Steven Syrek

Convene parallel role-specialized peer agents (dynamic roster, plan card first) to debate a cross-domain decision or audit a codebase in real time. Invoking Claude acts as CEO: convenes, routes peer-DMs, arbitrates deadlocks, writes a one-page decision log.

by Jason Colapietro

Public Suede skills and a read-only MCP for decisive agent workflows, code review, design, copy, SEO, app shipping, and creator work.

by Hamel Husain

Deep research across Claude and Codex in parallel with cross-pollination refinement

by Haptica

Give Codex an intelligence lifeline - Codex skill for calling ChatGPT Pro. Computer use, repomix file attach, thread isolation per repo.

Agent configuration utilities - project assimilation, config auditing, teammate definitions, MCP management, and hooks configuration

Coordination layer for multi-agent work using taskwarrior - parallel-safe queries, urgency scoring, GitHub issue/PR reconciliation, and native scheduling (wait/scheduled/due/recur)

by TreeX

Multi-agent orchestration framework with Socratic requirements discovery, Hybrid Tree PRD management, and structured quality evaluation