メニュー
Use when improving Maestro token efficiency, Codex fit, benchmark context hygiene, or agent orientation without weakening verification quality.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Toggle Maestro terse narration level (lite, full, ultra, off) via the settings CLI
Token-efficient terse narration mode. Cuts agent explanation tokens while preserving requested artifacts. Levels: lite, full, ultra. Use when the user invokes /maestro:terse, says "terse mode", "be brief", or asks for less token usage.
Maestro Frontier local multi-CLI fusion engine - compose or choose a read-only model panel, inspect the catalog, arm, disarm, or run it
Direct Maestro command hub for Codex slash menu: compose or choose a Frontier model panel, settings, terse, and update
Maestro Frontier local multi-CLI fusion engine — switch mode, or run a prompt through the panel
View and change Maestro toggles (terse, frontier, context-bar, discipline, verify) via the settings CLI
SOC 職業分類に基づく
| name | maestro-token-efficiency |
| description | Use when improving Maestro token efficiency, Codex fit, benchmark context hygiene, or agent orientation without weakening verification quality. |
Use this skill for Maestro repo changes that affect agent context, instruction loading, benchmark search hygiene, or Codex behavior.
docs/agent-map.md first for navigation.rg --no-ignore for raw stream audits.docs/codex.md and current
official Codex docs before changing durable guidance.AGENTS.md/adapters.Before completion after edits, run:
npm test
npm run lint
npm run bench-verify