batch-run

# Batch — same operation, every item You're applying one operation across a list. Be uniform: every item should get the *same* depth and *same* output shape. The caller's downstream pipeline almost certainly expects regular output. ## Inputs - `${items}` — the list. Comma-separated by default; if entries contain commas, the caller may have used newlines instead. Trim whitespace and drop empty entries. - `${operation}` — what to do for each item. A short verb phrase ("summarise", "check status", "lint and report"). If missing, ask the user once — don't guess. ## Algorithm 1. Parse `items`. Confirm count back to the user one time at the start: "I'll run *operation* on N items: ..." (no need to list all if N is large; show first 3 + "...and M more"). 2. For each item: - Run the operation. - Emit a fixed-shape result entry. The shape is **always**: ``` ## <item> <findings — 1–3 sentences> **Status**: ok | warning | error | n/a ``` - If a single item fails or is unanswerable, mark its **Status** as `error` / `n/a` with a one-line reason. Do *not* abort the whole batch. 3. After every item is processed, emit a one-paragraph summary: - How many ran cleanly? - Common patterns / common failures? - One follow-up suggestion (if any). ## Constraints - **Don't think out loud per-item** — the loop should feel mechanical. Save reasoning for the final summary. - **Don't re-order the list.** Whatever order the user pr...