Public multi-agent workbench skill pack for SDD, review gates, context discipline, VM lanes, Sanity context, and autonomous agent coordination.
3 files for GitHub Copilot, Codex, OpenCode and Claude Code: multica-ultimate-workbench copilot-instructions.md, multica-ultimate-workbench AGENTS.md, multica-ultimate-workbench CLAUDE.md — 11,867 tokens loaded in every session.
.github/copilot-instructions.md A 156 tok AGENTS.md A 10,508 tok CLAUDE.md A 1,203 tok These files are Fearvox/multica-ultimate-workbench's own configuration — they tell GitHub Copilot, Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.