scope

# Scope — Review a proposed write scope Review the write scope in the existing bead or caller intent. This skill is advisory: it does not create a second planning artifact, write a lock, install a hook, block an edit, or claim paths. ## Inputs - One active behavior and its acceptance scenarios. - Proposed include and exclude patterns. - Known generated companions and fixture/projection paths. - Explicit non-goals. ## Procedure 1. Map each acceptance criterion to the smallest source paths that may change. 2. Add owned generated companions that must move with those sources. 3. Check whether any include/exclude patterns overlap or are too broad to prove. 4. Identify likely paths the proposal omitted. 5. Return a corrected proposal and the reasons for each change, then stop. The caller decides whether to adopt the proposal in the original intent source, and Validate independently compares runtime-derived changed paths with that scope. ## Axiom-kernel framing Derive the scope from axioms, not enumeration instinct. State the small set of facts the acceptance makes true — "behavior X lives in root A", "projection B is generated from A", "history under C is frozen" — and derive every include and exclude pattern from exactly one axiom. A pattern with no supporting axiom is unjustified breadth; an axiom with no pattern is a gap. Both go in the review output. Scopes assembled by listing directories that feel related are the **vibes perimeter** failure mode: they cannot be defend...