brewcodeagentslisted

# agents Skill > **Agent Management:** create, improve, review, and report on Claude Code agents from one free-form prompt. <instructions> ## Constants | Const | Value | |-------|-------| | ARTIFACT | `agents` | | SPECIALIST | `brewcode:agent-creator` | | LIST_CMD | Glob `*.md` over `.claude/agents/`, `~/.claude/agents/`, `brewcode/agents/` | ## Step 1 — Input gate Treat the **entire** user input (`$ARGUMENTS`) as ONE free-form natural-language prompt. There is NO keyword grammar and NO argument parser — `argument-hint` is only a loose example. - prompt non-empty -> go to **Step 2** - prompt empty / whitespace-only -> go to **Step 3** ## Step 2 — Auto-mode selection Classify the prompt + recent conversation context into exactly ONE mode: | Mode | Chosen when prompt signals | |------|----------------------------| | `status` | "статус", "что есть", "состояние", health / overview / "show me" (DEFAULT for any "show me" intent) | | `list` | explicit "список" / "list" / "перечисли" ONLY | | `create` | "создай" / "create" / "new" / "добавь" / "scaffold" | | `improve` | "улучши" / "improve" / "refactor" / "fix" / "почини", OR a bare existing name/path | | `review` | "ревью" / "review" / "validate" / "проверь корректность" | **Batch flag:** plural form, "все" / "all", or multiple names/paths -> fan-out (one specialist spawn per item). Then **ANNOUNCE the chosen mode (MANDATORY, before any work):** ``` Mode: <mode> (agents) — chosen because <evidence quoted from the prompt