Instructions for starmynd-org/infinite-brain-os, covering infinite brain os, working repo (codex), forced startup for every non-trivial chat, forced session discipline, the eleven entities and namespace architecture.
Instructions for starmynd-org/infinite-brain-os, covering infinite brain os, working repo, forced startup for every non-trivial chat, forced session discipline, the eleven entities and namespace architecture.
Package something from an individual brain for the shared brain's maintainer to review. This is the only road from individual work to the shared brain; nobody edits shared core directly.
Run this first on a new machine, and again each day. It establishes git access, clones your brains into internal/, validates and registers them, and syncs. Work autonomously and verify each step before the next; only stop for a sign-in the person must click, and tell them exactly what to click. Report each step in one…
Sync every brain mounted under internal/. Convention: a folder named individual- is an individual brain (push freely); every other brain mounted under internal/ is a shared brain (content is free to push, core changes go to a review branch). Backend is plain git (GitHub by default). Use GITTERMINALPROMPT=0 so git…
Explain the harness to the person in warm, plain words. No git jargon, no file-tree dumps. Adapt to what they ask; if they just typed /workspace-help, cover this.
Instructions for starmynd-org/infinite-brain-harness, covering harness (codex orientation), one folder for everything you own: internal/, routing rule (which brain gets the work), commands and the registry.
Instructions for starmynd-org/infinite-brain-harness, covering harness (claude code orientation), one folder for everything you own: internal/, routing rule (which brain gets the work), commands and the registry.
23▲
+1 3d agoA1,714 tokens
copy · 94%MIT
At most 3 mods per repository are shown here — the rest are on their repository pages: