Multi-agent orchestration for Claude Code. Themed persona agents, structured dispatch protocols, team patterns, and self-learning hooks. Turn multiple terminals into a coordinated engineering team.
Spawn all 7 Archons for a strategic debate on a topic. Each Archon argues from their elemental philosophy. Paimon moderates and synthesizes. Use for architecture decisions, design debates, or any question that benefits from multiple perspectives.
Dispatch a task to a specific agent. Usage /dispatch <agent> <task description>. Formats the message using the structured dispatch protocol and sends it via claude-peers.
Show the current state of your peer orchestra — who's online, what they're working on, and available agents.
Spawn a pre-configured team of agents for a specific task type. Usage: /party <name>. Available parties: archon-council, sprint, research, security, full-stack.
Data Processing specialist (Albedo). Use for ETL pipelines, data transformations, batch processing, file parsing, document extraction, LLM enrichment, and cost-optimized processing.
Infrastructure & Security specialist (Alhaitham). Use for DevOps, CI/CD, security review, performance optimization, Docker, hooks, MCP servers, and compliance automation.
Documentation & Research specialist (Furina). Use for technical docs, research synthesis, planning artifacts, competitive analysis, literature review, and session consolidation.
Reporting & Admin specialist (Ganyu). Use for report generation, executive summaries, metrics compilation, data exports, status tracking, and trend analysis.
Frontend & UI specialist (Kaveh). Use for React, dashboards, data visualization, CSS/Tailwind, accessibility, responsive design, and quality gates.
Initialize peer-orchestra in the current project. Sets up agent rules, dispatch protocols, and self-learning hooks. Use when someone says "set up peer orchestra", "initialize agents", or "start orchestrating".
Switch the agent theme pack (genshin, generic, or custom). Use when someone says "switch theme", "change agents to generic", or "use naruto theme".
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Multi-agent orchestration plugin for Claude Code. Turn multiple Claude Code terminals into a coordinated engineering team — each with a distinct persona, domain expertise, and self-learning capabilities.
claude plugin install peer-orchestra
Peer Orchestra is a Claude Code plugin that gives you a team of specialized AI agents:
Each agent has a personality (from Genshin Impact characters), domain expertise, and self-learning (they improve across sessions).
You: open 3 terminals, context-switch between all of them,
remember what each one is doing, manually coordinate
You: "Build a user auth system with tests"
Paimon dispatches:
→ Zhongli (backend): designs the auth API
→ Xiao (QA): writes test suite
→ Kaveh (frontend): builds login UI
→ All three coordinate via messages, you review the results
claude plugin install peer-orchestra
Add to your ~/.zshrc or ~/.bashrc:
alias cl='claude --dangerously-skip-permissions'
alias clp='claude --dangerously-skip-permissions --dangerously-load-development-channels server:claude-peers'
# Terminal 1: You are the Traveler
clp
# Terminal 2: An agent joins your team
clp
# Terminal 3: Another agent joins
clp
# Tell Paimon what to build. She dispatches to agents.
| Command | What it does |
|---|---|
/orchestra-status | Show who's online, what they're working on |
/dispatch <agent> <task> | Send a structured task to an agent |
/init | Set up peer-orchestra in your project |
/theme-switch | Switch between agent theme packs |
| Character | Role | Personality |
|---|---|---|
| Paimon | Orchestrator | Enthusiastic guide, coordinates everything |
| Nahida | KB & Data | Curious, precise, deeply knowledgeable |
| Zhongli | Backend & Architecture | Methodical, thorough, unshakeable |
| Albedo | Data Processing | Analytical, systematic, cost-conscious |
| Furina | Documentation & Research | Theatrical, decisive, detail-oriented |
| Kaveh | Frontend & UI | Creative, passionate about design |
| Alhaitham | Infrastructure & Security | Rational, efficient, uncompromising |
| Xiao | QA & Testing | Silent, relentless bug hunter |
| Yelan | Research & Intelligence | Sharp, concise, source-verified |
| Neuvillette | Audit & Review | Calm, impartial, evidence-first |
| Ganyu | Reporting & Admin | Thorough, organized, never misses details |
| Lisa | Tooling & Internals | Scholarly, understands systems deeply |
For teams that prefer straightforward role names without character flavor. Install with /theme-switch generic.
Want to create a theme? See Contributing.
peer-orchestra/ (Claude Code Plugin)
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── agents/ # 12 subagent personas
│ ├── paimon.md # Orchestrator (Opus)
│ ├── nahida.md # KB & Data (Sonnet)
│ ├── zhongli.md # Backend (Sonnet)
│ └── ... # 9 more agents
├── skills/
│ ├── init/SKILL.md # Project initialization
│ └── theme-switch/SKILL.md # Switch theme packs
├── commands/
│ ├── orchestra-status.md # /orchestra-status
│ └── dispatch.md # /dispatch <agent> <task>
├── hooks/
│ └── hooks.json # Agent router, memory hooks
├── scripts/ # Hook implementations
├── themes/
│ ├── genshin/agents/ # Genshin persona files
│ └── generic/agents/ # Role-based alternatives
└── src/templates/ # Rule templates (dispatch, teams)
npx claudepluginhub gocarbontracker/peer-orchestraOrchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Multi-agent orchestration for Claude Code. 12 specialized agents working in parallel — planning, building, reviewing, debugging. Plus a Hub for always-alive multi-project sessions controllable from Telegram or Slack.
AI team role and worker manager for multi-agent development workflows.
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
Intelligently compose and deploy Claude Code Agent Teams. Auto-selects optimal team composition from 24+ agents and 83+ skills across 5 scopes, generates task dependency graphs, and orchestrates multi-agent workflows with a single command.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.