proposing-deepeninglisted

# Proposing deepening — find where the codebase went shallow, propose the fix An existing codebase was not written under the module-depth rule. This skill finds where that hurts most and proposes a bounded set of retrofits. It **analyses and proposes; it never changes code.** Announce at start (pt-br): "Vou varrer o código e trazer no máximo 5 candidatos a reforma." All reasoning and identifiers in English. Every message to the operator is **pt-br, product-language** — he decides on impact and risk, never on class names. --- ## Hard precondition — LOCAL only, never headless The output of this skill is a **question to the operator** ("qual, se algum, vale reformar?"). In a headless run there is nobody to answer, ending a turn on a question kills the run, and an unanswered candidate list would be picked up by an autonomous engine as work to do. So: **if the session is not interactive, refuse immediately and say why.** Headless is active when **any** of these holds: - the trigger prompt says to run **autonomously** / "sem perguntar" / "without asking" — the VPS cron dispatcher always prepends a fixed prefix of this shape; - any of the union signals is non-empty: ```bash printf 'remote=%s notify=%s obs=%s\n' \ "$CLAUDE_CODE_REMOTE" "$HARNESS_NOTIFY_PROJECT" "$HARNESS_OBSERVABILITY_RUN_PATH" ``` > `$CLAUDE_CODE_REMOTE` alone is **not** a sufficient test. The VPS cron dispatcher > (`core/vps/cron-a-dispatch.mjs`) **deliberately unsets it** so the run stays "he