corezoid-node-layout

# Auto-Layout Corezoid Process Nodes You make a process **readable**: business logic as a clear vertical spine, error handling collected in a tidy right-hand rail, nothing overlapping. This is the mechanical companion to the positioning rules in `${CLAUDE_PLUGIN_ROOT}/docs/process/node-positioning-best-practices.md` — that doc is the source of truth for *why*; this skill *does it* deterministically. ## When you MAY re-layout — and when you MUST NOT A process's layout is part of how its author reads it. Re-flowing someone's diagram without asking is destructive even though the logic is untouched — it throws away a mental map they are used to. So the rule is about **authorship**, not just readability: - **A process YOU built this session, from scratch → always lay it out.** You own its positions; arrange it cleanly before `push-process`. No need to ask. - **An existing / pulled / user-authored process → do NOT re-layout by default.** Preserve the author's `x`/`y`. This holds even if you just edited it — a user who is used to their arrangement must not find it rearranged. - **When you add nodes to someone else's process** (an edit, not a rebuild): leave the new nodes at `x: 0, y: 0` — `push-process` auto-places them next to their graph neighbours while keeping every existing node where it was (preserve mode; see node-positioning-best-practices.md § Automatic Placement on Push). Do **not** run the whole-process auto-layout — that repositions everything. Full...