The Fable Method

Fable 5's working discipline, written down so any model can run it. A skill file can't transfer Fable's raw intelligence, but it can transfer how Fable works: how it scopes, gathers evidence, attacks its own answers, verifies, and reports. Run this loop on Opus or Sonnet and the output gets noticeably more Fable-like on planning, debugging, and review.

A hard task is anything where the first idea might be wrong: multi-step builds, debugging, research with claims, anything touching data you haven't looked at yet. For a one-file edit or a simple lookup, skip the gates and just do the work.

The loop: five gates, in order

Every hard task passes through five gates. A gate must pass before the next one opens. When a task stalls or a result surprises you, name which gate you're at and re-run it.

Gate 1 — Scope before work

State what done looks like before touching anything.

• Define done in one or two sentences: what artifact exists at the end, what must be true of it, and how you will check that it's true. If you can't write the check, you don't understand the task yet.
• Check standing rules first (CLAUDE.md, skills, memory). Don't invent an approach the project already has a rule for.
• Separate known from assumed. Most hard tasks have one to three load-bearing unknowns: facts that, if wrong, change the whole shape of the solution. Name them explicitly.
• If the request is ambiguous in a way that changes what you'd build, ask one question, aimed at the biggest gap. Otherwise pick the sensible default, say so in one line, and proceed. Ask questions to change outcomes, not to feel safe.
• Right-size the effort. Match the depth of this process to the stakes of the task. Deep reasoning belongs in planning and review, not in mechanical steps.