X post

Rob Hallam: output-optimized Fable stack for Claude Code (thread)

By Rob Hallam · x.com · 2 July 2026

Read or watch the original on x.com

Advice from this source

BuildingX posts

Route Claude Code work: cheap scout reads, top model plans and builds, fresh reviewer diffs

Per task: scout agent (Opus, low effort, read-only) explores; the top model plans (high effort) then implements (medium) only files in a 'Files touched' list and writes an audit; Opus reviews the diff in a fresh context with Blocking/Non-blocking/Verdict output. Agent files live in ~/.claude/agents/, orchestrated by CLAUDE.md.

When it applies: Claude Code users hitting weekly usage limits

Topics:How do I ship faster with Claude Code and Cursor?How do I set up agents that do real work?How do I keep AI costs from eating my margin?How do I write prompts and context that work?