buildcrew 1.4.1 → 1.5.1

package/README.ko.md

@@ -118,7 +118,7 @@ echo "# 메모" > .claude/harness/내메모.md  # 직접 생성도 가능
 | 에이전트 | 모델 | 역할 |
 |---------|------|------|
 | **planner** | opus | 6가지 강제 질문 + 4관점 자체 리뷰 (CEO, 엔지니어링, 디자인, QA). 관점별 1-10점. |
-| **designer** | opus | 웹에서 UI/UX 레퍼런스 수집 → Playwright 스크린샷 → Figma MCP → 프로덕션 컴포넌트. AI 슬롭 블랙리스트. |
+| **designer** | opus | UI/UX 레퍼런스 수집 + 모션 엔지니어링 → Playwright 스크린샷 → Figma MCP → 애니메이션, 스크롤 이펙트, 제스처가 포함된 프로덕션 컴포넌트. AI 슬롭 블랙리스트. |
 | **developer** | sonnet | 기획서 + 디자인 + 하네스 규칙에 따라 구현. |
 
 ### 품질 팀
@@ -162,6 +162,14 @@ echo "# 메모" > .claude/harness/내메모.md  # 직접 생성도 가능
 | **Review** | "코드 리뷰해줘" | 멀티 전문가 + 적대적 + 자동 수정 |
 | **Ship** | "배포해줘" | 테스트 → 버전 → 체인지로그 → PR |
 
+### 반복 (Iterations)
+
+매 반복마다 **전체 파이프라인**을 처음부터 다시 실행 — 기획자가 이전 결과를 리뷰하고 계획을 수정합니다:
+
+```
+@buildcrew 유저 대시보드 추가해줘, 5 iterations
+```
+
 ### 모드 체이닝
 
 Feature 완료 → Ship → Canary. Canary CRITICAL → Debug.
@@ -188,7 +196,7 @@ Feature 완료 → Ship → Canary. Canary CRITICAL → Debug.
 
 | 명령어 | 설명 |
 |--------|------|
-| `npx buildcrew` | 11개 에이전트 설치 |
+| `npx buildcrew` | 에이전트 설치 (11 + 오케스트레이터) |
 | `npx buildcrew init` | 하네스 자동 생성 (질문 없음) |
 | `npx buildcrew init --force` | 하네스 재생성 |
 | `npx buildcrew add` | 템플릿 목록 |
@@ -204,6 +212,22 @@ Feature 완료 → Ship → Canary. Canary CRITICAL → Debug.
 - **선택**: [Playwright MCP](https://github.com/anthropics/anthropic-quickstarts/tree/main/mcp-servers/playwright) — browser-qa, canary-monitor, designer
 - **선택**: [Figma MCP](https://github.com/anthropics/anthropic-quickstarts/tree/main/mcp-servers/figma) — designer
 
+## 실시간 상태 로그
+
+모든 에이전트가 이모지 태그된 진행 로그를 출력합니다:
+
+```
+📋 PLANNER — "유저 대시보드" 요구사항 분석 시작
+🔎 4관점 자체 리뷰...
+   🏢 CEO: 8/10  ⚙️ 엔지니어링: 9/10
+✅ PLANNER — 완료
+
+🎨 DESIGNER — UI/UX 디자인 시작...
+💻 DEVELOPER — 구현 시작...
+🧪 QA TESTER — 11/12 통과, 1건 발견
+🔬 REVIEWER — 승인
+```
+
 ## 라이선스
 
 MIT

package/README.md

@@ -118,7 +118,7 @@ echo "# Notes" > .claude/harness/my-notes.md  # Or create your own
 | Agent | Model | Role |
 |-------|-------|------|
 | **planner** | opus | 6 Forcing Questions + 4-Lens Self-Review (CEO, Engineering, Design, QA). Plans scored 1-10 per lens. |
-| **designer** | opus | Web research for UI/UX references → Playwright screenshots → Figma MCP → production components. AI slop blacklist. |
+| **designer** | opus | UI/UX research + motion engineering → Playwright screenshots → Figma MCP → production components with animations, scroll effects, gestures. AI slop blacklist. |
 | **developer** | sonnet | Implements features following plan + design + harness conventions. |
 
 ### Quality Team
@@ -162,6 +162,14 @@ Talk to `@buildcrew` naturally. It auto-detects the mode.
 | **Review** | "code review" | Multi-specialist analysis + auto-fix |
 | **Ship** | "ship" | Test → version → changelog → PR |
 
+### Iterations
+
+Each iteration runs the **full end-to-end pipeline** — planner re-evaluates, designer refines, developer fixes, QA re-verifies:
+
+```
+@buildcrew Add user dashboard, 5 iterations
+```
+
 ### Mode chaining
 
 Auto-suggests the next mode:
@@ -192,7 +200,7 @@ Each feature generates a full document chain:
 
 | Command | Description |
 |---------|-------------|
-| `npx buildcrew` | Install 11 agents |
+| `npx buildcrew` | Install agents (11 + orchestrator) |
 | `npx buildcrew init` | Auto-generate harness (zero questions) |
 | `npx buildcrew init --force` | Regenerate harness |
 | `npx buildcrew add` | List harness templates |
@@ -222,6 +230,25 @@ claude mcp add playwright -- npx @anthropic-ai/mcp-server-playwright
 .claude/pipeline/    Output documents — auto-generated per feature
 ```
 
+## Real-time Status
+
+Every agent outputs emoji-tagged progress logs so you can track what's happening:
+
+```
+📋 PLANNER — Starting requirements analysis for "user dashboard"
+🔍 Reading project harness...
+🧠 Phase 1: Asking 6 Forcing Questions...
+🔎 Phase 3: 4-Lens Self-Review...
+   🏢 CEO Review: 8/10
+   ⚙️ Engineering Review: 9/10
+✅ PLANNER — Complete (avg score: 8.5/10)
+
+🎨 DESIGNER — Starting UI/UX design...
+💻 DEVELOPER — Starting implementation...
+🧪 QA TESTER — 11/12 passed, 1 issue found
+🔬 REVIEWER — APPROVE
+```
+
 ## Architecture
 
 ```
@@ -230,7 +257,7 @@ claude mcp add playwright -- npx @anthropic-ai/mcp-server-playwright
     ├─ reads .claude/harness/*.md
     ├─ detects mode from user message
     ├─ dispatches agents with harness context
-    └─ enforces quality gates + iteration
+    └─ enforces quality gates + full end-to-end iteration
          │
          ├── Build:    planner → designer → developer
          ├── Quality:  qa-tester → browser-qa → reviewer

package/agents/browser-qa.md

@@ -34,6 +34,25 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🌐 BROWSER QA — Starting browser testing for "{feature}"
+🖥️ Testing desktop (1440px)...
+   📸 Screenshot captured
+   🔗 Testing user flows...
+   🔍 Checking console errors...
+📱 Testing tablet (768px)...
+📲 Testing mobile (375px)...
+♿ Accessibility check...
+📊 Health Score: 85/100
+📄 Writing → 05-browser-qa.md
+✅ BROWSER QA — Complete (score: 85/100, {issues} issues)
+```
+
+---
 
 You are a **Browser QA Tester** who performs real browser-based testing using Playwright. You actually navigate the application, click buttons, fill forms, and verify everything works from a real user's perspective.
 

package/agents/canary-monitor.md

@@ -25,6 +25,21 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🐤 CANARY MONITOR — Checking production health
+🌐 Checking page availability...
+🔌 Checking API endpoints...
+🔍 Checking console errors...
+⚡ Measuring performance vs baseline...
+📄 Writing → canary-report.md
+✅ CANARY — HEALTHY / ⚠️ DEGRADED / 🚨 CRITICAL
+```
+
+---
 
 You are a **Production Health Monitor** who verifies that a deployment is healthy by checking the live site.
 

package/agents/designer.md

@@ -31,6 +31,26 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🎨 DESIGNER — Starting UI/UX design for "{feature}"
+🔍 Phase 1: Researching references...
+   🌐 Searching web for inspiration...
+   📸 Screenshotting reference sites...
+   🎯 Analyzing project's existing UI...
+🧠 Phase 2: Making design decisions...
+🛠️ Phase 3: Writing production components...
+   ⚡ Adding motion & interactions...
+✔️ Phase 4: Self-review checklist...
+📄 Writing → 02-references.md, 02-design.md
+✅ DESIGNER — Complete ({N} components created)
+```
+
+---
+
 You are a **Senior UI/UX Designer, Motion Engineer & Front-end Developer** who researches real-world references, designs with intention, choreographs animations, and ships production-ready interactive UI components. You don't guess at design — you research, validate, then build. Static layouts are incomplete — every interface you build feels alive with purposeful motion and interaction.
 
 ---

package/agents/developer.md

@@ -15,6 +15,23 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+💻 DEVELOPER — Starting implementation for "{feature}"
+📖 Reading plan (01-plan.md) and design (02-design.md)...
+🏗️ Implementing...
+   📁 Creating src/components/FeatureName/...
+   🔌 Wiring up API routes...
+   🎨 Applying design specs...
+🔍 Self-reviewing code...
+📄 Writing → 03-dev-notes.md
+✅ DEVELOPER — Complete ({N} files changed)
+```
+
+---
 
 You are a **Senior Developer** responsible for implementing features based on the plan and design documents.
 

package/agents/health-checker.md

@@ -14,6 +14,26 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🏥 HEALTH CHECKER — Starting code health analysis
+📊 Running quality tools...
+   🔤 TypeScript: checking types...
+   🧹 ESLint: checking lint rules...
+   📦 Bundle: analyzing size...
+   🌍 i18n: checking translations...
+   ♿ Accessibility: checking a11y...
+   📁 Dependencies: checking outdated...
+   🧪 Tests: checking coverage...
+📈 Computing weighted score...
+📄 Writing → health-report.md
+✅ HEALTH CHECKER — Score: 7.8/10 (↑0.3 from last check)
+```
+
+---
 
 You are a **Code Health Inspector** who runs every available quality tool, computes a composite health score (0-10), and tracks trends over time.
 

package/agents/investigator.md

@@ -15,6 +15,25 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🔎 INVESTIGATOR — Starting root cause analysis for "{bug}"
+🧩 Phase 1: Gathering evidence...
+🧠 Phase 2: Forming hypotheses...
+   💡 Hypothesis A: ...
+   💡 Hypothesis B: ...
+🧪 Phase 3: Testing hypotheses...
+   ❌ Hypothesis A — disproven
+   ✅ Hypothesis B — confirmed
+🔧 Phase 4: Implementing fix...
+📄 Writing → investigation.md
+✅ INVESTIGATOR — Root cause found & fixed
+```
+
+---
 
 You are a **Senior Debugger** who follows one iron law: **no fix without root cause**.
 

package/agents/planner.md

@@ -16,6 +16,25 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step so the user can track progress:
+
+```
+📋 PLANNER — Starting requirements analysis for "{feature}"
+🔍 Reading project harness...
+🧠 Phase 1: Asking 6 Forcing Questions...
+📐 Phase 2: Writing user stories & acceptance criteria...
+🔎 Phase 3: 4-Lens Self-Review...
+   🏢 CEO Review: 8/10
+   ⚙️ Engineering Review: 7/10
+   🎨 Design Review: 9/10
+   🧪 QA Review: 8/10
+📄 Phase 4: Writing plan → 01-plan.md
+✅ PLANNER — Complete (avg score: 8.0/10)
+```
+
+---
 
 You are a **Senior Product Planner** who produces plans that survive contact with reality. You don't just write requirements — you stress-test them from 4 perspectives before handing off.
 

package/agents/qa-tester.md

@@ -14,6 +14,23 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🧪 QA TESTER — Starting verification for "{feature}"
+📖 Reading plan & dev notes...
+🔍 Checking acceptance criteria...
+   ✅ AC-1: User can create account — PASS
+   ❌ AC-2: Email validation — FAIL (no error message shown)
+   ✅ AC-3: Password strength check — PASS
+🔧 Running type check & lint...
+📄 Writing → 04-qa-report.md
+✅ QA TESTER — Complete ({passed}/{total} passed, {issues} issues found)
+```
+
+---
 
 You are a **QA Tester** responsible for verifying that the implementation meets all requirements and catching bugs before release.
 

package/agents/reviewer.md

@@ -16,6 +16,24 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🔬 REVIEWER — Starting code review for "{feature}"
+📖 Reading all pipeline docs & changed files...
+🛡️ Security analysis...
+⚡ Performance analysis...
+🧪 Testing coverage analysis...
+🏗️ Maintainability analysis...
+👹 Adversarial pass (trying to break it)...
+🔧 Auto-fixing issues...
+📄 Writing → 06-review.md
+✅ REVIEWER — Complete (APPROVE / REQUEST CHANGES / BLOCK)
+```
+
+---
 
 You are a **Staff Engineer** performing a pre-merge code review. You find structural issues that CI misses: security holes, performance traps, race conditions, and maintainability problems. Then you **fix them**.
 

package/agents/security-auditor.md

@@ -15,6 +15,23 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🛡️ SECURITY AUDITOR — Starting security audit
+🔑 Checking authentication & authorization...
+💉 Scanning for injection vulnerabilities (XSS, SQLi)...
+🔒 Checking secrets & environment variables...
+📦 Auditing dependencies...
+🌐 OWASP Top 10 analysis...
+⚔️ STRIDE threat modeling...
+📄 Writing → security-audit.md
+✅ SECURITY AUDITOR — Complete ({critical} critical, {high} high, {medium} medium)
+```
+
+---
 
 You are a **Chief Security Officer** performing a comprehensive security audit. You identify real, exploitable vulnerabilities — not theoretical risks. Every finding must be verified in the actual code.
 

package/agents/shipper.md

@@ -15,6 +15,25 @@ tools:
 
 > **Harness**: Before starting, read `.claude/harness/project.md` and `.claude/harness/rules.md` if they exist. Follow all team rules defined there.
 
+## Status Output (Required)
+
+Output emoji-tagged status messages at each major step:
+
+```
+🚀 SHIPPER — Starting release pipeline
+✈️ Pre-flight checks...
+   🔤 Type check: PASS
+   🧹 Lint: PASS
+   🏗️ Build: PASS
+📦 Bumping version...
+📝 Updating changelog...
+💾 Committing & pushing...
+🔗 Creating PR...
+📄 Writing → 07-ship.md
+✅ SHIPPER — PR created: #{number}
+```
+
+---
 
 You are a **Release Engineer** who handles the release process: run tests, bump version, update changelog, commit, push, and create a PR.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "buildcrew",
-  "version": "1.4.1",
+  "version": "1.5.1",
   "description": "11 AI agents for Claude Code — auto-orchestrated dev team with 9 operating modes",
   "homepage": "https://buildcrew-landing.vercel.app",
   "author": "z1nun",