oh-my-customcode 0.16.2 → 0.16.3

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, 55 skills, 22 guides, 18 rules, 1 hook, 4 contexts, ontology graph - ready to use out of the box |
+| **Batteries Included** | 42 agents, 55 skills, 22 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 |
@@ -161,7 +161,7 @@ Comprehensive reference documentation covering:
 | **SHOULD** | 5 | Interactions, error handling (recommended) |
 | **MAY** | 1 | Optimization guidelines (optional) |
 
-### Hooks (1)
+### Hooks (2)
 
 Event-driven automation for agent lifecycle events (PreToolUse, PostToolUse, etc.).
 
@@ -219,7 +219,7 @@ your-project/
 ├── CLAUDE.md              # Entry point for Claude
 └── .claude/
     ├── rules/             # Behavior rules (18 total)
-    ├── hooks/             # Event hooks (1 total)
+    ├── hooks/             # Event hooks (2 total)
     ├── contexts/          # Context files (4 total)
     ├── agents/            # Agent definitions (42 flat .md files)
     │   ├── lang-golang-expert.md

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.16.2",
+  "version": "0.16.3",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/ontology/graphs/full-graph.json

@@ -111,7 +111,7 @@
     "R011": { "type": "Rule", "class": "ShouldRule" },
     "R012": { "type": "Rule", "class": "ShouldRule" },
     "R013": { "type": "Rule", "class": "ShouldRule" },
-    "R018": { "type": "Rule", "class": "ShouldRule" },
+    "R018": { "type": "Rule", "class": "MustRule" },
     "R005": { "type": "Rule", "class": "MayRule" }
   },
   "edges": [

package/templates/.claude/ontology/rules.yaml

@@ -6,10 +6,10 @@ generated_at: "2026-02-12T00:00:00Z"
 # Rule priority classes
 classes:
   MustRule:
-    rules: [R000, R001, R002, R006, R007, R008, R009, R010, R015, R016, R017]
+    rules: [R000, R001, R002, R006, R007, R008, R009, R010, R015, R016, R017, R018]
     description: "Mandatory rules - violation requires immediate correction"
   ShouldRule:
-    rules: [R003, R004, R011, R012, R013, R018]
+    rules: [R003, R004, R011, R012, R013]
     description: "Recommended rules - strong guidance"
   MayRule:
     rules: [R005]
@@ -231,21 +231,21 @@ rules:
     applies_to: [agent-modification, skill-modification, guide-modification, rules-modification]
 
   R018:
-    class: ShouldRule
+    class: MustRule
     categories: [teams]
-    title: "Agent Teams Rules"
-    filename: "SHOULD-agent-teams.md"
-    summary: "Use Agent Teams for 3+ agent coordinated tasks with shared state. Task tool for simple/independent work."
-    keywords: [agent-teams, coordination, shared-state, task-tool, broadcast, message, cost]
-    token_estimate: 267
+    title: "Agent Teams Rules (Conditional)"
+    filename: "MUST-agent-teams.md"
+    summary: "When Agent Teams enabled, MANDATORY for 3+ agent coordinated tasks with shared state or review cycles. Task tool fallback when disabled."
+    keywords: [agent-teams, coordination, shared-state, task-tool, broadcast, message, cost, mandatory]
+    token_estimate: 850
     applies_to: [multi-agent-coordination, complex-research]
 
 # Metadata
 metadata:
   total_rules: 18
-  must_rules: 11
-  should_rules: 6
+  must_rules: 12
+  should_rules: 5
   may_rules: 1
-  total_tokens_estimate: 5318
+  total_tokens_estimate: 5901
   source_directory: "templates/.claude/rules/"
   generated_by: "claude (default)"

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

@@ -0,0 +1,167 @@
+# [MUST] Agent Teams Rules (Conditional)
+
+> **Priority**: MUST - ENFORCED | **ID**: R018
+> **Condition**: Agent Teams enabled (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`)
+> **Fallback**: When disabled, R009/R010 apply
+
+## Detection
+
+Available when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present.
+
+## Decision Matrix
+
+| Scenario | Preferred | Reason |
+|----------|-----------|--------|
+| Simple independent subtasks | Task Tool | Lower cost, no coordination overhead |
+| Multi-step with shared state | **Agent Teams** | Shared task list, peer messaging |
+| Research requiring discussion | **Agent Teams** | Iterative discovery, synthesis |
+| Cost-sensitive batch ops | Task Tool | Minimal token overhead |
+| Complex debugging across modules | **Agent Teams** | Cross-module state sharing |
+| Code review + fix cycle | **Agent Teams** | Review → fix → re-review loop |
+| Single file operations | Task Tool | Overkill for simple tasks |
+| Dynamic agent creation + usage | **Agent Teams** | Create → test → iterate cycle |
+
+**When Agent Teams is enabled and criteria are met, usage is MANDATORY.**
+
+## Self-Check (MANDATORY Before Task Tool)
+
+BEFORE using Task tool for 2+ agent tasks, this check is **ENFORCED**:
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  BEFORE USING Task TOOL FOR 2+ AGENTS:                          ║
+║                                                                   ║
+║  1. Is Agent Teams available?                                    ║
+║     YES → MUST check criteria #2-#5                              ║
+║     NO  → Proceed with Task tool                                ║
+║                                                                   ║
+║  2. Do 2+ agents need to coordinate? → Agent Teams              ║
+║  3. Is there a review/fix/iterate cycle? → Agent Teams          ║
+║  4. Do agents need shared state? → Agent Teams                   ║
+║  5. Is research requiring synthesis? → Agent Teams              ║
+║                                                                   ║
+║  If YES to #1 AND any of #2-#5:                                  ║
+║  → MUST use Agent Teams                                          ║
+║  → Using Task tool instead is a VIOLATION                        ║
+║                                                                   ║
+║  Exception: Cost-sensitive batch ops with no inter-agent need    ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
+## Common Violations
+
+```
+❌ WRONG: Agent Teams enabled, 3+ research tasks using Task tool
+   Task(Explore):haiku → Analysis 1
+   Task(Explore):haiku → Analysis 2
+   Task(Explore):haiku → Analysis 3
+
+✓ CORRECT: TeamCreate → spawn researchers → coordinate via shared task list
+   TeamCreate("research-team")
+   Task(researcher-1) → Analysis 1  ┐
+   Task(researcher-2) → Analysis 2  ├─ Spawned as team members
+   Task(researcher-3) → Analysis 3  ┘
+   SendMessage(coordinate)
+
+❌ WRONG: Code review + fix as independent Tasks
+   Task(reviewer) → "Review code"
+   (receive result)
+   Task(implementer) → "Fix issues"
+   (receive result)
+   Task(reviewer) → "Re-review"
+
+✓ CORRECT: Agent Teams for review-fix cycle
+   TeamCreate("review-fix")
+   Task(reviewer) + Task(implementer) → team members
+   reviewer → SendMessage(implementer, "issues found")
+   implementer → fixes → SendMessage(reviewer, "fixed")
+   reviewer → re-reviews → done
+
+❌ WRONG: Multi-expert task without coordination
+   Task(lang-typescript-expert) → "Implement frontend"
+   Task(be-express-expert) → "Implement API"
+   (no shared state, results manually combined)
+
+✓ CORRECT: Agent Teams for cross-domain work
+   TeamCreate("fullstack")
+   Task(frontend-dev) + Task(backend-dev) → team members
+   Shared TaskList for interface contracts
+   SendMessage for API schema coordination
+```
+
+## Cost Guidelines
+
+| Criteria | Task Tool | Agent Teams |
+|----------|-----------|-------------|
+| Agent count | 1-2 | 3+ |
+| Inter-task dependency | None | Present |
+| Iteration cycles | None | Present (review→fix→re-review) |
+| Estimated duration | < 3 min | > 3 min |
+| Shared state needed | No | Yes |
+
+## Team Patterns
+
+### Standard Patterns
+
+- **Research**: researcher-1 + researcher-2 + synthesizer
+- **Development**: implementer + reviewer + tester
+- **Debug**: investigator-1 + investigator-2 + fixer
+
+### Hybrid Patterns
+
+- **Review+Fix**: reviewer + implementer (reviewer finds issues → implementer fixes → reviewer re-checks)
+- **Create+Validate**: mgr-creator + qa-engineer (create agent → validate → iterate)
+- **Multi-Expert**: expert-1 + expert-2 + coordinator (cross-domain tasks requiring multiple specialties)
+
+### Dynamic Patterns
+
+- **Dynamic Creation**: mgr-creator + domain-expert (create new agent → immediately use for pending task)
+- **Codex Hybrid**: codex-exec-agent + claude-reviewer (Codex generates → Claude reviews/refines)
+
+## Codex-Exec Integration
+
+When both Agent Teams and codex-exec are available:
+
+```
+Hybrid Workflow:
+  1. Claude agent analyzes requirements
+  2. codex-exec generates implementation (Codex strength: code generation)
+  3. Claude agent reviews and refines (Claude strength: reasoning, quality)
+  4. Iterate via team messaging until quality meets standards
+```
+
+| Step | Agent | Model |
+|------|-------|-------|
+| Analysis | Claude team member | sonnet/opus |
+| Generation | codex-exec | o3/o4-mini |
+| Review | Claude team member | sonnet |
+| Refinement | Appropriate expert | sonnet |
+
+## Dynamic Agent Creation in Teams
+
+When Agent Teams creates a new agent via mgr-creator:
+
+1. Team lead identifies missing expertise
+2. Spawns mgr-creator as team member
+3. mgr-creator creates agent with auto-discovered skills
+4. New agent joins team immediately
+5. Team continues with expanded capabilities
+
+## Lifecycle
+
+```
+TeamCreate → TaskCreate → Task(spawn members) → SendMessage(coordinate)
+  → TaskUpdate(progress) → ... → shutdown members → TeamDelete
+```
+
+## Fallback
+
+When Agent Teams unavailable: use Task tool with R009/R010 rules. Both approaches produce results; Agent Teams adds coordination richness.
+
+## Cost Awareness
+
+Agent Teams uses more tokens (full context per member + message passing). Use Task tool when:
+- Task takes < 3 minutes
+- No inter-agent communication needed
+- Simple independent subtasks only
+- Cost is the primary concern

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

@@ -191,9 +191,32 @@ CORRECT:
 The skill's WORKFLOW is followed, but git EXECUTION is delegated to mgr-gitnerd per R010.
 ```
 
-## Agent Teams (when enabled)
+## Agent Teams (MUST when enabled)
 
-When `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`: prefer Agent Teams for 2+ agent coordinated tasks requiring shared state or inter-agent communication. See R018 for the decision matrix. Task tool remains fallback for simple/independent tasks.
+When `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`: Agent Teams is **MANDATORY** for qualifying tasks per R018 (MUST-agent-teams.md).
+
+### Architecture (Agent Teams enabled)
+
+```
+Main Conversation (orchestrator)
+  ├─ Simple/independent tasks → Task tool (R009)
+  └─ Collaborative/iterative tasks → Agent Teams (R018)
+      ├─ TeamCreate
+      ├─ TaskCreate (shared tasks)
+      ├─ Task(spawn members)
+      └─ SendMessage(coordinate)
+```
+
+### When to Use Agent Teams vs Task Tool
+
+| Criteria | Task Tool | Agent Teams (MUST) |
+|----------|-----------|-------------------|
+| Agent count | 1-2 | 3+ |
+| Coordination needed | No | Yes |
+| Review/fix cycles | No | Yes |
+| Shared state | No | Yes |
+
+Using Task tool when Agent Teams criteria are met is a **VIOLATION** of R018.
 
 ## Announcement Format
 

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

@@ -124,12 +124,12 @@ rules:
     priority: SHOULD
     scope: all
 
-  # Agent Teams - SHOULD
+  # Agent Teams - MUST (Conditional)
   - id: R018
     name: agent-teams
-    title: Agent Teams Rules
-    path: ./SHOULD-agent-teams.md
-    priority: SHOULD
+    title: Agent Teams Rules (Conditional)
+    path: ./MUST-agent-teams.md
+    priority: MUST
     scope: orchestrator
 
   # MAY - Optional

package/templates/CLAUDE.md.en

@@ -122,6 +122,7 @@ Violation = immediate correction. No exception for "small changes".
 | 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 |
+| R018 | Agent Teams | **ENFORCED (Conditional)** - Mandatory for qualifying tasks when Agent Teams enabled |
 
 ### SHOULD (Strongly recommended)
 | ID | Rule | Description |
@@ -132,7 +133,6 @@ Violation = immediate correction. No exception for "small changes".
 | 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 |
 
 ### MAY (Optional)
 | ID | Rule | Description |
@@ -219,7 +219,7 @@ This is the core oh-my-customcode philosophy: **"No expert? CREATE one, connect
 | System | 2 | sys-memory-keeper, sys-naggy |
 | **Total** | **42** | |
 
-## Agent Teams
+## Agent Teams (MUST when enabled)
 
 When Claude Code's Agent Teams feature is enabled (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`), actively use it for qualifying tasks.
 
@@ -230,8 +230,8 @@ When Claude Code's Agent Teams feature is enabled (`CLAUDE_CODE_EXPERIMENTAL_AGE
 | Best for | Focused tasks | Research, review, debugging |
 | Token cost | Lower | Higher |
 
-**When enabled, ACTIVELY prefer Agent Teams for qualifying collaborative tasks.**
-See R018 (SHOULD-agent-teams.md) for the decision matrix.
+**When enabled, Agent Teams is MANDATORY for qualifying collaborative tasks (R018 MUST).**
+See R018 (MUST-agent-teams.md) for the decision matrix.
 Hybrid patterns (Claude + Codex, Dynamic Creation + Teams) are supported.
 Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
 
@@ -268,7 +268,6 @@ Install via `/plugin install <name>`:
 | superpowers | claude-plugins-official | TDD, debugging, collaboration patterns |
 | superpowers-developing-for-claude-code | superpowers-marketplace | Claude Code development documentation |
 | elements-of-style | superpowers-marketplace | Writing clarity guidelines |
-| double-shot-latte | superpowers-marketplace | Continuation prompt automation |
 | obsidian-skills | - | Obsidian markdown support |
 | context7 | claude-plugins-official | Library documentation lookup |
 
@@ -288,7 +287,6 @@ Install via `/plugin install <name>`:
 /plugin install superpowers
 /plugin install superpowers-developing-for-claude-code
 /plugin install elements-of-style
-/plugin install double-shot-latte
 
 # MCP setup (claude-mem)
 npm install -g claude-mem

package/templates/CLAUDE.md.ko

@@ -122,6 +122,7 @@ oh-my-customcode로 구동됩니다.
 | 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 |
+| R018 | Agent Teams | **강제(조건부)** - Agent Teams 활성화 시 적합한 작업에 필수 사용 |
 
 ### SHOULD (강력 권장)
 | ID | 규칙 | 설명 |
@@ -132,7 +133,6 @@ oh-my-customcode로 구동됩니다.
 | 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 |
 
 ### MAY (선택)
 | ID | 규칙 | 설명 |
@@ -219,7 +219,7 @@ project/
 | System | 2 | sys-memory-keeper, sys-naggy |
 | **총계** | **42** | |
 
-## Agent Teams
+## Agent Teams (MUST when enabled)
 
 Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`), 적격한 작업에 적극적으로 사용합니다.
 
@@ -230,8 +230,8 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 | 적합한 작업 | 집중된 작업 | 리서치, 리뷰, 디버깅 |
 | 토큰 비용 | 낮음 | 높음 |
 
-**활성화 시, 적격한 협업 작업에 Agent Teams를 적극적으로 우선 사용합니다.**
-결정 매트릭스는 R018 (SHOULD-agent-teams.md)을 참조하세요.
+**활성화 시, 적격한 협업 작업에 Agent Teams를 반드시 사용해야 합니다 (R018 MUST).**
+결정 매트릭스는 R018 (MUST-agent-teams.md)을 참조하세요.
 하이브리드 패턴 (Claude + Codex, 동적 생성 + Teams)이 지원됩니다.
 단순/비용 민감 작업에는 Task tool + 라우팅 스킬이 폴백으로 유지됩니다.
 
@@ -268,7 +268,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 | superpowers | claude-plugins-official | TDD, 디버깅, 협업 패턴 |
 | superpowers-developing-for-claude-code | superpowers-marketplace | Claude Code 개발 문서 |
 | elements-of-style | superpowers-marketplace | 글쓰기 명확성 가이드라인 |
-| double-shot-latte | superpowers-marketplace | 연속 프롬프트 자동화 |
 | obsidian-skills | - | 옵시디언 마크다운 지원 |
 | context7 | claude-plugins-official | 라이브러리 문서 조회 |
 
@@ -288,7 +287,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 /plugin install superpowers
 /plugin install superpowers-developing-for-claude-code
 /plugin install elements-of-style
-/plugin install double-shot-latte
 
 # MCP 설정 (claude-mem)
 npm install -g claude-mem

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

@@ -1,107 +0,0 @@
-# [SHOULD] Agent Teams Rules
-
-> **Priority**: SHOULD | **ID**: R018 | **Condition**: Agent Teams enabled locally
-
-## Detection
-
-Available when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` or TeamCreate/SendMessage tools present.
-
-## Decision Matrix
-
-| Scenario | Preferred | Reason |
-|----------|-----------|--------|
-| Simple independent subtasks | Task Tool | Lower cost, no coordination overhead |
-| Multi-step with shared state | **Agent Teams** | Shared task list, peer messaging |
-| Research requiring discussion | **Agent Teams** | Iterative discovery, synthesis |
-| Cost-sensitive batch ops | Task Tool | Minimal token overhead |
-| Complex debugging across modules | **Agent Teams** | Cross-module state sharing |
-| Code review + fix cycle | **Agent Teams** | Review → fix → re-review loop |
-| Single file operations | Task Tool | Overkill for simple tasks |
-| Dynamic agent creation + usage | **Agent Teams** | Create → test → iterate cycle |
-
-**ACTIVELY prefer Agent Teams for qualifying tasks.** The coordination richness justifies the token cost for complex work.
-
-## Self-Check (Mandatory Before Task Tool)
-
-BEFORE using Task tool for 2+ agent tasks, CHECK:
-
-```
-╔════════════════════════════════════════════════════════╗
-║  AGENT TEAMS CHECK:                                    ║
-║                                                        ║
-║  1. Is Agent Teams available?                          ║
-║  2. Does task need 3+ agents?                          ║
-║  3. Do agents need shared state?                       ║
-║  4. Is inter-agent communication needed?               ║
-║  5. Is there a review/fix/iterate cycle?               ║
-║                                                        ║
-║  If YES to #1 AND any of #2-#5 → USE Agent Teams      ║
-╚════════════════════════════════════════════════════════╝
-```
-
-## Team Patterns
-
-### Standard Patterns
-
-- **Research**: researcher-1 + researcher-2 + synthesizer
-- **Development**: implementer + reviewer + tester
-- **Debug**: investigator-1 + investigator-2 + fixer
-
-### Hybrid Patterns
-
-- **Review+Fix**: reviewer + implementer (reviewer finds issues → implementer fixes → reviewer re-checks)
-- **Create+Validate**: mgr-creator + qa-engineer (create agent → validate → iterate)
-- **Multi-Expert**: expert-1 + expert-2 + coordinator (cross-domain tasks requiring multiple specialties)
-
-### Dynamic Patterns
-
-- **Dynamic Creation**: mgr-creator + domain-expert (create new agent → immediately use for pending task)
-- **Codex Hybrid**: codex-exec-agent + claude-reviewer (Codex generates → Claude reviews/refines)
-
-## Codex-Exec Integration
-
-When both Agent Teams and codex-exec are available:
-
-```
-Hybrid Workflow:
-  1. Claude agent analyzes requirements
-  2. codex-exec generates implementation (Codex strength: code generation)
-  3. Claude agent reviews and refines (Claude strength: reasoning, quality)
-  4. Iterate via team messaging until quality meets standards
-```
-
-| Step | Agent | Model |
-|------|-------|-------|
-| Analysis | Claude team member | sonnet/opus |
-| Generation | codex-exec | o3/o4-mini |
-| Review | Claude team member | sonnet |
-| Refinement | Appropriate expert | sonnet |
-
-## Dynamic Agent Creation in Teams
-
-When Agent Teams creates a new agent via mgr-creator:
-
-1. Team lead identifies missing expertise
-2. Spawns mgr-creator as team member
-3. mgr-creator creates agent with auto-discovered skills
-4. New agent joins team immediately
-5. Team continues with expanded capabilities
-
-## Lifecycle
-
-```
-TeamCreate → TaskCreate → Task(spawn members) → SendMessage(coordinate)
-  → TaskUpdate(progress) → ... → shutdown members → TeamDelete
-```
-
-## Fallback
-
-When Agent Teams unavailable: use Task tool with R009/R010 rules. Both approaches produce results; Agent Teams adds coordination richness.
-
-## Cost Awareness
-
-Agent Teams uses more tokens (full context per member + message passing). Use Task tool when:
-- Task takes < 3 minutes
-- No inter-agent communication needed
-- Simple independent subtasks only
-- Cost is the primary concern