Skip to content

Live Rig Topology Changes

Guides an agent to safely add, remove, bind or adopt seats in a running OpenRig rig.

Stars
8,553
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches an AI agent how to change an OpenRig multi-agent setup while it is already running, such as adding or removing agent seats, relaunching a node, or attaching an existing terminal session to a logical node. It tells the agent which OpenRig commands to use (for example rig grow, rig expand, rig shrink, rig bind, rig adopt), when to write a configuration fragment instead, and what to verify afterward, such as that rig whoami and rig ps reflect the new state. It also lists four common failure modes to avoid, like new seats missing their queue or role files and stale references left after removal.

Great for

  • Developers running OpenRig rigs who want an agent to scale or reshape a live rig without rebuilding it
  • Teams testing OpenRig changes who need checks that work on an active rig rather than only a clean test fixture
  • Operators adopting an existing tmux or agent session into OpenRig topology

Skip it if

  • Creating a rig from scratch, where rig up is the right tool and this skill does not apply
  • Replacing the occupant of a seat while keeping its continuity, which the skill says belongs to the seat-continuity-and-handover skill
  • Anyone without OpenRig installed, since the commands only work against an OpenRig daemon and its rigs; running them on a live rig can change or remove working agent sessions

Try asking

  • “Add two more seats to my running research rig using rig grow, then confirm they show up in rig ps”
  • “Shrink the review pod in my active rig and check for stale topology references afterward”
  • “Adopt the existing tmux session 'api-dev' into the backend node of my rig and verify rig whoami reports it correctly”
  • “Attach my current shell to the planner node of the running rig as an observer”
Step-by-step guide: how to use Live Rig Topology ChangesInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    topology-mutation-and-seat-management.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip topology-mutation-and-seat-management.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip topology-mutation-and-seat-management.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run rig grow --help on your installed version first, since the skill notes some flags were added after v0.2.0
  • Name the target rig and the exact operation before letting the agent act, and confirm you are authorized to change that rig
  • Test mutations on an isolated active rig first; a passing schema check or fixture does not prove a live rig was changed correctly

What's inside

  • SKILL.md

Redistributed unmodified from mvschwarz/openrig under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.