harness-session

Reads CLAUDE.md and .claude/rules/* for a project and evaluates quality via LLM-judgment: length, internal contradictions, ambiguities, placeholder content, progressive disclosure, sensitive file protection. Returns CONTEXT_REPORT JSON. Read-only.

Audits a project's automation and verification posture: test infrastructure, formatter/linter PostToolUse hooks, PreToolUse dangerous-action blocks, verifier-agent separation, and whether registered project skills/hooks are actually invoked in recent sessions. Returns AUTOMATION_REPORT JSON.

Analyzes Claude Code session JSONL files to extract execution patterns: plan-ratio, delegation, parallel usage, handoff, repeated n-grams, tool frequency. Uses jq for efficient extraction of tool_use metadata only — never reads prompt text. Scales via split+parallel when many sessions exist. Returns SESSION_REPORT JSON.

Analyzes installed skills/plugins/MCP servers against ~/.claude.json to detect dead, ghost, duplicate, and collision-prone entries AND report the current accessible state (enabled plugins, runtime skills, connected MCP servers). Returns a structured JSON report. Read-only. Use from /check-harness.

Analyze the user's task and propose the optimal orchestration pattern, then execute it. 4 patterns: Sequential Pipeline, Parallel Subagent, Team Mode, Ralph Loop. Situation-aware pattern selection with user confirmation before execution. Use when: "/agent-orchestrate", "agent-orchestrate", "오케스트레이션", "어떤 패턴으로", "병렬로 할까", "순차로 할까", "팀 모드", "에이전트 패턴", "작업 방식 제안", "how should we run this", "pick a pattern". Also trigger when the user describes a complex multi-step task that would clearly benefit from agent coordination — e.g., "A사 B사 C사 분석해줘", "설계하고 구현하고 리뷰까지", "이거 순서대로 해줘", "3개 동시에 돌려", or any task with 3+ subtasks where choosing the right execution pattern matters for efficiency.

Harness 성숙도 진단 — **6축 24항목 체크리스트**와 **2×3 분석 매트릭스**(Static/Behavioral/Growth × User/Project)로 하네스의 사이클(구조→맥락→계획→실행→검증→개선)을 평가한다. 판단은 항상 "갖춘 것(Static) ↔ 실제로 하는 것(Behavioral)의 gap" 또는 "하네스가 자라고 있는지(Growth)"에서 나온다. 4개 서브에이전트(skill-portfolio-analyzer, session-pattern-analyzer, context-quality-reviewer, project-automation-auditor)를 병렬 실행. session-pattern-analyzer는 User 전역과 현재 프로젝트 두 번 돌려 User/Project 스코프를 분리한다. Use whenever the user asks to audit their Claude Code harness, review skill portfolio health, evaluate execution patterns across sessions, check project context/rules quality, or wants to know what's missing in their AI setup — even if they don't say "check-harness" explicitly. Trigger: "/check-harness", "check harness", "하네스 체크", "하네스 점검", "harness audit", "설정 점검", "뭐가 부족한지 봐줘", "하네스 진단", "성숙도 점검", "maturity check", "내 클로드 설정 봐줘", "스킬 정리".

"/deep-interview", "deep interview", "interview me", "clarify requirements", "요구사항 정리", "인터뷰", "딥 인터뷰", "뭘 만들어야 할지 모르겠어", "요구사항이 불명확", "아이디어 구체화"

Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect three kinds of issues: outdated claims, mutually contradictory statements, and risky-or-ambiguous wording. Produces a prioritized improvement list at `.drift-reports/`. Zero config. Trigger phrases: "doc drift", "memory drift", "memory audit", "context drift", "docs audit", "문서 점검", "문서 감사", "메모리 감사", "메모리 점검", "outdated 문서", "문서 충돌".

Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen. Three modes: browser (agent-browser/Playwright, fast, DOM-level), computer (MCP computer-use, screenshot + pixel clicks, any app), and cli (tmux, send-keys + capture-pane for interactive terminals). Auto-selects mode or accepts --browser / --computer / --cli override. Use when asked to "qa", "QA", "test this site", "test this app", "find bugs", "test and fix", "fix what's broken", "dogfood", "exploratory test", "bug hunt", "QA this app", "사이트 테스트", "앱 테스트", "브라우저 QA", "화면 보고 테스트해줘", "네이티브 앱 테스트", "screen test". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary.