正在打开每日关注
正在打开每日关注
基于官方 advisor 工具的三级模型编排配方：Opus 在关键节点审查，Sonnet 主力构建，Haiku 并行蜂群，附可复制配置提示词。
holy sh*t. Official Anthropic tip 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 --advisor opus --subagents haiku 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: haiku with effortLevel: medium for parallel 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 > Enable subagent parallel dispatcher pool (3x workers) 3. Configure automatic advisor consultation checkpoints in ~/.claude/CLAUDE.md: > Consult /advisor opus before finalizing multi-file architecture plans > Automatically summon /advisor opus 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: > Haiku subagents return structured AST summaries and docs snippets only without modifying main session context Show every configuration diff first. Do not apply edits until confirmed" ↳ https://t.co/gvAWk6KbDn
是什么：推文与配套视频提出基于 Claude Code 官方 advisor 工具的三级模型编排配方：Sonnet 5.5 主会话高投入写代码跑测试，Haiku 5.5 子代理并行做文件发现与文档检索，Opus 5.5 作为顾问仅在关键节点介入，并附一份可直接粘贴进 Claude Code 的配置提示词。
核心论点链：官方文档证实 advisor 真实存在——主模型可在计划锁定前、同一错误反复失败、宣告完成前咨询更强模型；advisor 接收完整会话历史（含所有工具调用），以服务端工具运行，且有严格的模型配对等级表（顾问不得低于主模型）。推文在此基础上演绎出"Opus 审查、Sonnet 构建、Haiku 蜂群"的分工，以及"Plan on high. Delegate on medium. Keep Opus on call"的成本分层口诀。
关键洞察：把 token 花在真正决定结果的地方——机械决策（选文件、选工具、重试或中止）下沉到代码与廉价模型层，前沿模型只在执行路径分叉时醒来；顾问读全量上下文却对常规执行保持沉默，以保护上下文预算与提示缓存。
边界与风险：JEV 微 fork 层、16ms、1500+ 分支、340 tok/s 及 --subagents 旗标均不见于官方文档，疑为演绎或虚构数据；advisor 属实验特性，仅限 Anthropic API（Bedrock 等不可用），会推高 token 成本；文中提示词会改写 settings.json 与 CLAUDE.md，照搬前应先审查 diff、确认模型版本（需 v2.1.260+）。