openrig
Define, boot, and manage persistent coding agent teams
All Skills in This Repository (24)
Pure Emerald Level Indicatorsrig-architect
Design, validate, and diagnose OpenRig multi-agent topologies.
mental-model-ha
Preserve and restore a pod's shared mental model across compaction events and restarts.
requirements-writer
Convert rough feature ideas into a PM-compliant requirements.md document.
backlog-capture
Capture ideas and feature requests into a structured backlog with deduplication.
context-builder
Gather and distill meeting notes and research into a feature background document.
office-hours
Guide product teams through six forcing questions to validate feature ideas.
ui-mockup
...
plan-review
Evaluate feature plans across strategy, design, and engineering to identify gaps.
exec-summary
Generate a 600-800 word executive summary with YAML frontmatter from feature documents.
openrig-user
Expose the shipped rig CLI for identity, inventory, communication, and lifecycle tasks.
development-team
Coordinate implementer, QA, and design roles into a single development loop.
orchestration-team
Coordinate multi-agent orchestration teams with roles, governance, and communication protocols.
Frequently Asked Questions
FAQPage SchemaHow to install OpenRig?â–¼
Run `npx skills add mvschwarz/openrig --all -g -y` in your terminal to install all skills in this suite globally.
What problem does OpenRig solve?â–¼
It turns scattered coding agent terminal sessions into a persistent, organized team. You define the team in YAML, boot it with one command, and restore it by name after a reboot.
Does OpenRig work with Claude Code and Codex?â–¼
Yes. Both runtimes run side by side in the same rig as ordinary tmux sessions, and you can mix models across roles for diverse reasoning.
Can OpenRig recover my agents after a restart?â–¼
Yes. `rig down` snapshots the full topology and `rig up <name>` restores it, reporting per-seat outcomes like resumed, fresh, or failed honestly.
Do I need coding experience to use OpenRig?â–¼
Basic terminal comfort helps, but the CLI is designed for plain commands like `rig up product-team`, and agents can drive the 40+ commands themselves via the built-in MCP server.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core