Marketplace for trusted AI agent skills

Skill Detail

Run managed Claude Code and Codex teams with OpenRig

Use OpenRig when an operator wants persistent tmux-backed Claude Code and Codex seats, YAML-defined team topology, shared TUI visibility, queue handoffs, recovery, and agent-to-agent coordination from one local control plane.

Developer ToolsMulti-Framework
Developer Tools Multi-Framework Security Reviewed
⭐ 1.4k GitHub stars ⬇ 2.5k/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill run-managed-claude-code-and-codex-teams-with-openrig Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
OpenRig CLI, Node.js 20/22/24, tmux, macOS or Linux, authenticated Codex and optional Claude Code or supported terminal harnesses
Install & setup
Install with npm install -g @openrig/cli. Review rig setup –dry-run before applying setup, confirm tmux and authenticated agent CLIs are available, then run rig up first-project –cwd . –plan, rig up first-project –cwd ., and rig tui –shared from the target repository.
Author
mvschwarz
Publisher
Open Source
Last updated
Sep 28, 2026
Quick brief

OpenRig is a local multi-agent harness for operating Claude Code, Codex, terminal seats, and related coding-agent runtimes as one managed team. Use it when an operator wants stable agent roles and addresses, a YAML RigSpec topology, tmux-backed sessions, a shared dashboard, queue-based handoffs, review seats, snapshots, recovery, and cross-agent messaging instead of manually juggling separate terminals. Invoke this instead of using Claude Code or Codex normally when the useful workflow is repeatable multi-agent coding operations: install the CLI, run a setup dry run, launch a starter rig in a repository, inspect seat readiness, send a bounded implementation task to an owner seat, and have a checker seat review the exact candidate. The scope boundary is local coding-agent team orchestration and lifecycle management, not a generic terminal multiplexer, hosted agent product, or broad framework listing.

How it works

What this skill actually does

Inputs and prerequisites: OpenRig CLI, Node.js 20/22/24, tmux, macOS or Linux, authenticated Codex and optional Claude Code or supported terminal harnesses.

Setup notes: Install with npm install -g @openrig/cli. Review rig setup –dry-run before applying setup, confirm tmux and authenticated agent CLIs are available, then run rig up first-project –cwd . –plan, rig up first-project –cwd ., and rig tui –shared from the target repository.

Source and verification boundary: use https://openrig.dev as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.