F*ck YES... Anthropic just released most INSANE cheat code for Claude Code: Fable 5.2 brain → while Sonnet 5.5 builds → Opus 5.5 checks → Haiku 5.5 swarms 1 min + /advisor command = up to 3.4x CHEAPER here's how to setup it: first understand how it works: •... This setup works for any tasks: Sonnet 5.5 builds, Opus 5.5 immediently check it, Haiku 5.5 swarm of agent search make research - at 80x cheaper per token than Fable • Fable 5.2 never writes code, it wakes up only 3 times: before a plan locks, when an error repeats, before "done" • you pay Fable prices only for decisions, the cheap models do all the rest here's how to setup it: 1 → run Claude update, Fable 5.2 needs Claude Code v2.1.321+ 2 → paste prompt below into Claude Code, it reads Anthropic's official advisor docs first 3 → it sets team at user level, so it works in every project: Sonnet main, Fable advisor, Haiku for subagents, a Opus checker 4 → it backs up your settings and shows every change as a diff before it applies it 5 → the part nobody tells you: there's one line that tells Sonnet 5.5 WHEN to call Fable. Without it, the advisor got called 0 times out of 198 in Anthropic's test full prompt + Anthropic's official advisor docs below Then read article to use Fable 5.2 at max out:show more

Antrhopic's cheat code: full prompt: "Set up my Claude Code as a 4-model team, at user level so it works in every project: - Sonnet 5.5 = main session. It builds: writes code, runs tests. - Fable 5.2 = advisor, the brain. It only advises, never writes code. - Opus 5.5 = checker subagent. It tests finished work and tries to break it, never edits. - Haiku 5.5 = search and research. It replaces the built-in Explore agent and is the default for other subagents. Before you change anything, read Anthropic's official docs: https: //code.claude.com/docs/en/advisor https: //code.claude.com/docs/en/sub-agents https: //code.claude.com/docs/en/model-config Use only the settings, fields and file formats those pages describe. If something below doesn't match the docs, follow the docs and tell me what you changed. Steps: 1. Check my Claude Code version. Fable 5.2 needs v2.1.321 or later. If it's older, run claude update, or tell me to. 2. In ~/.claude/settings.json: main model sonnet, advisorModel fable, env CLAUDE_CODE_SUBAGENT_MODEL haiku. Merge, never delete my settings. If my settings lower the main model's effort below its default, tell me: at lower effort the main model consults the advisor far less. 3. Create ~/.claude/agents/checker.md with model opus. It runs the tests, reads the diff and tries edge cases. It never edits code. It reports each real problem with the file, the line or command, and what it saw. 4. Create ~/.claude/agents/Explore.md with name Explore, model haiku and read-only tools (no Write, no Edit). A user subagent named Explore replaces the built-in one, which otherwise runs on my main model and ignores CLAUDE_CODE_SUBAGENT_MODEL. It finds files, greps, reads docs and returns short structured results. 5. Add to ~/.claude/CLAUDE.md: "Consult the advisor before you commit to an approach, when the same error comes back twice, and before you say a task is done. Run the checker before you call any task done. Send search and docs lookup to Explore. If a subagent must write code, give it model sonnet, never haiku. For a small task that fits in this session, skip subagents and do it yourself." 6. Fable as advisor needs a one-time usage-credit consent on some plans. If mine needs it, stop and tell me: run /model fable once, accept, then switch back with /model sonnet. Back up every file before you edit it. Show me all changes as one diff and apply them only after my yes. Done means: after a restart, Claude Code starts on Sonnet, /advisor shows fable, and /agents lists checker (opus) and Explore (haiku). End with three headings: Changed, Needs me, How to check it works. Under the last one tell me: an "Advising" line appears when Fable is consulted, Ctrl+O shows its advice, and /usage shows what it cost. Anthropic's official advisor docs: https: //code.claude.com/docs/en/advisor"

BRILLIANT. currently best way to use Claude Code right now, thank you for this! already send prompt to my Claude

I've already test this setup and believe me, this is gold!

wild that one missing line can leave the smartest model sitting there unused

true, and it's actually takes 1 min to setup

oh my, what a perfect find! sending to claude, thanks!

I really think everyone should install this

mega cool setup ngl, gonna send it tmrw to my claude, ty!

tmrw? bro it takes literally 1 min, just send link + prompt to Claude and that's it

aight aight, waking up from bed to test it

yeah, that's right decision...XD

Incorrect frame: the expensive model does everything. Correct frame: it thinks, the cheap ones work. Delegation 101 😄

Woow bro this is sick fr

that's actually super useful man! glad to help

ولكن ماذا عن الكاش اليس مفضل ان تبدأ جلسة جديدة عند كل وكيل او نموذج وتعطيه التقرير سواء كانت الخطة او التنفيذ ؟ كيف يعمل بالضبط

the real cheat code is still a good rules file. same model, way better output when it knows how you work

How would integrate with codex if you have both subscriptions?

Great video! Is this a real Claude Code session with a custom mod drawing the agent tree and the cost chart above the prompt, or an edited animation? If it's a mod, would you share it?

What happens to that 3.4x saving when the reviewer sends the same patch back twice?

hello world!!!

has anyone measured quality, not just cost? for my bot's backtests the expensive part is a wrong answer that looks right, not the tokens.

thanks for the writeup codila

using fable as advisor with sonnet building saves tokens while keeping top-tier logic

@grok analyse et dit moi si ça marche vraiment ?

Three wake ups for Fable is a clever way to keep token usage cheap

Thanks, I was searching for this setup. Gonna make it myself.

fable only waking up for 3 checkpoints is a smart way to spend it

Nice trick—what’s the latency and failure rate?

and for How can I set this up in the program, not with the terminal, but with the app?

3.4x cheaper and fable only wakes up 3 times thats the detail everyone misses