oh-my-customcode 0.30.2 → 0.30.4

package/README.md

@@ -21,7 +21,7 @@ Like oh-my-zsh transformed shell customization, oh-my-customcode makes personali
 
 | Feature | Description |
 |---------|-------------|
-| **Batteries Included** | 42 agents, 66 skills, 22 guides, 18 rules, 2 hooks, 4 contexts, ontology graph - ready to use out of the box |
+| **Batteries Included** | 43 agents, 67 skills, 23 guides, 18 rules, 2 hooks, 4 contexts, ontology graph - ready to use out of the box |
 | **Sub-Agent Model** | Supports hierarchical agent orchestration with specialized roles |
 | **Dead Simple Customization** | Create a folder + markdown file = new agent or skill |
 | **Mix and Match** | Use built-in components, create your own, or combine both |
@@ -93,15 +93,67 @@ Claude Code selects the appropriate model and parallelizes independent tasks (up
   └── qa-engineer:sonnet        — test generation
 ```
 
-### Built-in Commands
+### Slash Commands
 
-| Command | Agent | Description |
-|---------|-------|-------------|
-| `/create-agent <name>` | mgr-creator | Create a new agent |
-| `/update-docs` | mgr-updater | Sync docs with project structure |
-| `/audit-agents` | mgr-supplier | Verify agent dependencies |
-| `/dev-review` | lang-* experts | Review code with expert agents |
-| `/sauron-watch` | mgr-sauron | Full synchronization check |
+All commands are invoked inside the Claude Code conversation.
+
+#### Analysis & Research
+
+| Command | Description |
+|---------|-------------|
+| `/analysis` | Analyze project and auto-configure agents, skills, rules |
+| `/research` | 10-team parallel deep analysis with cross-verification |
+
+#### Development
+
+| Command | Description |
+|---------|-------------|
+| `/dev-review` | Code review against best practices |
+| `/dev-refactor` | Code refactoring for better structure |
+
+#### Agent Management
+
+| Command | Description |
+|---------|-------------|
+| `/create-agent` | Create new agent |
+| `/update-docs` | Sync project structure and documentation |
+| `/update-external` | Update agents from external sources |
+| `/audit-agents` | Audit agent dependencies |
+| `/fix-refs` | Fix broken references |
+
+#### Memory
+
+| Command | Description |
+|---------|-------------|
+| `/memory-save` | Save session context to claude-mem |
+| `/memory-recall` | Search and recall memories |
+
+#### DevOps & Publishing
+
+| Command | Description |
+|---------|-------------|
+| `/npm-publish` | Publish package to npm registry |
+| `/npm-version` | Semantic version management |
+| `/npm-audit` | Dependency security audit |
+
+#### Optimization
+
+| Command | Description |
+|---------|-------------|
+| `/optimize-analyze` | Bundle and performance analysis |
+| `/optimize-bundle` | Bundle size optimization |
+| `/optimize-report` | Generate optimization report |
+
+#### Verification & System
+
+| Command | Description |
+|---------|-------------|
+| `/sauron-watch` | Full R017 sync verification |
+| `/monitoring-setup` | OTel console monitoring enable/disable |
+| `/codex-exec` | Execute Codex CLI prompt |
+| `/lists` | Show all available commands |
+| `/status` | System status and health checks |
+| `/help` | Help information |
 
 ---
 
@@ -123,7 +175,7 @@ Claude Code selects the appropriate model and parallelizes independent tasks (up
 | **Infrastructure** | 2 | infra-docker-expert, infra-aws-expert |
 | **QA** | 3 | qa-planner, qa-writer, qa-engineer |
 | **Security** | 1 | sec-codeql-expert |
-| **Total** | **42** | |
+| **Total** | **43** | |
 
 ### Skills (67)
 
@@ -223,12 +275,12 @@ your-project/
     ├── rules/             # Behavior rules (18 total)
     ├── hooks/             # Event hooks (2 total)
     ├── contexts/          # Context files (4 total)
-    ├── agents/            # Agent definitions (42 flat .md files)
+    ├── agents/            # Agent definitions (43 flat .md files)
     │   ├── lang-golang-expert.md
     │   ├── be-fastapi-expert.md
     │   ├── mgr-creator.md
     │   └── ...
-    ├── skills/            # Skill modules (66 directories, each with SKILL.md)
+    ├── skills/            # Skill modules (67 directories, each with SKILL.md)
     │   ├── go-best-practices/
     │   ├── react-best-practices/
     │   ├── secretary-routing/
@@ -239,7 +291,7 @@ your-project/
     │   ├── skills.yaml
     │   ├── rules.yaml
     │   └── graphs/
-    └── guides/            # Reference docs (22 total)
+    └── guides/            # Reference docs (23 total)
 ```
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.30.2",
+  "version": "0.30.4",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

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

@@ -186,7 +186,7 @@ Hybrid Workflow:
 | Step | Agent | Model |
 |------|-------|-------|
 | Analysis | Claude team member | sonnet/opus |
-| Generation | codex-exec | o3/o4-mini |
+| Generation | codex-exec | (Codex default) |
 | Review | Claude team member | sonnet |
 | Refinement | Appropriate expert | sonnet |
 

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

@@ -52,6 +52,12 @@ The main conversation is the **sole orchestrator**. It uses routing skills to de
 ║     YES → Good. Continue.                                        ║
 ║     NO  → STOP. This is a VIOLATION. Re-route to mgr-gitnerd.   ║
 ║                                                                   ║
+║  4. Am I about to spawn 2+ agents in parallel?                   ║
+║     YES → Check R018: Agent Teams may be REQUIRED                ║
+║           3+ agents → MUST use Agent Teams                       ║
+║           2+ issues in batch → SHOULD use Agent Teams            ║
+║     NO  → Proceed                                                ║
+║                                                                   ║
 ║  If ANY answer is wrong → SPLIT THE TASK                         ║
 ╚══════════════════════════════════════════════════════════════════╝
 ```

package/templates/.claude/rules/MUST-parallel-execution.md

@@ -15,7 +15,12 @@ Independent (MUST parallelize):
 
 Examples: creating multiple agents, reviewing multiple files, batch operations on different resources.
 
-## Agent Teams Gate (R018 Integration)
+## CRITICAL: Agent Teams Gate (R018)
+
+> **WARNING**: Before spawning 2+ parallel agents, you MUST evaluate Agent Teams eligibility.
+> Skipping this check is a VIOLATION of both R009 and R018.
+>
+> Quick rule: **3+ agents OR review cycle OR 2+ issues in same batch → Agent Teams (MUST)**
 
 Before spawning parallel Agent instances, evaluate Agent Teams eligibility:
 

package/templates/.claude/skills/research/SKILL.md

@@ -211,6 +211,19 @@ Round N:
 |---|------|--------|----------|-------|
 ```
 
+## Post-Research Advisory
+
+After research completion, the orchestrator SHOULD display:
+
+```
+[Advisory] Research complete.
+├── For complex implementations (10+ files): /structured-dev-cycle
+├── For quick planning: EnterPlanMode (plan mode)
+└── For simple tasks (< 3 files): proceed directly
+```
+
+This advisory is informational only and does not block execution.
+
 ## Fallback Behavior
 
 | Scenario | Fallback |

package/templates/.claude/skills/structured-dev-cycle/SKILL.md

@@ -2,7 +2,7 @@
 name: structured-dev-cycle
 description: 6-stage structured development cycle with stage-based tool restrictions
 version: 1.0.0
-user-invocable: false
+user-invocable: true
 ---
 
 # Structured Development Cycle

package/templates/CLAUDE.md.en

@@ -17,7 +17,12 @@ Powered by oh-my-customcode.
 |     [agent-name] -> Tool: {tool}                                  |
 |     [agent-name] -> Target: {path}                                |
 |                                                                   |
-|  If NO to either -> FIX IMMEDIATELY before continuing             |
+|                                                                   |
+|  3. Am I about to spawn 2+ agents?                               |
+|     YES -> Check R018: Agent Teams may be REQUIRED                |
+|     3+ agents OR review cycle -> Agent Teams (MUST)               |
+|                                                                   |
+|  If NO to any -> FIX IMMEDIATELY before continuing                |
 +==================================================================+
 ```
 
@@ -164,6 +169,7 @@ Violation = immediate correction. No exception for "small changes".
 | `/optimize-bundle` | Optimize bundle size |
 | `/optimize-report` | Generate optimization report |
 | `/sauron-watch` | Full R017 verification |
+| `/structured-dev-cycle` | 6-stage structured development cycle (Plan → Verify → Implement → Verify → Compound → Done) |
 | `/lists` | Show all available commands |
 | `/status` | Show system status |
 | `/help` | Show help information |

package/templates/CLAUDE.md.ko

@@ -17,6 +17,11 @@ oh-my-customcode로 구동됩니다.
 |     [에이전트명] -> Tool: {도구}                                  |
 |     [에이전트명] -> Target: {경로}                                |
 |                                                                   |
+|                                                                   |
+|  3. 2개 이상 에이전트를 스폰하려 하는가?                          |
+|     YES -> R018 체크: Agent Teams 필수 여부 확인                  |
+|     3+ 에이전트 OR 리뷰 사이클 -> Agent Teams 필수                |
+|                                                                   |
 |  하나라도 NO면 -> 즉시 수정 후 계속                               |
 +==================================================================+
 ```
@@ -164,6 +169,7 @@ oh-my-customcode로 구동됩니다.
 | `/optimize-bundle` | 번들 크기 최적화 |
 | `/optimize-report` | 최적화 리포트 생성 |
 | `/sauron-watch` | 전체 R017 검증 |
+| `/structured-dev-cycle` | 6단계 구조적 개발 사이클 (Plan → Verify → Implement → Verify → Compound → Done) |
 | `/lists` | 모든 사용 가능한 커맨드 표시 |
 | `/status` | 시스템 상태 표시 |
 | `/help` | 도움말 표시 |

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.30.2",
+  "version": "0.30.4",
   "lastUpdated": "2026-03-09T00:00:00.000Z",
   "components": [
     {