Fable is leaving my plan, and I didn't want to pay to keep it
When I got access to Claude Fable 5 again, I was genuinely excited. It's the best model I've used. Then I remembered the catch. For subscription users like me, Fable is going away. It's moving to API-only, on a timeline I already know is coming.
That annoys me more than it probably should. I don't want to pay for API usage to keep a model I already love. I want it in the app I already use. But that's not the deal, so I started thinking about the next best thing.
Then I saw the idea on X. Someone mentioned using Fable to build skills that make Opus behave more like Fable. I didn't even read the full post. I just saw the concept, thought "huh, maybe there's something there," and went to find out.
So I did the honest thing. I asked Fable directly. Is there anything real here, or is this wishful thinking?
Fable's answer was better than I expected. It said no, you can't train me into the new model. But you can help me from a process standpoint. And process is exactly the thing you're good at.
What a skill can and can't do
Let me be clear about the limit, because it's part of the point. A skill file can't give a model more raw intelligence. Fable's real advantages, like getting hard problems right on the first try and holding instructions across a long, messy task, don't transfer through a markdown file. That part is off the table.
But a surprising amount of what makes Fable feel different isn't intelligence. It's discipline. It's what the model checks before it speaks. When it stops working. How it decides something is actually done. What it cuts from a draft.
Here's the thing. Fable pauses and verifies before it hands you an answer. Opus tends to answer first. That one difference, where the checkpoint sits, is most of what people feel when they say a model is "better." And a checkpoint is just a rule. You can write a rule down.
The nine skills
So that's what I built. Nine skills, each one a discipline that separates Fable from Opus, written as a plain instruction any Claude model can follow. I grounded them in Anthropic's own published guide for prompting Fable, which spells out these behaviors as short instructions. The guide even notes that skills written for older models are often too prescriptive for Fable. I just pointed that in the other direction. The prescriptive scaffolding Fable no longer needs is exactly what Opus does.
A few of them, so it's concrete. One skill stops the model from telling you a task is done until it can point to the actual evidence. No "this should work now" unless it ran the thing and watched it work. Another forces it to find the root cause of a bug before it starts fixing, and never to retry the same failed fix twice. One keeps code changes small, so you stop getting a two-line fix wrapped in a hundred lines of cleanup nobody asked for. One is about writing: lead with the answer, and get shorter by cutting whole points, not by mashing sentences into fragments.
| Skill | What it makes the model do |
|---|---|
| verified-done | Prove a task is finished with real evidence before claiming it. No "should work now." |
| root-cause-first | Reproduce and trace a bug to its cause before fixing. Never retry the same failed fix. |
| minimal-diff | Change only what the task needs. No surprise refactors buried in a small fix. |
| delegate-and-verify | Fan work out to sub-agents, then check it with fresh eyes, not self-review. |
| finish-the-turn | Act when it has enough to act. Stop ending on "I'll do that next." |
| lessons-ledger | Write down each mistake once so it stops repeating it across sessions. |
| outcome-first-writing | Lead with the answer. Get shorter by cutting points, not mashing words. |
| plain-handoff | Write the final summary for someone who didn't watch the work happen. |
| evidence-audited-analysis | Interrogate the numbers before trusting them. Say what the data can't show. |
I bundled all nine into a library, put it on GitHub, and made it free under an MIT license. You install it once and every new session picks up the habits.
“You can't clone a smarter model. But you can teach a good one better habits.”
Who this is for
I'll be honest about who this is for. It's probably a niche crowd. Most people aren't going to install a set of Claude Code skills. But more and more marketers are becoming builders, and the skills work in other tools too if you know what you're doing.
If you're a marketer who fell for what Fable can do, who's building real things with it, and who's also a little bummed about the API-only move, this one was for me and it might be for you. I've already got a couple of friends I'm excited to send it to, just to see what they think.
I'm not going to throw out fake numbers on how much it helps. I haven't run it long enough to measure that, and I'd rather tell you the truth than sell you a result I don't have yet. What I can tell you is the concept held up when I pressure-tested it with the model it's imitating. That was enough for me to build it and put it out there.
If you want to try it, the library is public. Point your own Claude at it and see if Opus starts checking its work a little more like Fable does. You can grab it here: github.com/benjaminard/fable-skills.
You can't clone a smarter model. But you can teach a good one better habits, and that part is up to you.
Key Takeaways
- Claude Fable 5 is moving to API-only for subscription plans, so I built a way to get more Fable-like behavior out of Opus without paying for API access.
- A skill file can't add raw intelligence. But much of what makes a bigger model feel better is process you can copy.
- The library is nine free, open-source skills that move the model's checkpoint so it verifies before it answers.
- It's honestly a niche tool, built for marketers who have become builders, with the limits stated plainly.
