Engineering

Claude Code as a team: Sonnet builds, Haiku swarms, Opus reviews

Your Claude Code set up like a team: Sonnet builds, three Haiku subagents map the repo, hunt call sites and audit in their own worktree, and Opus steps in as advisor only at decision points. Based on a post by plusxbt.

CloneKit@clonekitaiCloneKit creator
Checked automatically · v1.0.0 · Oct 22

What your AI will deliver

  • .claude/agents/repo-mapper.md: a read-only Haiku subagent that maps the repo and returns a short map
  • .claude/agents/call-site-hunter.md: a read-only Haiku subagent that finds every use of a symbol and returns path:line
  • .claude/agents/auditor.md: a Haiku subagent with isolation: worktree that runs tests, lint and type checks and reports failures
  • A short routing section in CLAUDE.md telling the main session when to delegate and when to consult the advisor

How it runs

In your AI, with your accounts. It starts by researching your business. How kits work ›

  1. 1. Understand

    Researches your business first, then asks you 4 questions it can't answer alone

  2. 2. Choose

    Nothing to choose: the kit follows one path

  3. 3. Build

    6 steps, risky ones ask you first

  4. 4. Deliver

    6 checks before delivery

Tools it uses

You pay each tool directly, not CloneKit. Your AI checks which ones you already have.

Details