A free guide by New Money School
Before July 7th
Fable 5 is included in your plan until July 7th, then it becomes pay-per-use. This is the exact playbook to spend that window building things you keep forever, with the full copy-paste prompts for all three.
Why This Matters
Through July 7th, Fable 5, the most powerful model, is included in your plan. After that it is pay-per-use. So the smart play is not to burn this window on little tasks a cheap model can do. It is to have your smartest model build durable assets, things that keep paying off long after the meter turns on. Set your effort to high or max so Fable goes all in.
Do these in order. Move 1 makes everything you already do better. Move 2 clears the things you have been stuck on. Move 3 builds a plan a cheaper model can run for months. Each one hands you something you keep.
Move 1Upgrade Every Skill & Workflow You Have
Fable writes the most detailed, precise skills and instructions of any model, and an upgraded skill keeps working even after you drop back to Opus 4.8. So point it at everything you already use and have it make each one sharper. How you do this depends on where your skills live.
Step 1
Know where your skills actually live
In Claude Code, your skills and instructions are files inside 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 custom instructions. You will upgrade them a little differently depending on which you use.
Step 2
Put Fable 5 on them
In Claude Code, switch to Fable 5 with /model, set /effort high, and use the first prompt. It reads and rewrites your files directly, you do not paste anything. In the Claude app, open one skill (or your Project instructions) at a time and use the second prompt on that single one.
Step 3
Apply the upgrades
In Claude Code it edits the files in place, just review the changes and keep them. In the app, copy the improved version it gives you and paste it back into that skill or your Project instructions.
If you use Claude Code — reads and rewrites your filesCopy
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.
If you use the Claude app — one skill at a timeCopy
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 2Finally Solve The Roadblocks You're Stuck On
Throw your hardest, most annoying problems at this one, the ones you have been stuck on for weeks. The trick (shoutout to Brad in my AI Challenge) is to give Fable the full context by packaging the whole stuck conversation and moving it somewhere fresh, where your smartest model has a clean head and room to actually think.
Step 1
In the stuck chat, capture everything
Run the first prompt right in the conversation where you hit the wall. It turns the whole thing into a complete markdown handoff: every attempt, every error, every dead end.
Step 2
Start fresh on Fable 5, maxed out
Open a new chat or project, select Fable 5, set effort to high or max, and paste in the markdown from Step 1 so it starts with full context and none of the old baggage.
Step 3
Tell it to solve it
Run the second prompt. It finds the real root cause, weighs the best approaches, and either solves it outright or hands you the next three concrete steps, without pestering you for things it can figure out itself.
Prompt 1 of 2 — Capture the full context as markdownCopy
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)Copy
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 3Build A Plan A Cheaper Model Runs For Months
This is the one people sleep on. A plan written by the best model becomes an asset your cheaper models can execute against for months, they inherit the quality of the thinking without the price of the thinker. So have Fable build the strategy once, then let Opus, Sonnet, or Haiku run it day to day.
Step 1
Pick what to plan
A content plan, a project roadmap, a launch plan, a hiring plan, whatever has been living in your head. The bigger and more repeatable, the better.
Step 2
Have Fable build it in full
On Fable 5 at high effort, run the first prompt. It asks you a few sharp questions first so the plan is actually yours, then builds a phased plan with clear acceptance criteria and steps small enough that a simpler model can execute each one.
Step 3
Hand execution to a cheaper model
Save the plan. From here on, drop it into a cheaper model with the second prompt whenever you want the next piece done. Your expensive thinking is already banked.
Prompt 1 of 2 — Build the durable plan (use Fable 5)Copy
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 — Hand a step to a cheaper modelCopy
Here is a plan my most capable model built. Execute the next step exactly as written, meet its acceptance criteria, and flag anything that does not line up with the plan. Do not redesign the strategy, just run it well and give me the finished deliverable.
Here is the plan, and the step I want done:
[paste the plan, and name the step]
Do It Before July 7th
All three of these are worth the most while Fable is still included in your plan. After the 7th you would be paying per use to do this, and these upgraded skills, solved problems, and plans keep working long after. Set effort to high or max and go build.