Update — July 24, 2026: ClaudeDevs' zoom / crop cookbook — Fable 5 Chartography 29%→73% with a full-res lean-in tool. Pair with this advisor/executor split when vision QA is the bottleneck.
Update — July 22, 2026: Cursor's swarm research puts the same planner/worker split on a SQLite rebuild — Opus+Composer ≈ $1.3k vs all-GPT-5.5 ≈ $10.5k at similar quality: swarm model economics.
Sonnet 5 executes. Fable 5 directs. That is Anthropic's recommended split for long coding and creative builds — not two sessions you switch manually, but one Claude Code session where Sonnet runs tools and Fable consults at decision points via the advisor tool.
The @ClaudeDevs July 8 benchmarks put numbers on it: ~92% of Fable solo on SWE-bench Pro at ~63% cost when Fable advises ~once per task. This guide is the how-to: /advisor setup, pairing rules, prompt templates (including a game-dev example), and when to use advisor vs opusplan vs subagents.
TL;DR — setup in 60 seconds
| Step | Command / setting |
|---|---|
| Requirements | Claude Code v2.1.170+ · Fable 5 access · Anthropic API (not Bedrock/GCP/Foundry) |
| Main model | /model sonnet → Sonnet 5 executor |
| Advisor | /advisor fable → persists to advisorModel |
| One-shot launch | claude --advisor fable |
| settings.json | "advisorModel": "fable" |
| Turn off | /advisor off or CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1 |
| See advice | Ctrl+O on Advising lines in transcript |
Official docs: Escalate hard decisions with the advisor tool · The advisor strategy · API advisor tool
Model pairing — what Anthropic allows
From the Claude Code advisor docs:
| Main model | Accepted advisors |
|---|---|
| Sonnet 5 | Fable, Opus, Sonnet 5 |
| Sonnet 4.6 | Fable, Opus, Sonnet |
| Opus 4.7+ | Fable, Opus 4.7, Opus 4.8 |
| Fable 5 | Fable only |
Your target pairing: Sonnet 5 main + Fable advisor — one of Anthropic's common pairings: "Fable 5 guidance at decision points without running Fable 5 throughout."
Subagents inherit the configured advisor if their model satisfies the pairing check.
Division of labor — executor vs advisor
| Role | Model | Job |
|---|---|---|
| Executor | Sonnet 5 | Write code · fix bugs · run tools · ship iterations · most tokens |
| Advisor | Fable 5 | Architecture · pacing · UX · progression · quality review · unblock after 2+ failed attempts |
Same framing as Matt Shumer's Workbench playbook: goal + bar for the project, execution for the fast model — except Anthropic wires Fable in as a server tool instead of you pasting advice manually.
Prompt principle: Tell Sonnet it is the implementation agent. Tell it to consult the advisor proactively — not only on errors, but on creative, architectural, pacing, progression, and UX decisions when multiple valid directions exist.
Prompt template — executor instructions
Paste this at the top of a long session (game, refactor, greenfield app):
You are the implementation agent (Sonnet 5).
## Your job
- Execute code, fix bugs, implement systems, ship working improvements.
- Do not stop to overthink — keep moving.
- Never ask me for implementation decisions unless truly blocked.
## Advisor (Fable 5)
Consult the advisor:
- Before any major feature or architecture change
- Before progression, boss, AI Director, UI redesign, or rendering systems
- Before marking a task complete (quality review)
- After 2+ failed attempts on the same issue
- Whenever multiple valid design directions exist — proactively, not only on errors
Flow: consult advisor → pick strongest solution → implement.
Advisor owns direction. You own execution.
Add project-specific tasks below (combat, weapons, story acts, etc.). Keep house rules and definition of done in the same doc — same pattern as Field Guide to Fable unhobbling: give Sonnet room to execute, fence with rules Fable helps refine.
Worked example — indie game AAA pass
A common failure mode: one giant prompt to Fable solo — expensive, or one giant prompt to Sonnet solo — shallow UI and weak systems design. Advisor split maps cleanly:
| Workstream | Executor (Sonnet) | Advisor consult (Fable) |
|---|---|---|
| Cooldown UI on abilities | Implement HUD timers | Review readability + juice before merge |
| Weapon attach to hands | Fix transforms, sockets | Review animation pipeline + sprite sheet plan |
| Weapon orientation (mace handle) | Patch all weapon prefabs | Confirm convention once for all weapons |
| Boss drops + legendary weapons | Data model + drop tables | Pacing: when Thor-like weapon unlocks |
| AI Director | Implement telemetry + spawn logic | Balance philosophy — fun not max difficulty |
| Story acts vs "level 20" | Act flags, checkpoints | Narrative structure + checkpoint art briefs |
| Asset gen (sprites, audio) | Subagents or APIs in parallel | Art direction bar before replacing placeholders |
| UI redesign | Rebuild HUD, game over, menus | UX review against target (Hades / Dead Cells tier) |
Delegate assets without blocking code: Sonnet keeps implementing with placeholders while image/audio agents run — same multi-agent pattern as loop engineering and official /loop guidance.
Story note: Acts (Escape → Mutation → Hunt) beat numbered levels. Advisor helps define narrative checkpoints; Sonnet wires when they trigger. Use image APIs at act boundaries — advisor drafts what each panel must communicate.
Enable advisor — three ways
1. /advisor command (recommended)
/model sonnet
/advisor fable
Saves to user advisorModel. If org availableModels blocks Fable, pick an allowed advisor or request access — see Fable 5 status.
2. settings.json
{
"advisorModel": "fable"
}
3. Launch flag
claude --advisor fable
Session-only; overrides saved setting for that run.
Full command reference: Claude Code commands — /advisor.
When Claude calls the advisor
Anthropic docs: Claude decides when — tends toward:
- Before committing to an approach
- Recurring errors (same failure twice)
- Before declaring done
You can force rhythm in prompts: consult the advisor before you continue — same as any tool request.
In session UI: Advising line with model name → Ctrl+O for full Fable guidance. Sonnet follows advice unless evidence contradicts it (file contents, failed step) — then it surfaces the conflict.
Cost: Advisor tokens bill at Fable rates; executor at Sonnet rates. Advisor runs at decision points, not every turn — see cost breakdown. Track with /usage.
Advisor vs opusplan vs subagents vs switching model
| Approach | When stronger model runs | Best for |
|---|---|---|
| Advisor (this guide) | Decision points mid-task | Long builds — mostly Sonnet turns, Fable at forks |
| opusplan | Plan mode only, then Sonnet executes | Up-front plan you approve once |
| Subagents | Whole delegated subtask on chosen model | Parallel asset gen, isolated modules |
/model fable | Every subsequent turn | When every turn needs frontier reasoning |
For month-long game polish: Sonnet + Fable advisor + subagents for assets beats Fable solo on cost and beats Sonnet solo on direction.
For API pipelines (not Claude Code), use advisor_20260301 — API setup in our orchestrator post.
Requirements checklist
- Claude Code v2.1.98+ (
claude update) - v2.1.170+ for Fable advisor
- Fable 5 access for your org/account
- Anthropic API billing or subscription — advisor not on Bedrock / GCP / Foundry
- Main model Sonnet 5 (or other compatible executor)
- Prompt tells Sonnet when to consult advisor proactively
Anti-patterns
| Mistake | Fix |
|---|---|
| Running Fable main for every file edit | Switch to Sonnet main + Fable advisor |
| Advisor only on errors | Add proactive consult for design forks |
| Asking you for implementation choices | Prompt: consult advisor first |
| Sonnet 4.6 advisor with Sonnet 5 main | Rejected — use Fable or Opus 4.7+ |
| Expecting advisor on Bedrock | Use Anthropic API path only (for now) |
Related on explainx.ai
- Claude zoom tool — Chartography Fable/Sonnet gains
- Claude Code desktop in-app browser — verify UI after advisor-planned redesigns
- Cursor agent swarm economics — planner/worker cost curves
- Fable 5 advisor & orchestrator patterns — @ClaudeDevs benchmarks
- Claude Code loops — official @ClaudeDevs guide
- Claude Code commands —
/advisor,/model - Field Guide to Fable — Thariq Shihipar
- Matt Shumer — goal/bar loops (GPT-5.6-Sol / Fable)
- Claude Code model vs effort
- Is Fable 5 back? — access hub
- Fable 5 top use cases July 2026
Official: Advisor tool — Claude Code docs · Advisor strategy blog · API advisor tool
Pairing rules, version gates, and availability reflect Anthropic's Claude Code documentation as of July 2026. Org allowlists and Fable access may limit /advisor fable on your account — verify with /advisor picker output.