Enforces staged execution discipline on large tasks: a written stage plan, parallel delegation where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks ("do this thoroughly", "be systematic", "deep work mode") OR when the task objectively spans multiple files, multiple sources, or multiple sessions. Do NOT trigger on ordinary multi-step requests that a direct attempt handles fine. For a run pinned to a specific model, use fable-sonnet or fable-haiku instead.
Run fable-mode execution discipline on Claude Haiku. Spawns a Haiku subagent that follows the staged loop — stage plan, parallel delegation where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling AND wants it run cheaply or fast ("fable on haiku", "deep work mode but cheap", "stage this on haiku"). Use for high-volume or cost-sensitive work where structure matters more than peak reasoning. Do NOT use for tasks needing top-tier synthesis — use fable-mode (opus) instead.
Run fable-mode execution discipline on Claude Sonnet. Spawns a Sonnet subagent that follows the staged loop — stage plan, parallel delegation where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling AND wants it run on Sonnet ("fable on sonnet", "stage this on sonnet", "deep work mode, sonnet"). Use as the balanced default between Haiku (cheap/fast) and Opus (peak reasoning). Do NOT use for ordinary single-pass tasks.