Back to directory

Orchestrator

A skill and CLI that lets one AI coding agent orchestrate several others in the background, assigning specific models or agents to specific parts of a task.

Orchestrator

Orchestrator is a skill built on a local command-line tool, inspired by kubectl, that lets a coding agent such as Claude Code or Codex delegate work to other agent harnesses running in the background rather than acting as a replacement harness itself. A user describes outcomes in terms of models, for example asking for one agent to build a backend, another to design a frontend, and a third to review the result, and the calling agent translates that into orchestrated background workers.

Each worker is a named task with status, logs, output, and follow-up, resume, and stop controls, driven through a small JSON command loop. Orchestrator discovers available model names and IDs from the runtimes actually installed rather than relying on a fixed list, and preferences for which model to use for which kind of work can be set in a preferences file.

It installs as a skill plus an optional command-line tool, which the skill can also install on first use.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.