Claude Code workflow: Sonnet builds, Haiku scouts, Opus reviews in parallel worktrees
Arindam_1729 · x · 2026-10-14
A practical Claude Code setup assigns each model to its strength: Sonnet 5.5 builds features in isolated Git worktrees, Haiku 5.5 scouts the repo (AST indexing, dependencies, implementation paths) in parallel, and Opus 5.5 reviews architecture and verifies diffs before merge. Launch sessions like claude --worktree feat-auth and claude -w feat-scout --model haiku so agents edit and test in parallel without clobbering each other; .worktreeinclude shares local configs across worktrees. The quoted post also links a tutorial on building a Jev-style routing/decision model in 15 minutes.
More from coding & agent
- Dev Flags Agent Flaw: pkill Matches Its Own Shell and Kills the Session — tristanbob · 2026-10-14
- Mysterious Blackbox plugin lands in Hermes Agent catalog to guard AI agents from compromise — Teknium · 2026-10-14
- Obsidian Starter Kit v5 ships Claude Code slash commands like /checkin and /closeday — dSebastien · 2026-10-14
- Modder plugs a local 2B decision model into Halo CE as a split-screen AI co-op teammate — CurtisSawtooth · 2026-10-14
- Agentic software factory workshop demos a queue-driven agent system built live in Codex — hugobowne · 2026-10-14
- Solo dev built a 24/7 AI-generated TV network with Claude writers, running at ~$40/day — matbox · 2026-10-14