Official Anthropic tip for Claude Code: Opus 5.5 advises. Sonnet 5.5 builds. Haiku 5.5 investigates
turn Claude Code into your own 3-model engineering team
01 Sonnet 5.5 → the builder
turns findings into code changes, runs tests, and owns implementation
02 Opus 5.5 → the advisor
reviews the approach when a decision needs another pass
03 Haiku 5.5 → the research crew
maps the codebase, finds relevant files, and returns useful evidence
the clever part:
scouts research in separate contexts and bring back findings for the main agent to act on
create custom Haiku scouts with:
model: haiku
tools: Read, Grep, Glob
that tool list gives them read-and-search access
↳ [subagent setup]
↳ https://t.co/HI76SvzP47
with Sonnet as your main model, enable Opus advice:
/advisor opus
the advisor is experimental and uses the Anthropic API
↳ [advisor setup]
↳ https://t.co/GltC9JBgWH
add the optional community hooks:
npx claude-code-templates@latest --setting hooks/subagents-explore-only --hook security/subagent-read-only-guard
SubagentStart → adds research instructions. [instruction hook]
↳ https://t.co/wnDZe39lTG
PreToolUse → blocks covered subagent write attempts. [guard hook]
↳ https://t.co/vnC1Ql0Yqr
keep the tool allowlist and verify the guard runs; MCP calls are outside its coverage
the goal:
dedicated researchers, useful advice, and a main agent that owns the code changes
the loop:
ask → read → search → report → main agent edits → tests
save this, then read the full guide for Opus 5.5 Harness Engineering