메뉴
Show the model-routing decision for a task (Fable/Opus/Sonnet/Haiku) with reasoning. Use before launching a packet to sanity-check the tier and to override when you have stronger judgment than the heuristic.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | route |
| description | Show the model-routing decision for a task (Fable/Opus/Sonnet/Haiku) with reasoning. Use before launching a packet to sanity-check the tier and to override when you have stronger judgment than the heuristic. |
Surface the routing decision so the human (or the orchestrator) can confirm or override.
| Class | Tier | Reason |
|---|---|---|
| plan | Fable 5 while included (→2026-06-22), else Opus | decomposition quality propagates downstream |
| architect, spec | Opus | reasoning + spec authorship (pinned) |
| verify, audit | Opus | independent skepticism |
| debug-hard | Opus | subtle, multi-cause |
| implement, refactor, test | Sonnet | routine coding, fast and capable |
| search, summarize, classify, route | Haiku | cheap throughput |
--tier opus or --opus user signalFable 5 (claude-fable-5, launched 2026-06-09, 2× Opus price) runs in two configurations via resolveFableAccess() (CMAX_FABLE_ACCESS=included|credits overrides):
plan baselines to Fable; multispec decompose runs on Fable; --long-horizon escalates plan/debug-hard (overnight runs, multi-day converge loops, ambiguous root-cause hunts)--tier fable / cmax loop run --fable reaches Fableverify/spec/architect (pinned to Opus)--cheap / forceCheap mode AND class is not verify or spec → Sonnetverify or spec (fable tries opus first, then sonnet)verify and spec always run on Opus. They are the supervisor and the contract — cheap them and the whole harness loses its teeth.
Tier, model id, tools, maxTurns, estimated cost USD, escalation flag, reasoning. Pure read-only — no side effects.
Ask. Achieve. The canonical user-facing entry to claudemax — describe your goal, the SOTA-2026 pipeline (deepresearch → multispec → parallel /goal → verify) handles the rest. Same engine as /cmax with a friendlier verb. CLI equivalent is `cmax ask "<goal>"`.
The default FAT umbrella. Auto-runs deepresearch + multispec decomposition + parallel /goal + verify. Opus for planning/judgment/verification; Sonnet for sub-Spec execution (escalates per router). Multispec engine selects Mode A (SDK subagents) or Mode B (Claude Code Agent Teams) automatically based on work size. Your default daily-driver.
Max-effectiveness umbrella. Opus for EVERYTHING — planning, decomposition, sub-Spec /goal execution, verification. Use for novel domains, security/auth/payments, or when you want the highest ceiling regardless of cost.
Reviews a proposed diff for correctness, security, style, taste alignment. Distinct from /audit (which reviews existing code, not diffs) and /verify (which checks SPEC completion).
Spec quality gate. Every completion condition must have a mechanically-checkable verifyHint (file path, command, test name, behavior). Blocks /goal handoff if the spec wouldn't be verifiable.
Independent Opus supervisor pass that re-reads the repo blind and re-checks every SPEC completion condition. The source of truth for whether a run actually succeeded. Never skip.