model-orchestrationlisted

Apply the fixed model-role and thinking-effort policy whenever work is delegated to subagents or a model/effort choice is made: the orchestrator (top-tier model, Fable) DIRECTLY owns 설계· 기획·분배·리뷰 — sets service direction, arbitrates and reviews plan/spec documents (with multi-persona-review), improves shipped features, and hunts performance/security problems; core implementation, test authoring/execution (E2E included), and code verification/V&V go to Opus at xhigh or above; repetitive/simple implementation (applying an established pattern) goes to Sonnet at high or above — Sonnet is never used for tests or verification; plan/spec drafts may be produced by Opus from a Fable direction brief, but the review/decision is always Fable's. Never delegate below the effort floors. Use whenever you are about to spawn an Agent/Task/Workflow worker, pick a model for a subtask, set a thinking/effort level, assign verification, or hand off orchestration because the current model's quota is exhausted. Trigger on "위임해", "에이전
uzysjung/uzys-agent-harness · ★ 3 · AI & Automation · score 67

Install: claude install-skill uzysjung/uzys-agent-harness

# Model Orchestration Policy A fixed role split between model tiers, set by the user (2026-07-04, revised 2026-07-07 and 2026-08-02 — *"설계·분배·기획·리뷰는 Fable5, 핵심 구현·테스트·검증은 opus5, 반복·단순 구현은 sonnet"*). The premise is **quality-over-cost**: delegation floors are set at the effort levels Anthropic itself recommends for intelligence-sensitive work ("start with xhigh for coding and agentic use cases, high as the minimum for most intelligence-sensitive workloads" — official effort guidance), not at the cost-saving end ("low ... like subagents"). When this policy and a cost instinct conflict, the policy wins; surface the cost, don't silently downgrade. ## Role split | Role | Who | Effort floor | Duties | |------|-----|--------------|--------| | **Orchestrator + Product Manager** | Top-tier session model (Fable) | session level | 설계·기획·분배·**리뷰** 전부. Directly: 서비스 방향성 수립·논의, 설계 결��·트레이드오프 확정, 작업 분배, 기획/스펙문서 **리뷰·중재**, 기개발 기능 **개선**, 문제점(성능·보안) 발굴 — see below | | **Core builder + Tester + V&V** | `opus` | **xhigh** (or `max`) | **핵심 구현**(새 설계 표면·경계 판단이 남는 것) + **테스트 작성·실행**(E2E 포함) + **코드 리뷰·검증/V&V**(fresh instance). 기획/스펙 문서 *초안*은 Fable의 방향 브리프를 받아 작성 가능하되, 확정은 Fable 리뷰를 거친다. **리뷰의 분업**: 설계·기획·스펙 문서 리뷰 = Fable / 코드(diff) 리뷰 = Opus V&V | | **Repetitive builder + read-only assist** | `sonnet` | **high** (or above) | **반복·단순 구현** — 확립된 패턴의 적용, 설계 판단이 이미 끝난 기계적 구현 (산출물은 Opus 교차검증) + 리서치 스윕. **테스트·검증 투입 금지** | | **Orchestrator stand-in** (quota exhausted) | `opus` @ `max` | max | Takes ov