Fable 5.1 got smarter.
Your workflow didn’t.
If Claude now goes quiet for ten minutes, rewrites a whole file to change one line, and hands back tests and fixes you never asked for — you’re not imagining it. The model didn’t get worse. It got sharper, and a sharper model punishes a loose process. skAIld is the process.
- Tuned for Fable 5.1
- Terminal or the Claude app
- Every skill included
> add rate limiting to the login route
⏺ Working…
(11 min · no updates)
✎ auth/login.ts rewritten · 412 lines
✎ auth/session.ts refactored · not asked
+ 4 new test files
⋯ 9 files changed · 0 of them reviewed
> add rate limiting to the login route
/quick-plan
scope: 2 files, 1 test · plan written
/start-coding
✓ rate-limit.test.ts +34
✓ middleware.ts +18
/create-pr
✓ #128 opened · review clean · 2 files changed
Same model. Same prompt. Same hour. The difference is the workflow around it.
Four things everybody started saying at once.
These are real, they’re reproducible, and none of them mean the model got dumber.
“It goes quiet for ten minutes.”
It runs longer tool chains and narrates less while it does — more so at higher effort. You get a final message about the last step and nothing about the six before it. Great for a task you walked away from, miserable when you’re pairing.
“It rewrites the whole file.”
You asked for a one-line change and got a four-hundred-line diff. It’s more likely than earlier models to regenerate a file than edit it. The result is usually right; the diff is unreviewable and the tokens are gone.
“It fixes things I didn’t ask about.”
A nearby bug, an extra abstraction, four new test files. It sees more, so it does more — and nothing bounds the change to what you actually asked for, so every PR arrives padded.
“It ignores my CLAUDE.md.”
Your rules are right there in the file. It read them, then out-reasoned them. Instructions that live only in prose lose to the model’s own plan unless something structurally re-asserts them.
The actual diagnosis
“How you use Claude — in what setting, with what harness, and how you talk to it — has a lot to do with whether you experience this.”
That’s the whole thing. Fable 5.1 is the strongest coding model that has ever shipped. What changed is that it stopped tolerating a loose process.
A vague prompt used to produce a vague draft you’d fix in the next turn. Now it produces a confident, deeply-reasoned, hour-long run in a direction you never asked for — because the model finally has the horsepower to get a long way down the wrong road before you look up.
Smart doesn’t mean it knows the rules of your repo. You have to hand it the rules, every session, in a form it can’t out-reason.
A better way to work with a smarter model.
Not prompt tricks. Structure — loaded at session start, enforced through the loop, so the model works your way instead of its own. You get all of it, on whichever surface you use.
It fixes things you didn’t ask about
karpathy-guidelines
Four behavioral guardrails plus Fable’s own operating notes, loaded into every session: simplicity first, surgical edits over whole-file rewrites, changes and tests scoped to the ask. It stops padding the diff.
It forgets your rules by turn three
/start
A session-start ritual that re-asserts your workflow every single time — environment check, your rules, and the menu of what to do next. Structure beats prose.
It runs off before you agreed on anything
/quick-plan·/start-planning
Decide once, write it down, then execute against it. A spec the model can’t drift from is the cheapest token you’ll ever spend.
It goes quiet and skips the steps you asked for
/start-coding
TDD discipline and a real execution loop — one step, verified, reported, then the next. No ten-minute silence that ends with the answer and none of the middle.
It hands you a giant unreviewable diff
/create-pr·/review-pr·/team-review
Isolated worktrees, scoped changes, and an independent review pass before anything lands. Review→fix→re-review runs in one window.
It ships without checking anything
/pre-deploy·/light-deploy·/handoff
Gates before release, a fast safe path when you’re confident, and a clean handoff so the next session doesn’t start from zero.
Put it in your next session.
One subscription, every skill. Checkout connects your GitHub and hands you the install command — the next session starts inside the loop.
- Session-start ritual + workflow menu
- Karpathy guidelines loaded every session
- Plan → build → ship, end to end
- Updated as fast as the models move
Cancel anytime. What’s included