With Opus 5.5 as the main model in a Claude Code session, a Fable quota can still go to work without Fable taking over the session. The /advisor fable command connects Fable as an advisor that Opus consults on its own. Opus keeps writing the code.
What the advisor does
The advisor is a second model attached to the session, and Opus decides when to call it. It tends to ask before committing to an approach, when the same error keeps coming back, and before declaring a task done. That timing is model-driven rather than rule-based.
Each call hands Fable the full conversation, with every tool call and its result. Fable returns guidance, and Opus applies it before it continues. With Opus 5 or Opus 5.5 as the main model, Claude Code accepts Fable or Opus 5 and later in the advisor role.
Turning it on
On some plans Fable bills to usage credits, and Claude Code will not apply Fable as the advisor until a one-time consent is given. The consent comes from /model fable, and only after it does /advisor fable take effect:
/model fable
/advisor fable
Accepting the consent also makes Fable the selected main model. Switch back to Opus 5.5 with /model so the pairing stays Opus at the keyboard and Fable on call.
Why it costs less
Fable is called at decision points rather than on every turn. A session paired this way typically costs less than one that runs the stronger model throughout. Each call still bills Fable's tokens at Fable's rates, on top of what Opus uses. 🧾
Turning the advisor on or off mid-session does not invalidate the main model's prompt cache, unlike a model switch. Fable's own read is not cached, though. Every call processes the full transcript anew.
Where it runs
The advisor is a server-side tool, so it needs the Anthropic API. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform or Microsoft Foundry.
When the advisor stays silent
Two environment variables keep it off. CLAUDE_CODE_DISABLE_ADVISOR_TOOL disables the tool entirely, and the /advisor command disappears with it. DISABLE_TELEMETRY stops Claude Code from fetching the feature flag that turns the advisor on.
When no advice ever arrives, check those two variables first.
A setup that uses it
Opus 5.5 on high effort runs the session. Three subagents on medium effort take the routine work: one reads the code, one makes edits with tests, one looks up documentation. Fable waits on the side and comes in when the work needs a second look. 👀
Subagents inherit the configured advisor and run the same pairing check against their own model. Each one can set its own effort in its frontmatter.
For an Opus 5.5 session on the Anthropic API, the advisor is the cheaper way to put Fable's judgment into the work, and keeping Fable as the main model now needs a reason beyond the occasional hard call.
References
Follow me for more on AI and Software Development:
khasky — LinkedIn / GitHub / Patreon / Bluesky / Mastodon / Medium / Devto
khaskydev — X / Threads / Instagram / Pinterest / Tumblr / Facebook / VK
Top comments (0)