Package Exports

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (orchestray) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Orchestray

Multi-agent orchestration plugin for Claude Code. Automatically detects complex tasks, decomposes them across specialized AI agents, and produces fully audited output — without manual configuration.

What it does

You type a prompt. Orchestray's PM agent scores its complexity. If it warrants orchestration, the PM decomposes the task, assigns agents (architect, developer, reviewer, custom specialists), coordinates their work, and delivers a consolidated result with full audit trail.

Simple prompts pass through to normal Claude Code behavior. Complex prompts get the full treatment.

Key features

Auto-trigger — complexity scoring detects when orchestration helps
Smart model routing — assigns Haiku/Sonnet/Opus per subtask based on complexity, tracks cost savings
Parallel execution — independent subtasks run concurrently via subagents
Verify-fix loops — reviewer failures route back to developer with specific feedback
Persistent specialists — dynamic agents that prove useful get saved for reuse
Pattern learning — extracts reusable strategies from past orchestrations
Agent Teams — opt-in dual-mode execution for tasks needing inter-agent communication
Full audit trail — per-agent tokens, cost breakdown, routing decisions, model savings

Install

npx orchestray --global

This installs agents, skills, and hooks into ~/.claude/. No --plugin-dir flag needed — Claude Code discovers them automatically.

For project-local install:

npx orchestray --local

Uninstall

npx orchestray --global --uninstall

Usage

Orchestray activates automatically on complex prompts. You can also use slash commands:

Command	What it does
`/orchestray:run [task]`	Manually trigger orchestration
`/orchestray:status`	Check orchestration state
`/orchestray:config`	View/modify settings
`/orchestray:report`	Generate audit report with cost breakdown
`/orchestray:specialists`	Manage persistent specialist agents
`/orchestray:learn [id]`	Extract patterns from a past orchestration
`/orchestray:resume`	Resume interrupted orchestration

Agent roles

Agent	Role
PM	Orchestrator — decomposes tasks, assigns work, monitors progress, routes models
Architect	Design-only — produces design documents and technical decisions
Developer	Implements code changes
Reviewer	Read-only review across correctness, quality, security, performance
Specialists	Dynamic or persistent agents for domain-specific tasks

Configuration

Run /orchestray:config to view all settings. Key options:

complexity_threshold    Score threshold for auto-orchestration (default: 6)
auto_review             Auto-spawn reviewer after developer (default: true)
model_floor             Minimum model tier: haiku/sonnet/opus (default: sonnet)
force_model             Override all routing with a specific model (default: null)
enable_agent_teams      Enable Agent Teams mode (default: false)

How it works

User prompt
    |
    v
Complexity scoring (0-12)
    |
    +-- Score < threshold --> Normal Claude Code
    |
    +-- Score >= threshold --> PM orchestration
            |
            v
        Task decomposition
            |
            v
        Model routing (Haiku/Sonnet/Opus per subtask)
            |
            v
        Agent spawning (parallel where safe)
            |
            v
        Result collection + verify-fix loops
            |
            v
        Pattern extraction + audit report

Runtime state

All orchestration state lives in .orchestray/ (gitignored):

.orchestray/
  state/          # Active orchestration state
  kb/             # Shared knowledge base
  audit/          # Event logs and metrics
  history/        # Archived orchestrations
  specialists/    # Persistent specialist registry
  patterns/       # Extracted learning patterns
  config.json     # User configuration

Requirements

Claude Code v2.0.0+
Agent Teams features require v2.1.32+ (opt-in)

License

MIT