Helper agentssubagents
/advisor: Opus 5.5 works, Fable on call
Fable quota idle while Opus 5.5 does the work: Fable called in before a plan, when an error repeats and before ‘done’.
5.5K saves on X, as of Posted
Set up my Claude Code to match this tree:
1. For the three subagents, reuse fitting ones from ~/.claude/agents and .claude/agents, and propose new ones only for missing roles. Set each to model: opus and effort: medium. Leave any subagent that already sets a different model alone, and list it.
2. Set the main session's default effort to high with effortLevel in ~/.claude/settings.json.
3. Check for environment variables that turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, or DISABLE_TELEMETRY and anything else that stops flag fetching) and for CLAUDE_CODE_EFFORT_LEVEL, which overrides every subagent's effort. Report them; don't change them.
4. Add one rule to ~/.claude/CLAUDE.md: ask the advisor before committing to a big plan, when the same error shows up a second time, and before calling a long task done.
Show me the changes first. Don't edit any files yet. CLAUDE CODE AGENT TREE · OPUS 5.5 + FABLE ON CALL
Opus 5.5 · high - - - - Fable · on call
main session /advisor fable
|
| Opus usually calls it:
| · before picking a plan
| · when an error repeats
| · before calling it done
delegate to custom subagents
on medium
|
+-----------------------+-----------------------+
| | |
explorer worker researcher
| | |
Opus 5.5 · medium Opus 5.5 · medium Opus 5.5 · medium
| | |
read code edits + tests look up docs
| | |
+-----------------------+-----------------------+
|
back to main session · high
review + verify
Plan on high. Delegate on medium. Keep Fable on call.Next Send the prompt and the agent tree to Claude Code, then run /advisor fable there.
Once Opus 5.5 is your main model, don’t let your Fable quota sit idle. Run /advisor fable and Claude Code gets an advisor on the sidelines. Opus 5.5 keeps doing the work and usually calls Fable in at three moments:
- Before committing to a plan: is it right?
- When the same error keeps coming back: am I heading the wrong way?
- Before saying “done”: did I miss anything?
Fable reads the whole session and gives advice. Opus still writes the code. The full setup: Opus 5.5 on high runs the main session. Three subagents on medium split the rest: one reads code, one edits and runs tests, one looks up docs. Fable waits on the sidelines.
The advisor docs: https://code.claude.com/docs/en/advisor
Original is in an image, transcribed verbatim.
Part of a playbook
AI coding rulesAgents go wrong at every stage: rules for AGENTS.md, model switches, long tasks, pages and launch.OpenShare this tip
