oh-my-customcode 0.10.1 → 0.10.2

package/templates/.claude/rules/MUST-sync-verification.md

@@ -1,6 +1,6 @@
 # [MUST] Sync Verification Rules
 
-> **Priority**: MUST - ENFORCED | **ID**: R017
+> **Priority**: MUST - ENFORCED | **ID**: R016
 
 ## Core Rule
 

package/templates/.claude/rules/SHOULD-agent-teams.md

@@ -1,6 +1,6 @@
 # [SHOULD] Agent Teams Rules
 
-> **Priority**: SHOULD | **ID**: R018 | **Condition**: Agent Teams enabled locally
+> **Priority**: SHOULD | **ID**: R017 | **Condition**: Agent Teams enabled locally
 
 ## Detection
 

package/templates/.claude/rules/index.yaml

@@ -62,7 +62,7 @@ rules:
     scope: agents
 
   # Intent Transparency - MUST
-  - id: R015
+  - id: R014
     name: intent-transparency
     title: Intent Transparency Rules
     path: ./MUST-intent-transparency.md
@@ -70,7 +70,7 @@ rules:
     scope: orchestrator
 
   # Continuous Improvement - MUST
-  - id: R016
+  - id: R015
     name: continuous-improvement
     title: Continuous Improvement Rules
     path: ./MUST-continuous-improvement.md
@@ -78,7 +78,7 @@ rules:
     scope: all
 
   # Sync Verification - MUST
-  - id: R017
+  - id: R016
     name: sync-verification
     title: Sync Verification Rules
     path: ./MUST-sync-verification.md
@@ -125,7 +125,7 @@ rules:
     scope: all
 
   # Agent Teams - SHOULD
-  - id: R018
+  - id: R017
     name: agent-teams
     title: Agent Teams Rules
     path: ./SHOULD-agent-teams.md

package/templates/.claude/skills/de-lead-routing/SKILL.md

@@ -219,6 +219,19 @@ Pipeline design completed.
 - **secretary-routing**: DE agents accessible through secretary for management tasks
 - **qa-lead-routing**: Coordinates with QA for data quality testing
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single-tool DE task | Task Tool |
+| Multi-tool pipeline design (3+ tools) | Agent Teams |
+| Cross-tool data quality analysis | Agent Teams |
+| Quick DAG/model validation | Task Tool |
+
 ## Usage
 
 This skill is NOT user-invocable. It should be automatically triggered when the main conversation detects data engineering intent.

package/templates/.claude/skills/dev-lead-routing/SKILL.md

@@ -77,4 +77,18 @@ user-invocable: false
 
 Multi-language: detect all languages, route to parallel experts (max 4). Single-language: route to matching expert. Cross-layer (frontend + backend): multiple experts in parallel.
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single-language review | Task Tool |
+| Multi-language code review (3+) | Agent Teams |
+| Code review + fix cycle | Agent Teams |
+| Cross-layer debugging (FE + BE + DB) | Agent Teams |
+| Simple file search/validation | Task Tool |
+
 Not user-invocable. Auto-triggered on development intent.

package/templates/.claude/skills/qa-lead-routing/SKILL.md

@@ -265,6 +265,19 @@ metrics:
   test_case_count: number
 ```
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single QA phase (plan/write/execute) | Task Tool |
+| Full QA cycle (plan + write + execute + report) | Agent Teams |
+| Quality analysis (parallel strategy + results) | Agent Teams |
+| Quick test validation | Task Tool |
+
 ## Usage
 
 This skill is NOT user-invocable. It should be automatically triggered when the main conversation detects QA intent.

package/templates/.claude/skills/sauron-watch/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: sauron-watch
-description: Full R017 verification (5+3 rounds) before commit
+description: Full R016 verification (5+3 rounds) before commit
 disable-model-invocation: true
 ---
 
 # Sauron Watch Skill
 
-Execute full R017 verification process with 5 rounds of manager agent verification and 3 rounds of deep review.
+Execute full R016 verification process with 5 rounds of manager agent verification and 3 rounds of deep review.
 
 ## Purpose
 
@@ -84,7 +84,7 @@ Ensure complete synchronization of agents, commands, documentation, and project
 ```
 [mgr-sauron:watch]
 
-Starting full R017 verification...
+Starting full R016 verification...
 
 ═══════════════════════════════════════════════════════════
  PHASE 1: Manager Agent Verification (5 rounds)
@@ -140,5 +140,5 @@ Ready to commit. 커밋할까요?
 
 ## Related
 
-- R017: Sync Verification Rules
+- R016: Sync Verification Rules
 - mgr-gitnerd: Git operations agent

package/templates/.claude/skills/secretary-routing/SKILL.md

@@ -19,7 +19,7 @@ Routes agent management tasks to the appropriate manager agent. This skill conta
 | mgr-supplier | Validate dependencies | "audit", "check deps" |
 | mgr-gitnerd | Git operations | "commit", "push", "pr" |
 | mgr-sync-checker | Sync verification | "sync check", "verify sync" |
-| mgr-sauron | R017 auto-verification | "verify", "full check" |
+| mgr-sauron | R016 auto-verification | "verify", "full check" |
 | mgr-claude-code-bible | Claude Code spec compliance | "spec check", "verify compliance" |
 | sys-memory-keeper | Memory operations | "save memory", "recall", "memory search" |
 | sys-naggy | TODO management | "todo", "track tasks", "task list" |
@@ -79,6 +79,19 @@ When command requires multiple independent operations:
 | sys-memory-keeper | sonnet | Memory operations, search |
 | sys-naggy | haiku | Simple TODO tracking |
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single manager task | Task Tool |
+| Batch agent creation (3+) | Agent Teams |
+| Multi-round verification (sauron) | Task Tool |
+| Agent audit + fix cycle | Agent Teams |
+
 ## Usage
 
 This skill is NOT user-invocable. It is automatically triggered when the main conversation detects agent management intent.

package/templates/.codex/agents/mgr-gitnerd.md

@@ -40,6 +40,6 @@ Types: feat, fix, docs, style, refactor, test, chore
 - NEVER skip pre-commit hooks without reason
 - ALWAYS create new commits (avoid --amend unless requested)
 
-## Push Rules (R017)
+## Push Rules (R016)
 
 All pushes require prior mgr-sauron:watch verification. If sauron was not run, REFUSE the push.

package/templates/.codex/agents/mgr-sauron.md

@@ -1,6 +1,6 @@
 ---
 name: mgr-sauron
-description: Use when you need automated verification of R017 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds) before commits
+description: Use when you need automated verification of R016 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds) before commits
 model: sonnet
 memory: project
 effort: high
@@ -15,7 +15,7 @@ tools:
   - Bash
 ---
 
-You are an automated verification specialist that executes the mandatory R017 verification process, acting as the "all-seeing eye" that ensures system integrity through comprehensive multi-round verification.
+You are an automated verification specialist that executes the mandatory R016 verification process, acting as the "all-seeing eye" that ensures system integrity through comprehensive multi-round verification.
 
 ## Core Capabilities
 
@@ -34,7 +34,7 @@ You are an automated verification specialist that executes the mandatory R017 ve
 
 | Command | Description |
 |---------|-------------|
-| `mgr-sauron:watch` | Full R017 verification (5+3 rounds) |
+| `mgr-sauron:watch` | Full R016 verification (5+3 rounds) |
 | `mgr-sauron:quick` | Quick verification (single pass) |
 | `mgr-sauron:report` | Generate verification status report |
 

package/templates/.codex/rules/MUST-continuous-improvement.md

@@ -1,6 +1,6 @@
 # [MUST] Continuous Improvement Rules
 
-> **Priority**: MUST | **ID**: R016 | **Trigger**: User points out rule violation
+> **Priority**: MUST | **ID**: R015 | **Trigger**: User points out rule violation
 
 ## Core Rule
 

package/templates/.codex/rules/MUST-intent-transparency.md

@@ -1,6 +1,6 @@
 # [MUST] Intent Transparency Rules
 
-> **Priority**: MUST | **ID**: R015
+> **Priority**: MUST | **ID**: R014
 
 ## Core Rule
 

package/templates/.codex/rules/MUST-orchestrator-coordination.md

@@ -117,7 +117,7 @@ The skill's WORKFLOW is followed, but git EXECUTION is delegated to mgr-gitnerd
 
 ## Agent Teams (when enabled)
 
-When `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`: use Agent Teams for 3+ agent coordinated tasks. See R018 for decision matrix. Task tool remains fallback for simple/independent tasks.
+When `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`: use Agent Teams for 3+ agent coordinated tasks. See R017 for decision matrix. Task tool remains fallback for simple/independent tasks.
 
 ## Announcement Format
 

package/templates/.codex/rules/MUST-sync-verification.md

@@ -1,6 +1,6 @@
 # [MUST] Sync Verification Rules
 
-> **Priority**: MUST - ENFORCED | **ID**: R017
+> **Priority**: MUST - ENFORCED | **ID**: R016
 
 ## Core Rule
 

package/templates/.codex/rules/SHOULD-agent-teams.md

@@ -1,6 +1,6 @@
 # [SHOULD] Agent Teams Rules
 
-> **Priority**: SHOULD | **ID**: R018 | **Condition**: Agent Teams enabled locally
+> **Priority**: SHOULD | **ID**: R017 | **Condition**: Agent Teams enabled locally
 
 ## Detection
 

package/templates/.codex/rules/index.yaml

@@ -62,7 +62,7 @@ rules:
     scope: agents
 
   # Intent Transparency - MUST
-  - id: R015
+  - id: R014
     name: intent-transparency
     title: Intent Transparency Rules
     path: ./MUST-intent-transparency.md
@@ -70,7 +70,7 @@ rules:
     scope: orchestrator
 
   # Continuous Improvement - MUST
-  - id: R016
+  - id: R015
     name: continuous-improvement
     title: Continuous Improvement Rules
     path: ./MUST-continuous-improvement.md
@@ -78,7 +78,7 @@ rules:
     scope: all
 
   # Sync Verification - MUST
-  - id: R017
+  - id: R016
     name: sync-verification
     title: Sync Verification Rules
     path: ./MUST-sync-verification.md
@@ -125,7 +125,7 @@ rules:
     scope: all
 
   # Agent Teams - SHOULD
-  - id: R018
+  - id: R017
     name: agent-teams
     title: Agent Teams Rules
     path: ./SHOULD-agent-teams.md

package/templates/.codex/skills/de-lead-routing/SKILL.md

@@ -219,6 +219,19 @@ Pipeline design completed.
 - **secretary-routing**: DE agents accessible through secretary for management tasks
 - **qa-lead-routing**: Coordinates with QA for data quality testing
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single-tool DE task | Task Tool |
+| Multi-tool pipeline design (3+ tools) | Agent Teams |
+| Cross-tool data quality analysis | Agent Teams |
+| Quick DAG/model validation | Task Tool |
+
 ## Usage
 
 This skill is NOT user-invocable. It should be automatically triggered when the main conversation detects data engineering intent.

package/templates/.codex/skills/dev-lead-routing/SKILL.md

@@ -77,4 +77,18 @@ user-invocable: false
 
 Multi-language: detect all languages, route to parallel experts (max 4). Single-language: route to matching expert. Cross-layer (frontend + backend): multiple experts in parallel.
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single-language review | Task Tool |
+| Multi-language code review (3+) | Agent Teams |
+| Code review + fix cycle | Agent Teams |
+| Cross-layer debugging (FE + BE + DB) | Agent Teams |
+| Simple file search/validation | Task Tool |
+
 Not user-invocable. Auto-triggered on development intent.

package/templates/.codex/skills/qa-lead-routing/SKILL.md

@@ -265,6 +265,19 @@ metrics:
   test_case_count: number
 ```
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single QA phase (plan/write/execute) | Task Tool |
+| Full QA cycle (plan + write + execute + report) | Agent Teams |
+| Quality analysis (parallel strategy + results) | Agent Teams |
+| Quick test validation | Task Tool |
+
 ## Usage
 
 This skill is NOT user-invocable. It should be automatically triggered when the main conversation detects QA intent.

package/templates/.codex/skills/sauron-watch/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: sauron-watch
-description: Full R017 verification (5+3 rounds) before commit
+description: Full R016 verification (5+3 rounds) before commit
 disable-model-invocation: true
 ---
 
 # Sauron Watch Skill
 
-Execute full R017 verification process with 5 rounds of manager agent verification and 3 rounds of deep review.
+Execute full R016 verification process with 5 rounds of manager agent verification and 3 rounds of deep review.
 
 ## Purpose
 
@@ -84,7 +84,7 @@ Ensure complete synchronization of agents, commands, documentation, and project
 ```
 [mgr-sauron:watch]
 
-Starting full R017 verification...
+Starting full R016 verification...
 
 ═══════════════════════════════════════════════════════════
  PHASE 1: Manager Agent Verification (5 rounds)
@@ -140,5 +140,5 @@ Ready to commit. 커밋할까요?
 
 ## Related
 
-- R017: Sync Verification Rules
+- R016: Sync Verification Rules
 - mgr-gitnerd: Git operations agent

package/templates/.codex/skills/secretary-routing/SKILL.md

@@ -19,7 +19,7 @@ Routes agent management tasks to the appropriate manager agent. This skill conta
 | mgr-supplier | Validate dependencies | "audit", "check deps" |
 | mgr-gitnerd | Git operations | "commit", "push", "pr" |
 | mgr-sync-checker | Sync verification | "sync check", "verify sync" |
-| mgr-sauron | R017 auto-verification | "verify", "full check" |
+| mgr-sauron | R016 auto-verification | "verify", "full check" |
 | mgr-claude-code-bible | Claude Code spec compliance | "spec check", "verify compliance" |
 | sys-memory-keeper | Memory operations | "save memory", "recall", "memory search" |
 | sys-naggy | TODO management | "todo", "track tasks", "task list" |
@@ -179,6 +179,19 @@ failure_modes:
   timeout: Retry or skip with notice
 ```
 
+## Agent Teams Awareness
+
+Before routing via Task tool, check if Agent Teams is available (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present).
+
+**Self-check:** Does this task need 3+ agents, shared state, or inter-agent communication? If yes, prefer Agent Teams over Task tool. See R018 for the full decision matrix.
+
+| Scenario | Preferred |
+|----------|-----------|
+| Single manager task | Task Tool |
+| Batch agent creation (3+) | Agent Teams |
+| Multi-round verification (sauron) | Task Tool |
+| Agent audit + fix cycle | Agent Teams |
+
 ## Usage
 
 This skill is NOT user-invocable. It should be automatically triggered when the main conversation detects agent management intent.

package/templates/CLAUDE.md.en

@@ -117,8 +117,8 @@ Flow:
 | R008 | Tool Identification | **ENFORCED** - Display agent when using ANY tool |
 | R009 | Parallel Execution | **ENFORCED** - Parallel execution, large task decomposition |
 | R010 | Orchestrator Coordination | **ENFORCED** - Orchestrator coordination, session continuity, direct action prohibition |
-| R016 | Continuous Improvement | **ENFORCED** - Update rules when violations occur |
-| R017 | Sync Verification | **ENFORCED** - Verify sync before structural changes |
+| R015 | Continuous Improvement | **ENFORCED** - Update rules when violations occur |
+| R016 | Sync Verification | **ENFORCED** - Verify sync before structural changes |
 
 ### SHOULD (Strongly recommended)
 | ID | Rule | Description |
@@ -128,8 +128,8 @@ Flow:
 | R011 | Memory Integration | Session persistence with claude-mem |
 | R012 | HUD Statusline | Real-time status display |
 | R013 | Ecomode | Token efficiency for batch ops |
-| R015 | Intent Transparency | **MUST** - Transparent agent routing |
-| R018 | Agent Teams | Active use of Agent Teams when enabled |
+| R014 | Intent Transparency | **MUST** - Transparent agent routing |
+| R017 | Agent Teams | Active use of Agent Teams when enabled |
 
 ### MAY (Optional)
 | ID | Rule | Description |
@@ -158,7 +158,7 @@ Flow:
 | `/optimize-analyze` | Analyze bundle and performance |
 | `/optimize-bundle` | Optimize bundle size |
 | `/optimize-report` | Generate optimization report |
-| `/sauron-watch` | Full R017 verification |
+| `/sauron-watch` | Full R016 verification |
 | `/lists` | Show all available commands |
 | `/status` | Show system status |
 | `/help` | Show help information |
@@ -171,7 +171,7 @@ project/
 +-- .claude/
 |   +-- agents/                  # Subagent definitions (42 files)
 |   +-- skills/                  # Skills (51 directories)
-|   +-- rules/                   # Global rules (R000-R018)
+|   +-- rules/                   # Global rules (R000-R017)
 |   +-- hooks/                   # Hook scripts (memory, HUD)
 |   +-- contexts/                # Context files (ecomode)
 +-- guides/                      # Reference docs (22 topics)
@@ -216,7 +216,7 @@ When Claude Code's Agent Teams feature is enabled (`CLAUDE_CODE_EXPERIMENTAL_AGE
 | Token cost | Lower | Higher |
 
 **When enabled, actively use Agent Teams for complex collaborative tasks.**
-See R018 (SHOULD-agent-teams.md) for the decision matrix.
+See R017 (SHOULD-agent-teams.md) for the decision matrix.
 Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
 
 ## Quick Reference
@@ -279,25 +279,4 @@ npm install -g claude-mem
 claude-mem setup
 ```
 
-## Git Workflow (MUST follow)
-
-| Branch | Purpose |
-|--------|---------|
-| `develop` | Main development branch (default) |
-| `feature/*` | New features -> PR to develop |
-| `release/*` | Release preparation -> **npm publish here only** |
-| `hotfix/*` | Critical fixes -> tag -> publish -> merge to develop |
-
-**Publishing flow:**
-```
-develop → release/x.y.z → npm publish → merge back to develop
-```
-
-**Key rules:**
-- Create feature branches from `develop`
-- **npm publish MUST only happen from release branch**
-- Use conventional commits: `feat:`, `fix:`, `docs:`, `chore:`
-- Include "Closes #N" in commit message to auto-close issues
-- Pre-commit hooks run tests automatically
-
-See [CONTRIBUTING.md](CONTRIBUTING.md) for detailed workflow.
+<!-- omcustom:git-workflow -->

package/templates/CLAUDE.md.ko

@@ -117,8 +117,8 @@ oh-my-customcode로 구동됩니다.
 | R008 | 도구 식별 | **강제** - 모든 도구 사용 시 에이전트 표시 |
 | R009 | 병렬 실행 | **강제** - 병렬 실행, 대규모 작업 분해 |
 | R010 | 오케스트레이터 조율 | **강제** - 오케스트레이터 조율, 세션 연속성, 직접 실행 금지 |
-| R016 | 지속적 개선 | **강제** - 위반 발생 시 규칙 업데이트 |
-| R017 | 동기화 검증 | **강제** - 구조 변경 전 검증 |
+| R015 | 지속적 개선 | **강제** - 위반 발생 시 규칙 업데이트 |
+| R016 | 동기화 검증 | **강제** - 구조 변경 전 검증 |
 
 ### SHOULD (강력 권장)
 | ID | 규칙 | 설명 |
@@ -128,8 +128,8 @@ oh-my-customcode로 구동됩니다.
 | R011 | 메모리 통합 | claude-mem을 통한 세션 지속성 |
 | R012 | HUD 상태줄 | 실시간 상태 표시 |
 | R013 | Ecomode | 배치 작업 토큰 효율성 |
-| R015 | 의도 투명성 | **필수** - 투명한 에이전트 라우팅 |
-| R018 | Agent Teams | 활성화 시 Agent Teams 적극 사용 |
+| R014 | 의도 투명성 | **필수** - 투명한 에이전트 라우팅 |
+| R017 | Agent Teams | 활성화 시 Agent Teams 적극 사용 |
 
 ### MAY (선택)
 | ID | 규칙 | 설명 |
@@ -158,7 +158,7 @@ oh-my-customcode로 구동됩니다.
 | `/optimize-analyze` | 번들 및 성능 분석 |
 | `/optimize-bundle` | 번들 크기 최적화 |
 | `/optimize-report` | 최적화 리포트 생성 |
-| `/sauron-watch` | 전체 R017 검증 |
+| `/sauron-watch` | 전체 R016 검증 |
 | `/lists` | 모든 사용 가능한 커맨드 표시 |
 | `/status` | 시스템 상태 표시 |
 | `/help` | 도움말 표시 |
@@ -171,7 +171,7 @@ project/
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (42 파일)
 |   +-- skills/                  # 스킬 (51 디렉토리)
-|   +-- rules/                   # 전역 규칙 (R000-R018)
+|   +-- rules/                   # 전역 규칙 (R000-R017)
 |   +-- hooks/                   # 훅 스크립트 (메모리, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
 +-- guides/                      # 레퍼런스 문서 (22 토픽)
@@ -216,7 +216,7 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 | 토큰 비용 | 낮음 | 높음 |
 
 **활성화 시, 복잡한 협업 작업에 Agent Teams를 적극 사용합니다.**
-결정 매트릭스는 R018 (SHOULD-agent-teams.md)을 참조하세요.
+결정 매트릭스는 R017 (SHOULD-agent-teams.md)을 참조하세요.
 단순/비용 민감 작업에는 Task tool + 라우팅 스킬이 폴백으로 유지됩니다.
 
 ## 빠른 참조
@@ -279,25 +279,4 @@ npm install -g claude-mem
 claude-mem setup
 ```
 
-## Git 워크플로우 (반드시 준수)
-
-| 브랜치 | 용도 |
-|--------|------|
-| `develop` | 메인 개발 브랜치 (기본) |
-| `feature/*` | 새 기능 -> develop으로 PR |
-| `release/*` | 릴리스 준비 -> **npm 배포는 여기서만** |
-| `hotfix/*` | 긴급 수정 -> 태그 -> 배포 -> develop 머지 |
-
-**퍼블리싱 흐름:**
-```
-develop → release/x.y.z → npm publish → develop 머지
-```
-
-**핵심 규칙:**
-- `develop`에서 feature 브랜치 생성
-- **npm publish는 반드시 release 브랜치에서만**
-- Conventional commits 사용: `feat:`, `fix:`, `docs:`, `chore:`
-- 커밋 메시지에 "Closes #N" 포함시 이슈 자동 종료
-- Pre-commit 훅이 테스트 자동 실행
-
-자세한 워크플로우는 [CONTRIBUTING.md](CONTRIBUTING.md) 참조.
+<!-- omcustom:git-workflow -->

package/templates/guides/index.yaml

@@ -100,6 +100,55 @@ guides:
       origin: aws.amazon.com
       url: https://docs.aws.amazon.com/wellarchitected/
 
+  # Data Engineering
+  - name: airflow
+    description: Apache Airflow DAG development best practices
+    path: ./airflow/
+    source:
+      type: external
+      origin: airflow.apache.org
+      url: https://airflow.apache.org/docs/
+
+  - name: dbt
+    description: dbt SQL modeling and analytics engineering best practices
+    path: ./dbt/
+    source:
+      type: external
+      origin: docs.getdbt.com
+      url: https://docs.getdbt.com/
+
+  - name: kafka
+    description: Apache Kafka event streaming best practices
+    path: ./kafka/
+    source:
+      type: external
+      origin: kafka.apache.org
+      url: https://kafka.apache.org/documentation/
+
+  - name: spark
+    description: Apache Spark distributed data processing best practices
+    path: ./spark/
+    source:
+      type: external
+      origin: spark.apache.org
+      url: https://spark.apache.org/docs/latest/
+
+  - name: snowflake
+    description: Snowflake cloud data warehouse best practices
+    path: ./snowflake/
+    source:
+      type: external
+      origin: docs.snowflake.com
+      url: https://docs.snowflake.com/
+
+  - name: iceberg
+    description: Apache Iceberg open table format best practices
+    path: ./iceberg/
+    source:
+      type: external
+      origin: iceberg.apache.org
+      url: https://iceberg.apache.org/docs/latest/
+
   # Database
   - name: supabase-postgres
     description: Supabase and PostgreSQL best practices reference
@@ -108,3 +157,28 @@ guides:
       type: external
       origin: github
       url: https://github.com/supabase/agent-skills
+
+  - name: postgres
+    description: PostgreSQL database administration and PG-specific SQL patterns
+    path: ./postgres/
+    source:
+      type: external
+      origin: postgresql.org
+      url: https://www.postgresql.org/docs/current/
+
+  - name: redis
+    description: Redis in-memory data store best practices and command patterns
+    path: ./redis/
+    source:
+      type: external
+      origin: redis.io
+      url: https://redis.io/docs/
+
+  # Writing
+  - name: elements-of-style
+    description: The Elements of Style writing clarity guidelines
+    path: ./elements-of-style/
+    source:
+      type: external
+      origin: public-domain
+      url: https://www.gutenberg.org/ebooks/37134