← Back to all free guides
A free guide by Mariah Brunner ↗ INSTAGRAM ↗ TIKTOK

3 Fable
Moves

Fable costs a lot more than the other Claude models, so I only use it for work that keeps paying off. Here are the three moves I make with it, with every copy-paste prompt.

Fable 5.1 is the model Anthropic points to for "demanding reasoning and long-horizon agentic work." It is also the slowest and priciest. (Anthropic models overview)

The free window I filmed this video about ended in July. Here is how access works now (Anthropic help center):

  1. Max and Ultra: up to 50% of your weekly limit can go to Fable at no extra cost. Past that, you pay with usage credits or switch models.
  2. Pro: Fable runs on pay-as-you-go usage credits.
  3. Free: no Fable.

So don’t burn it on small tasks Opus 5.5 or Sonnet 5.5 can handle. Have Fable build assets you keep using after you switch back. Do these in order.

Move 1: Upgrade Your Skills

An upgraded skill keeps working after you switch back to a cheaper model. So point Fable at everything you already use.

01

Find where your skills live

In Claude Code, they are files in your project: your CLAUDE.md, anything in .claude/skills, and your subagents in .claude/agents. In the Claude app, they are your saved skills and your Project instructions.

02

Switch to Fable on high effort

In Claude Code, run /model fable, then /effort high (or /effort max). In the app, click the model name next to the send button, pick Fable 5.1 (look under More models if you don’t see it), then click Effort and choose High or Max. (How to change model and effort)

03

Run the prompt and keep the upgrades

Claude Code edits the files in place, so review the changes and keep the good ones. In the app, paste one skill or your Project instructions at a time, then paste the upgraded version back where it came from.

Claude Code: reads and rewrites your files
Go through every skill, workflow, and instruction file in this project: my CLAUDE.md, everything in .claude/skills, and my subagents in .claude/agents. Read each one, then for each: 1. Tell me in one line what it is for. 2. Audit it hard. Where is it vague, incomplete, or likely to give inconsistent results? Look for missing context, undefined terms, no examples, no defined output format, and no rules for what it should never do. 3. Rewrite the file in place to fix all of that: specific instructions, a clear step-by-step process, the exact output format it should produce, one or two concrete examples of a great result, and explicit do-nots. Keep my intent and my voice. When you are done, give me a short summary of what you changed in each file, tell me which skills overlap or should be merged, and name the one skill or workflow I am clearly missing for the kind of work I do. Don't ask me anything until you have done all of this.
Claude app: one skill at a time
Here is one of my skills (or my Project's custom instructions). Make it dramatically better. 1. Tell me in one line what it is for. 2. Audit it hard. Where is it vague, incomplete, or likely to give inconsistent results? Look for missing context, undefined terms, no examples, no defined output format, and no rules for what it should never do. 3. Rewrite it into a sharper version with specific instructions, a clear step-by-step process, the exact output format I want, one or two concrete examples of a great result, and explicit rules for what it should never do. Keep my voice and intent. 4. In a few bullets, tell me what you changed and why it will perform better. Give me the upgraded version as one clean, copy-paste-ready block so I can drop it straight back in. Here it is: [paste one skill, or your Project's custom instructions, here]
Move 2: Crack What You're Stuck On

Throw your hardest problems at Fable, the ones you’ve been stuck on for weeks. The trick (shoutout to Brad in my AI Challenge) is to package the whole stuck conversation and move it into a fresh chat, so Fable starts with full context and none of the clutter.

01

Capture the stuck chat

Run Prompt 1 inside the conversation where you hit the wall. It turns everything you tried, and every error, into one markdown handoff.

02

Start fresh on Fable

Open a new chat, pick Fable 5.1 on High or Max effort, and paste in the markdown from Step 1.

03

Tell it to solve it

Run Prompt 2. It looks for the root cause, weighs the options, then either solves it or gives you the next three steps.

Prompt 1 of 2: capture the full context
Turn this entire conversation into a single, complete markdown handoff so I can paste it somewhere fresh and a new AI can pick up with zero prior context and full understanding. Use these headers: - Goal: what I am actually trying to accomplish, and why it matters. - Current state: what exists right now, what is working, what is not. - What we have tried: every approach we attempted and exactly what happened with each one, including the precise errors, dead ends, and anything we ruled out and why. - Constraints and rules: anything that must stay true, the tools I am using, things I cannot change. - Key details: the specific files, names, numbers, links, or snippets that matter. - Where I am stuck: the exact roadblock, described precisely. Be thorough and specific. Do not summarize away any detail a fresh AI would need to actually solve this. Output only the markdown block, nothing else.
Prompt 2 of 2: solve it in the fresh chat
Below is the full context of a problem I have been stuck on. I moved it into a fresh chat on your most capable settings so you have room to actually solve it. Do this: 1. Diagnose the REAL root cause of the roadblock, not just the surface symptom. If my own assumptions about what is wrong look mistaken, say so directly. 2. Lay out the 2 to 3 best ways to solve it with the tradeoffs of each, then pick the one you would actually do, and why. 3. Then either fully solve it and give me the finished result, or, if it genuinely cannot be finished in one pass, complete as much as you can and give me the next three concrete steps in order. Rules: - Only stop to involve me if a payment, a login, or a decision that is truly mine to make is required. Otherwise keep going and solve it, don't ask me questions you can reasonably answer yourself. - Do not violate any of the constraints or rules listed in the context. - Lead with the solution, then show your reasoning briefly so I can follow it. Here is the full context: [paste the markdown from Prompt 1 here]
Move 3: Build A Plan A Cheaper Model Runs

This is the one people sleep on. A plan written by your best model becomes something Opus, Sonnet or Haiku can execute for months. They inherit the quality of the thinking without the price.

01

Pick what to plan

A content plan, a launch, a project roadmap, a hiring plan. The bigger and more repeatable, the better.

02

Have Fable build it once

Run Prompt 1 on Fable at high effort. It asks you a few sharp questions, then builds a phased plan with acceptance criteria and steps small enough for a simpler model to run.

03

Hand each step to a cheaper model

Save the plan in a Project. Whenever you want the next piece done, switch to Sonnet 5.5 or Opus 5.5 and use Prompt 2.

Prompt 1 of 2: build the plan (use Fable)
You are my strategist. Build me a detailed, durable [content plan / project roadmap / launch plan] for [describe the goal, the timeframe, and any context] that I can execute against for the next few months. Important: I am going to build this once with you now, then have a cheaper, less capable AI actually run it day to day. So it has to be clear and specific enough that a simpler model could follow it without you. Include: 1. Strategy: the overall approach and the single most important outcome we are driving toward. 2. Phases: the major phases in order, each with one clear goal. 3. Tasks: inside each phase, the specific tasks or deliverables, broken down small enough to hand to a simpler AI one at a time. 4. Acceptance criteria: for every task, spell out what "done well" actually looks like, so it is obvious when a piece is truly finished and not just technically done. 5. Inputs and risks: what I will need (tools, assets, info) and the bottlenecks or risks to watch for. 6. Rhythm: a simple weekly or daily cadence so I always know exactly what to work on next. Make it specific to my situation, not generic filler. Before you build it, ask me up to five sharp questions that would make the plan meaningfully better, then deliver the full plan. Here is my context: [paste your niche, audience, offer, current numbers, timeline, and any constraints]
Prompt 2 of 2: run one step (use a cheaper model)
You are executing one step of a plan that a more capable model wrote for me. Your job is to run it well, not to redesign it. Do this: 1. Find the step I name below in the plan. Restate its goal and its acceptance criteria in two or three lines so we agree on what "done" means. 2. List anything you need from me that is not in the plan or my notes. If nothing is missing, say so and keep going. 3. Do the step and give me the finished deliverable, ready to use. 4. Check your work against every acceptance criterion and mark each one Met or Not met, with one line on why. 5. Flag anything in the plan that no longer fits my situation, but do not change the strategy yourself. Rules: - Stay inside the plan's scope and constraints. - If a criterion is unclear, pick the most reasonable reading and tell me which one you picked. - Keep the deliverable first and your notes short, after it. Here is the plan: [paste the full plan] The step I want done: [name the step, plus any new notes or numbers since last time]

Good To Know

Fable costs 2.5 times what Opus 5.5 does per token, so it eats into your limit fast. If you’re on Pro, check your usage credits before a long session.