holy sh*t. Official Anthropic pattern for Claude Code: stop burning Opus 5.5 context on tasks Haiku 5.5 can swarm, while Sonnet 5.5 builds put the architect on call with /advisor claude --model sonnet --advisor opus Sonnet 5.5 drives the primary session on high effort, writing diffs and running test suites Haiku 5.5 subagents swarm the repo in parallel at 340 tok/s, handling file discovery and spec docs lookup Opus 5.5 stays on call in the background as the advisor, only stepping in at three critical moments: → before a plan locks: does the implementation plan miss auth invariants or schema contracts? → when a test breaks twice: are we fixing the root cause or falling into a recursive rabbit hole? → before calling done: did the full diff introduce hidden regressions or break pre-flight rules? Opus 5.5 reviews. Sonnet 5.5 builds. Haiku 5.5 swarms Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep Opus on call. - the full advisor setup > Opus 5.5 on call reads full session history and catches deep architectural traps > Sonnet 5.5 lead drives edits, writes core logic, and executes test harnesses > Haiku 5.5 subagents swarm AST parsing, grep scans, and API docs in parallel > JEV micro-fork layer resolves 1,500+ mechanical routing branches in under 16ms > advisor stays completely silent on routine bash execution to protect context paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for hierarchical advisor orchestration: 1. Audit ~/.claude/settings.json and project config for model roles fitting lead, subagents, and advisor: > Pin main session model: sonnet with effortLevel: high for primary execution > Pin subagents model via CLAUDE_CODE_SUBAGENT_MODEL: haiku for file discovery and docs retrieval > Pin advisor model: opus on call for strategic review 2. Enable the advisor tool in ~/.claude/settings.json: > Set advisorModel to claude-opus-5-5 > Set subagentPromptCacheTtl to 5m 3. Configure automatic advisor consultation checkpoints in ~/.claude/CLAUDE.md: > Consult the advisor tool before finalizing multi-file architecture plans > Automatically summon the advisor when the same test or compiler error fails twice > Enforce advisor diff contract audit before declaring tasks complete or staging git commits 4. Constrain subagent scopes in ~/.claude/agents/: > Haiku subagents use read-only tools (Read, Grep, Glob) and return structured summaries without editing files Show every configuration diff first. Do not apply edits until confirmed" ↳
marfin@marfinxx · 2026-11-05Stop letting unmanaged Claude Code runs fail at turn 14 Set up the harness before launching multi-file tasks Isolate worktrees, enforce contracts, verify with Fable 5.5 The complete production agent architecture below ↓
The Harness Is the Machine: How to Build Unbreakable AI Agents with Claude Code & Claude 5.5
Read the X Article ↗Engagement counts are snapshots taken when collected.



