uzys-agent-harness

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) DIRECTLY sets service direction, reviews plan/spec documents (with multi-persona-review), improves shipped features, and hunts performance/security problems; plan/spec/planning documents are AUTHORED by Opus, which also owns core implementation and V&V, at xhigh or above; repetitive implementation and E2E tests go to Sonnet at high or above — never delegate below those 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", "에이전트로 돌려", "오케스트레이션", "모델 역할분담", "어떤 모델로", "effort 얼마로", "thinking level", "서브에이전트", or in English "delegate this", "spawn an agent for", "which model should", "route this task", "verify with", "orchestrate". Fire even when the user does

Treats GitHub Issues as the async backlog + decision channel between user and AI agent. Use when a non-blocking todo / bug / decision needs to persist beyond the chat session. Enforces 5-section body template (Background / Given / Decision / AC / Next) so issues become reusable agent context, not just sticky notes.

Defines and enforces a project's long-term direction (North Star Statement, NSM, Will/Won't, 4-gate decision heuristic). Use when starting a new project, when scope creep is suspected, or when a non-obvious feature request needs prioritization. Sits one layer above SPEC/PRD — answers 'why and where to', not 'what and how'.

Captures screenshots of key UI flows after E2E tests pass, runs an agent-side first-pass diff (regressions, console errors, layout shifts), then surfaces a checklist for the user's final approval. Use after E2E tests pass on a UI track (csr-*, ssr-*, full). Adapts the GoalTrack screenshot-review pattern into a repeatable workflow.

Two-mode chained gap analysis. DETECT scans the current service end-to-end through three lenses — north-star alignment, correctness (bugs), and user-perspective (UX) — and enumerates concrete, severity-ranked gaps. Then BENCHMARK researches how reference/benchmark services actually solved each high-ranked gap and PROPOSES a closing approach. Use when the user says any of: "북극성 기준으로 부족한 점", "사용자 관점에서 부족한 점", "다른 벤치마크 서비스는 이 부분을 어떻게 해결했는지", "갭분석", "레퍼런스 서비스랑 비교해서 부족한 점 찾아줘" — or the English equivalents: "gap analysis", "what are we missing vs the ideal/north-star", "benchmark against reference services". Fires for both Korean and English phrasing. NOT for a whole-codebase multi-dimension audit (use ultracode-service-audit) or single-artifact prose review (use multi-persona-review) — this is the narrower gap-vs-benchmark loop.

A panel-review skill that critiques ONE artifact (launch post, README, doc, markdown, plan, design) via 3-5 disjoint user-perspective personas running in parallel, then synthesizes deduped, severity-ranked improvement points (P0/P1/P2). Use when the user says "작성글을 사용자 관점의 페르소나를 여러명 만들어서 (손넷 모델정도로) 피드백 받아바", "다면 리뷰 해볼까", "페르소나로 리뷰", "여러 관점으로 피드백", or in English "multi-persona review", "review this from different user perspectives", "get persona feedback on this post/README/doc", "panel review this artifact". Lighter than a full service audit — point it at ONE artifact, not a whole codebase. NOT for a whole-codebase multi-dimension audit (use ultracode-service-audit) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e).

Run a multi-agent, adversarially-verified full-service audit across 7 dimensions (code / UX / scalability / planning+north-star / security / promotion / extensible), separating findings into confirmed / unverified / rejected and producing a priority-ranked, M-numbered milestone roadmap (as many milestones as the findings warrant). Use when the user says "ultracode 전체 서비스 점검", "전체 서비스를 점검하자", "코드·UX·확장성·기획·북극성지표·보안·홍보 문제점을 파악하고 우선순위에 따라 개선", "다차원 서비스 감사", or in English "audit the whole service / full multi-dimensional service audit / find code, UX, scalability, planning, security, and marketing problems and prioritize fixes". The heavyweight superset audit — orchestrate it as a Workflow with fan-out finders and an adversarial verify pass. NOT for a single-artifact prose/README review (use multi-persona-review) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e) — those are the lighter siblings.

Present a decision or confirmation request in the user's four-part format: 전후맥락 (context) → 추천 + 이유 (recommendation) → UI/UX 형태 (a scannable table/option-list) → ASIS→TOBE contrast, led by the recommendation so the user can say yes fast. Fire at genuine A-or-B / approval / explicit-ASIS-TOBE moments. Triggers on the user's verbatim phrases "ASIS TOBE로 설명", "ASIS-TOBE로 알려줘", "화면으로 ASIS TOBE로 설명", "의사결정 / 컨펌 요청", "이거 진행할까요?", and the softer "다음 진행할 것들 알려줘"; English equivalents: "present this as ASIS/TOBE", "give me the as-is to-be", "should I do A or B", "ask for my approval", "lay out the options". Do NOT fire for pure information with no decision, or trivial reversible actions you would just do.

Execute a structured handoff right before a context compaction so no state is lost — persist durable facts to memory, take an atomic git snapshot (clean tree + open-PR check), and emit a fixed-field resume anchor (current state / verified / what's left / next action) plus a suggested custom /compact summary line. Use when the user says "컴팩션 준비해줘", "컴팩션하고 이어서 진행할 수 있게 준비해줘", "핸드오프 준비해줘", or in English "prepare for compaction", "get ready to compact and continue", "hand off before /compact", "checkpoint before compacting". Also fire proactively when context is nearing the window limit and an auto-compact is imminent.

Read the project's NORTH_STAR / vision doc, measure current state against the goal, then propose a forward direction plus prioritized feature proposals — persisted as a durable roadmap in docs/plans + memory so the plan survives /compact and new sessions. Use when the user asks where the project should go next or wants a backlog grounded in the vision. Fires on the user's real phrasings: "앞으로 어떤 방향으로 개선·발전시킬지 고민해봐", "NORTH.md / NORTH_STAR 보고 나아갈 방향 + 기능 제안", "나아갈 방향 + 기능제안 (수용 → 계획 수립하고 메모리에 기록)", "북극성 정렬 로드맵", as well as the English equivalents: "what direction should we take next", "propose a roadmap / feature backlog from the north star", "plan the next milestones and save it to memory". Not for detecting bugs or auditing current quality (see gap-analysis-e2e / ultracode-service-audit) — this skill DIRECTS forward planning.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Detects when SPEC.md or PRD.md exceeds 300 lines and proposes feature-based splitting with a master route document. Use when SPEC.md grows too large to be effectively used as a single document.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Detects when SPEC.md or PRD.md exceeds 300 lines and proposes feature-based splitting with a master route document. Use when SPEC.md grows too large to be effectively used as a single document.