Claude Code 分层顾问编排：Jev 处理 1500+ 路由规则

Bober_smart @Bober_smart原推发布于 2026.10.10

在 X 上打开原推

Why is no one talking about this? Official Anthropic recommendation for Claude Code: stop wasting Opus 5.5 compute on tasks Haiku 5.5 can swarm, while Sonnet 5.5 handles core development. switch the architect model into standby using /advisor  claude -> advisor opus -> subagents haiku Sonnet 5.5 powers the main workflow at maximum effort, drafting code changes and executing test suites Haiku 5.5 subagents index the repository in parallel at 340 tokens/sec, discovering files and reviewing technical documentation Opus 5.5 remains on standby as an expert consultant, stepping in only during three key scenarios:  -> prior to committing to a strategy: does the blueprint lack authentication edge cases or schema rules? -> when a test fails repeatedly: are we tackling the root issue or wasting time in a rabbit hole? -> before marking the task complete: did recent diffs introduce silent bugs, and are baseline checks satisfied? Opus 5.5 assesses. Sonnet 5.5 builds. Haiku 5.5 executes concurrently Jev engineering applies this identical structure one level down: automated logic requiring zero reasoning (selecting files, invoking tools, retrying or cancelling) completes in 16ms, so heavy models trigger only when execution paths split Plan at max power. Delegate at mid power. Keep Opus on standby On-call Opus 5.5 inspects overall session history and catches deep structural flaws Lead Sonnet 5.5 performs edits, writes core logic, and manages test environments Haiku 5.5 subagents run AST parsing, grep queries, and API doc analysis concurrently JEV micro-fork layer processes 1,500+ routing rules in under 16ms Expert model stays silent during basic terminal commands to preserve context window Configure my Claude Code workspace for hierarchical advisor orchestration:  1. Verify ~/.claude/settings.json and project-level configs for model role alignment (main, subagents, and advisor) Set main session model: sonnet with high effort level for primary execution Set subagents model: haiku with effortLevel: medium for parallel file discovery and doc gathering Set advisor model: opus on call for high-level analysis  2. Turn on the advisor tool inside ~/.claude/settings.json:  Define advisorModel as claude-opus-5-5 Enable subagent parallel dispatcher pool (3x workers)  3. Establish automatic advisor review checkpoints in ~/.claude/CLAUDE.md:  Call /advisor opus prior to finalizing multi-file architectural changes Trigger /advisor opus automatically whenever the same compiler or test error happens twice Require an advisor diff contract audit prior to completing tasks or staging git commits  4. Restrict subagent execution boundaries:  Haiku subagents must return only structured AST summaries and doc snippets without bloating the primary session context  Display all configuration diffs before applying changes. Do not commit modifications until confirmed  Http://code.claude.com/docs/en/advisor

这条是引用着另一条写的：x.com/bober_smart/status/2078784709253841039