Claude Code 多模型分工：Jev 做低层路由过滤
用 Opus 5.5 规划、Sonnet 5.5 执行、Fable 5.1 审查，Jev 在 12ms 内处理确定性路由分支，token 消耗降 79%，任务完成率超 92%。
Official Anthropic tip for Claude Code: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle and stop burning Opus tokens on tasks Sonnet 5.5 can swarm Put it on call with /advisor: run /advisor fable Opus 5.5 plans and ships the code. Sonnet 5.5 swarms the routine work at medium effort. Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Fable 5.1 reviews. Sonnet 5.5 swarms. Jev filters. Opus 5.5 ships. Jev engineering is the same move one layer down: the forks that need no thinker, such as which file, which tool, retry or stop, go to Jev in under 12ms, and the big model only sees the branches that split. Token burn drops by 79%. Context windows stay lean. Task completion jumps past 92%. Plan on high. Delegate on medium. Filter on low. Keep Fable on call. - the full tree: > Opus 5.5 on high runs the main session > explorer reads the code > worker edits and runs tests > researcher pulls the docs > verifier checks tests in isolated git worktrees > all subagents on Sonnet 5.5 at medium effort > Jev on low handles deterministic routing > Fable 5.1 on call as the advisor Paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker, researcher, and verifier. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Set verifier to run in an ephemeral git worktree so failed tests never pollute HEAD > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off [CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable that stops feature-flag fetching] plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add two rules to ~/.claude/CLAUDE.md: - Consult the advisor before a large plan, when an error repeats, and before calling a long task done - Circuit breaker: if any test fails twice, call Fable automatically before attempting a third retry Show me every change as a diff first. No edits until I say go." ↳ http://code.claude.com/docs/en/advisor
这条是引用着另一条写的：x.com/28qortex/status/2103949670435492020