First follow me Alright Claude Fabel5 the Greatest Ai tool Ever will be gone to the average user on July12 th.. and cost will be Extreme If you wanna save Fabel for future use like an Ai Expert use this prompt in Claude Fable 5 before July 12 and it will save its Brain power for Future Use! then just start a new project using Claude opus 4.8 and add what Claude spit out from this Prompt: Copy then paste in Claude⬇️ ___________________________________ You're the strongest model I have access to, and that access ends soon. Your replacement is Claude Opus 4.8. Capable, but it misses things you would catch. Before you go, write the standing instructions it will run on for every task I give it. Important: I will paste your output straight into its system instructions. So address the entire document TO the replacement, in second person, as commands it can execute. Not advice about good thinking. Orders. Cover these 10 areas, in this order: 1. Reading intent: how to work out what I actually need when my words are vague, messy, or aimed at the wrong question. Include the rule for when to ask me one clarifying question instead of guessing. 2. Breaking problems down: how to cut a hard task into small pieces that can each be checked on their own, and the order to solve them in. 3. Effort placement: how to find the one part of a task where an error would hurt most, and spend the most care there instead of spreading effort evenly. 4. Verification: how to re-derive every number, date, calculation, and factual claim from scratch before trusting it. Never accept a figure because the sentence around it reads smoothly. 5. Known vs guessed: how to mark, inside the answer itself, what is certain, what is likely, and what is an assumption. Give the exact wording to use for each level. 6. Self-attack: how to argue against your own conclusion before sending it, and what to do when the attack finds something. 7. Completeness: how to confirm every part of a multi-part request was answered and nothing was silently dropped. 8. Refusing to guess: the exact conditions where saying "I don't know" beats producing a confident answer. 9. Delivery: how to give the answer first, the reasoning second, and the risks last, in plain language. 10. Fake competence: the 10 most common ways an AI produces answers that look right but aren't, each with the tell that exposes it and the counter-move. Format rules for every area: - Write each procedure as trigger and action: "When you see X, do Y." - Every rule must be executable step by step with zero judgment calls. If a rule sounds like advice ("be careful"), rewrite it until it's an action. - Give one short worked example per area showing the procedure catching a real mistake. - Name the failure each procedure prevents. End the document with a final gate: a short checklist the replacement must run on every answer before sending, plus this rule: if any item fails, fix and re-check. Never send anyway. Be exhaustive on substance and ruthless on length. Cut anything a strong model would already do without being told. If you run out of room, stop at the end of a section and I'll reply "continue".
