be

name	be
description	Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with an AI review gauntlet (codex debate → lens debate (lowy ⇄ hickey) → code-police → CI → evidence). ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
argument-hint	<issue-url | prompt>

Be

Take a task to a shipped, reviewed PR. Unlike /do (autonomous start to finish), /be opens with a short interview — and is then fully autonomous, exactly like /do, from §1 onward. The interview is the only place /be asks the user anything; after it, make sensible defaults and keep moving — no further AskUserQuestion, no stopping between steps. The single exception is the optional plan-review pause in §1, and only when "plan first" was chosen. Concise by design — defer mechanics to the skills it calls.

Requires Claude Code's Workflow and Skill tools. Under codex/opencode the review fan-out degrades to sequential subagents.

0. Interview (the differentiator)

Before any work, ask the user via AskUserQuestion (one call, batched):

• Plan first? — write an HTML plan to docs/plans/<slug>.html for review before implementing, or implement straight. Default: straight, unless the task is large/ambiguous. (If the prompt already points at an existing docs/plans/*.html, skip this question — that file is the plan of record; reuse it.)