Orchestration plugins

Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.

v11.23.0 - UberLLM seats, isolated presets and accurate run results. 31 personas, 56 commands, 64 skills. Run /octo:setup.

71 skills · 56 commands · hooks

74 skills for Claude Code and Codex. A build DAG researches your repo, fans out disjoint lanes, and refutes its own review before anything lands. A blunt A-F ship grade blocks the bad merge instead of complimenting it. The same folder designs the page, writes the copy, and ships native iOS and Android builds.

70 skills · 1 MCP server

A coordinated engineering team of named AI specialists that remembers your project between sessions. Call yui to route work, or call any specialist directly: Go (jaan, siim, mart), Angular (liis, kadi, tiiu), iOS (ren, shu, ryo), Python (eero, anu, ivo), React (noa, rui, aki), SQL (saku), NoSQL (remo), architecture for any stack (kai), process management (enn), and DevOps/infra (sora). Each ships as both a skill and a subagent. Bundled hooks capture finished work when a session ends and say at the next session start that saved work exists, and record per-session and per-agent token and time usage. Every specialist follows the same discipline: read context first, make the smallest correct change, verify.

23 skills · 20 agents · hooks

Multi-agent orchestration grounded in an LLM wiki. /dev-loop:orchestrate splits one goal into a dependency graph of parallel Claude Code sessions, each in its own worktree, and supervises them natively on Orca (a tracked Task + Dispatch per phase, pushed worker_done / question / escalation events instead of polling, stall detection; raw tmux fallback). Every plan decision must cite a page in a bundled best-practice wiki of 400+ pages across 10 domains, checked by machine gates and a fresh-context plan reviewer. Insights from your sessions are queued and turned into reviewed wiki PRs when you run /dev-loop:knowledge-flush (automatic flushing is opt-in and never bypasses permission checks).

9 skills · 11 agents · 1 MCP server · hooks

Microsoft Azure MCP and Skills integration for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from your development environment.

35 skills · 1 MCP server

Customer advocacy orchestration covering sourcing, activation, and storytelling

3 skills · 4 commands · 3 agents

Multi-channel campaign coordination and optimization

3 skills · 3 commands · 3 agents

Account-based marketing orchestrator coordinating tiering, plays, and analytics

3 skills · 3 commands · 3 agents

WAVES (Workers, Aggregate, Verify, Extend): wave-based orchestration for Cursor. Decompose a big task into independent slices, fan them out to isolated parallel subagents with the Task tool as a bounded wave, verify each handoff, then synthesize. The manifest is the stop function: continue until every slice is terminal; stop only on completion, stagnation, or budget. Reduce entropy first; route scouting to cheap fast models. Runs in place of cloud orchestration. Opt-in via /waves. For large research, analysis, audits, and codebase or data exploration. Formerly parallel-orchestrate.

1 skill

WAVES (Workers, Aggregate, Verify, Extend): wave-based orchestration for Codex. Decompose into independent slices, spawn parallel Codex subagents (or spawn_agents_on_csv) as a bounded wave, verify evidence-backed handoffs, then synthesize. The manifest is the stop function: stop only on completion, stagnation, or budget. Reduce entropy first; route scouting reads to gpt-5.6-terra low. Tuned for Codex roles, config.toml limits, codex exec fleets, and a Desktop coordinator-thread mode. Formerly parallel-orchestrate-codex.

1 skill

Gives Claude Code a multi-agent coordination layer over MCP — an atomic shared blackboard (locked propose/validate/commit), permission gating with HMAC/Ed25519-signed tokens, federated token-budget tracking, and append-only audit-log queries. Backed by an orchestrator with 32 framework adapters (LangChain, AutoGen, CrewAI, Gemini, and more).

4 commands · 1 MCP server

通过并行委托多个 Codex 代理来编排复杂任务，然后合并和审查结果

2 commands

Orchestration Temporal (TypeScript) — workflows skill_eval, source_watch, usage_observer + activities.

Hands-free implementation of an agreed plan — worktrees and cheap-model executors under TDD, an item-by-item conformance check against the plan on the premium model, an adversarial review sized to the change (installed skills or an on-the-spot panel), technical decisions logged and functional ones left to the user, a capacity check and /goal condition up front, and no worktree deleted without asking.

1 skill

Budget loop for long-running or parallel agent work under Claude's 5-hour and weekly usage limits — run bounded waves, check real usage between them, pause before the cap, and resume with self-contained prompts only when the window is actually clear.

1 skill

Run expensive top-tier models (Claude Fable/Opus, GPT-5.6 Sol, or similar) efficiently — the premium model keeps judgment, architecture, synthesis, and final review, while cheaper subagents (Sonnet, Haiku, Terra, Luna) do bounded token-heavy research, coding, and testing with self-contained handoffs and verified results.

1 skill

Multi-agent orchestration system for Claude Code — 38 skills + 19 agents covering audit, plan, build, verify, ship, release, retrospective, and ops. Includes ralph (autonomous PRD loop), release, ultrawork, ultraqa, team, trace, visual-verdict, debug, deep-dive, deep-interview, autopilot, autoresearch. Vendored snapshot at third-party/oh-my-claudecode/ pinned to upstream SHA aacde3e (v4.13.6). Heavy overlap with continuous-improvement /ralph and /superpowers — pick per task.

37 skills · 19 agents

Agent teams, swarm coordination, Monitor streams, and worktree isolation. Wraps 4 swarm_* + 8 agent_* MCP tools (12 total) plus 6 topologies (hierarchical, mesh, hierarchical-mesh, ring, star, adaptive). Slash commands /swarm and /watch. Skills swarm-init and monitor-stream. Cherry-picked from ruvnet/ruflo monorepo (the other 31 plugins are explicitly out of scope). Vendored snapshot at third-party/ruflo-swarm/ pinned to upstream SHA addb5cd (v0.2.0). Activation note: assets reference unpinned npx @claude-flow/cli@latest — supply-chain risk inert until installed.

2 skills · 2 commands · 2 agents

Brief it like a teammate, it conducts Claude Code in your seat. Charter-driven decisions, git locked.

15 skills · hooks

Run a Big Smooth that drives Claude Code worker sessions over tmux, coordinate agents over th-mail, drive the org's Smooth Operator, and track work in pearls. Provides the /smooth command + a windows-build-box skill (throwaway Windows EC2 over SSM). Ships the shared SmooAI repo guardrail hooks (worktree enforcement, th-over-curl nudges, pearls-label reminder, pearl-store read-only-wedge guard).

9 skills · 1 command · 1 MCP server · hooks

amq-squad agent-team coordination skills for Claude Code: live coordination (amq-squad), first-time team setup (amq-team-setup), custom role authoring (amq-squad-role-creator), and lead-agent orchestration (amq-squad-orchestrator).

7 skills · hooks

PaperClip Pro - AI agent orchestration platform. Manage multi-agent companies with org charts, heartbeat scheduling, task queues, budget tracking, and governance.

3 skills · 6 agents · hooks

Multi-agent investigation, planning and delegation, and an evidence-backed living memory of a project.

23 skills

Orchestrate complex tasks by delegating to multiple parallel Codex agents, then merge and review results

1 command

Оркестрація: маршрутизація наміру в скіли, мета-гарнес важких процесів, топології суб-агентів, мульти-провайдерний роутинг. (6 скілів)

Mycelium distributed intelligence system with 130+ expert agents, dual-mode coordination (Redis/TaskQueue/Markdown), real-time pub/sub messaging, and durable workflows

3 commands · 120 agents · hooks

Hook-driven agentic workflow orchestrator. Automatic routing (shell or LLM-hybrid), sprint-contract enforcement, TDD loop, session bootstrap, handoff nudges. Self-evolution SEPL loop (propose/assess/commit/rollback) over versioned resources. Composes agents/evaluator/context-engine/memory rather than duplicating them.

11 skills · hooks

Native-git stacked-PR management: push guard (blocks wrong-branch and bare --force pushes), stack-graph state, restack/reparent/submit workflows built on git rebase --update-refs and --onto. No third-party stacking binary.

5 skills · hooks

Multi-agent debate skills for coding CLIs. Orchestrates codex, gemini, cursor, kimi, and claude through structured debate formats to reach more robust answers than any single model.

6 skills