メニュー
Autonomous Opus loop that pursues a SPEC across multiple turns until every completion condition is satisfied or a real blocker surfaces. Use only when the work is non-decomposable and benefits from sustained reasoning. Always preceded by /spec.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | goal |
| description | Autonomous Opus loop that pursues a SPEC across multiple turns until every completion condition is satisfied or a real blocker surfaces. Use only when the work is non-decomposable and benefits from sustained reasoning. Always preceded by /spec. |
Hand the SPEC to an Opus driver that works across many turns until every completion condition is met. Inspired by Claude Code 2.1.139's /goal semantics; sharpened by claudemax's spec-first gate and supervisor verification.
SPEC.md exists at the project root.FINISHED block with per-condition evidence and exits.BLOCKED with what would unblock./goal is always Opus. If you need cheap, decompose into /dispatch-able packets first.A status (finished | blocked | max-turns), an evidence map keyed by completion condition id, a summary paragraph, and a session id for resumption.
Never declare success on the strength of /goal's own claim. /verify runs an independent Opus pass.
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.
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.
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.