52 tagged Orchestration, measured the same way as everything else here.
Browse within: Multi-Agent 25claude-code-plugin 20development-twin 5plan-first 5
Plugin Claude Code
Bundles 40 commands, 15 agents, 1 MCP server · 1,015 tokens together
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
Plugin Claude Code
Bundles 1 skill · 40 tokens together
franke-skills. Agent-first CLI that runs Codex, Claude Code, and Grok as detached coding workers, while a stronger model keeps orchestration, steering, and review.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 11 tokens together
MCP server that orchestrates multiple Claude CLI instances as parallel workers with a real-time dashboard.
Plugin Claude Code
Bundles 28 skills, 27 agents · 1,775 tokens together
Orchestrated planning, code review, and developer workflow skills.
wu736139669/agent-taskgraph-protocol
Plugin Claude Code
Bundles 1 skill · 97 tokens together
Build native Claude Code Agent Teams with goals, roles, task graphs, collaboration protocols, and lifecycles.
Plugin Claude Code
Bundles 39 skills, 9 agents, 12 hooks · 2,227 tokens together
GAIA — Generative AI Interface for Agents. Security-first multi-agent orchestration for Claude Code and OpenCode: reads run free, state changes need approval, irreversible ops blocked.
Plugin Claude Code
Bundles 3 skills, 2 agents · 169 tokens together
Local Grok CLI delegation: task, review, resumable history, background jobs, stats, and setup health checks.
Plugin Claude Code
Bundles 46 skills, 1 command, 12 agents · 6,549 tokens together
Orchestrates a team of specialized AI agents for full-cycle software development with inline quality gates.
Plugin Claude Code
Bundles 11 skills, 8 commands, 4 agents, 6 hooks · 939 tokens together
A harness for long-horizon Claude Code work: one map per project with the objective and the distance to it, a loop that kills ideas with cheap tests, hooks that catch the bad session, and four kinds of decision that stay yours.
Plugin Claude Code
Bundles 3 skills, 4 agents · 478 tokens together
Multi-agent development orchestrator: classify by complexity, implement in isolated git worktrees with TDD + Tidy First, review under a two-party boundary, and stop at open PRs for human merge.
Plugin Claude Code
Bundles 14 skills, 3 agents, 2 hooks · 497 tokens together
Fleet orchestration, worktree-isolated parallel execution, automated phase gates, and supervision for Claude Code teammates.
Plugin Claude Code
Bundles 1 skill · 67 tokens together
Conduct a parallel multi-session sprint: one conductor, several work managers in git worktrees, a file-based mailbox, watchdog supervision, and a clean teardown.
JiaWeiXie/swarm-pi-code-plugin
Plugin Claude Code
Bundles 10 skills, 2 agents, 1 hook · 594 tokens together
Portable Pi workflows with durable Host Assistance, discovery, review, and isolated implementation.
anilcancakir/claude-code-plugin
Plugin Claude Code
Bundles 6 skills, 9 commands, 2 hooks · 522 tokens together
Main-agent planning trio (/ac:plan, /ac:execute, /ac:wisdom) with autonomous execution mode plus setup, init, commit commands and skill, agent, command, rule, CLAUDE.md creator skills. Two hooks back the workflow: SessionStart for twin-skill and resume, PreCompact for state preservation.
Plugin Cursor
Bundles 3 skills, 1 MCP server · 96 tokens together
Agent orchestration, decisions, and organizational memory for Cursor. Review pending decisions, scaffold initiatives, assign work to specialist agents, and render live widgets in-line.
SkiTemplar/ultron-control-center
Plugin Claude Code
Bundles 3 hooks, 2 MCP servers
Expone la memoria personal de ULTRON (brain.db + Qdrant, recall hibrido BM25+E5) y el buscador de papers academicos (OpenAlex + Semantic Scholar) como servidores MCP locales de solo lectura, con los 3 hooks minimos de memoria (resume al abrir, gate socratico por prompt, captura al cerrar), para chat, Claude Desktop y…
Plugin Claude Code
Bundles 1 skill, 4 commands, 2 agents · 394 tokens together
The Good, the Bad and the Ugly — tiered multi-agent orchestration for Claude Code. The Good (brain) plans and verifies, the Bad (judgment executor) handles work needing taste, the Ugly (mechanical executor) does the grunt work — in parallel herdr panes with fenced scopes.
Plugin Claude Code
Bundles 20 skills, 1 agent, 4 hooks · 1,266 tokens together
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.
Plugin Claude Code
Bundles 7 skills · 780 tokens together
Agentic loop-engineering for complex tasks. PRD -> tagged phase plan -> autonomous TDD execution loop with deterministic escalation, command-based verification, and disk-backed state that survives compaction.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: