oh-my-customcode 0.156.3 → 0.158.0

package/templates/.claude/ontology/graphs/skill-rule.json

@@ -8,7 +8,9 @@
     "claude-code-bible": [],
     "create-agent": [],
     "dbt-best-practices": [],
-    "de-lead-routing": ["R009"],
+    "de-lead-routing": [
+      "R009"
+    ],
     "dev-lead-routing": [],
     "dev-refactor": [],
     "dev-review": [],
@@ -19,13 +21,12 @@
     "go-backend-best-practices": [],
     "go-best-practices": [],
     "help": [],
-    "intent-detection": ["R015"],
+    "intent-detection": [
+      "R015"
+    ],
     "kafka-best-practices": [],
     "kotlin-best-practices": [],
     "lists": [],
-    "memory-management": ["R011"],
-    "memory-recall": ["R011"],
-    "memory-save": ["R011"],
     "monitoring-setup": [],
     "npm-audit": [],
     "npm-publish": [],
@@ -39,9 +40,14 @@
     "qa-lead-routing": [],
     "react-best-practices": [],
     "redis-best-practices": [],
-    "result-aggregation": ["R009", "R013"],
+    "result-aggregation": [
+      "R009",
+      "R013"
+    ],
     "rust-best-practices": [],
-    "sauron-watch": ["R017"],
+    "sauron-watch": [
+      "R017"
+    ],
     "secretary-routing": [],
     "snowflake-best-practices": [],
     "spark-best-practices": [],
@@ -56,11 +62,20 @@
     "writing-clearly-and-concisely": []
   },
   "reverse": {
-    "R009": ["de-lead-routing", "result-aggregation"],
-    "R011": ["memory-management", "memory-recall", "memory-save"],
-    "R013": ["result-aggregation"],
-    "R015": ["intent-detection"],
-    "R017": ["sauron-watch"],
+    "R009": [
+      "de-lead-routing",
+      "result-aggregation"
+    ],
+    "R011": [],
+    "R013": [
+      "result-aggregation"
+    ],
+    "R015": [
+      "intent-detection"
+    ],
+    "R017": [
+      "sauron-watch"
+    ],
     "R000": [],
     "R001": [],
     "R002": [],
@@ -74,5 +89,7 @@
     "R012": [],
     "R016": [],
     "R018": []
-  }
+  },
+  "nodes": [],
+  "links": []
 }

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

@@ -40,7 +40,7 @@ categories:
   memory:
     rules: [R011]
     summary: "Memory integration and persistence"
-    keywords: [memory, persistence, claude-mem, session]
+    keywords: [memory, persistence, native-auto-memory, session]
   display:
     rules: [R012]
     summary: "HUD and status display"
@@ -175,8 +175,8 @@ rules:
     categories: [memory]
     title: "Memory Integration Rules"
     filename: "SHOULD-memory-integration.md"
-    summary: "Primary: Native auto memory (frontmatter). Supplementary: claude-mem MCP for cross-session search."
-    keywords: [memory, native, claude-mem, persistence, session, temporal, cross-agent]
+    summary: "Primary: Native auto memory (frontmatter). Session persistence via agent memory directories."
+    keywords: [memory, native, persistence, session, temporal, cross-agent]
     token_estimate: 248
     applies_to: [agents-with-memory, memory-operations]
 

package/templates/.claude/ontology/skills.yaml

@@ -29,10 +29,6 @@ classes:
     skills: [optimize-analyze, optimize-bundle, optimize-report]
     description: "Performance optimization"
 
-  MemorySkill:
-    skills: [memory-save, memory-recall, memory-management]
-    description: "Memory persistence operations"
-
   PackageSkill:
     skills: [npm-publish, npm-version, npm-audit]
     description: "Package management"
@@ -276,33 +272,6 @@ skills:
     keywords: [lists, commands, categories, system]
     rule_references: []
 
-  memory-management:
-    class: MemorySkill
-    description: "Memory persistence operations using claude-mem"
-    user_invocable: false
-    model_invocable: true
-    summary: "Provide memory persistence operations using claude-mem for session context"
-    keywords: [memory, claude-mem, persistence, session, context]
-    rule_references: [R011]
-
-  memory-recall:
-    class: MemorySkill
-    description: "Search and recall memories from claude-mem"
-    user_invocable: true
-    model_invocable: true
-    summary: "Search and recall relevant memories from claude-mem using semantic search"
-    keywords: [memory, recall, search, semantic, claude-mem]
-    rule_references: [R011]
-
-  memory-save:
-    class: MemorySkill
-    description: "Save current session context to claude-mem"
-    user_invocable: true
-    model_invocable: false
-    summary: "Save current session context to claude-mem for persistence across compaction"
-    keywords: [memory, save, session, context, claude-mem]
-    rule_references: [R011]
-
   monitoring-setup:
     class: MonitoringSkill
     description: "Enable/disable OpenTelemetry console monitoring for Claude Code usage tracking"

package/templates/.claude/profiles/data-eng.json

@@ -6,7 +6,6 @@
       "superpowers@claude-plugins-official",
       "context7@claude-plugins-official",
       "episodic-memory@superpowers-marketplace",
-      "claude-mem@thedotmack",
       "gopls-lsp@claude-plugins-official"
     ],
     "disabled": [

package/templates/.claude/profiles/harness-dev.json

@@ -10,7 +10,6 @@
       "superpowers-developing-for-claude-code@superpowers-marketplace",
       "context7@claude-plugins-official",
       "episodic-memory@superpowers-marketplace",
-      "claude-mem@thedotmack",
       "elements-of-style@superpowers-marketplace"
     ],
     "disabled": [

package/templates/.claude/profiles/minimal.json

@@ -4,8 +4,7 @@
   "plugins": {
     "enabled": [
       "superpowers@claude-plugins-official",
-      "episodic-memory@superpowers-marketplace",
-      "claude-mem@thedotmack"
+      "episodic-memory@superpowers-marketplace"
     ],
     "disabled": [
       "vercel@claude-plugins-official",

package/templates/.claude/profiles/web-app.json

@@ -9,8 +9,7 @@
       "typescript-lsp@claude-plugins-official",
       "context7@claude-plugins-official",
       "superpowers-developing-for-claude-code@superpowers-marketplace",
-      "episodic-memory@superpowers-marketplace",
-      "claude-mem@thedotmack"
+      "episodic-memory@superpowers-marketplace"
     ],
     "disabled": [
       "codex@openai-codex",

package/templates/.claude/rules/SHOULD-memory-integration.md

@@ -2,12 +2,11 @@
 
 > **Priority**: SHOULD | **ID**: R011
 
-## Architecture
+> **Note**: This project uses **native auto memory ONLY** (memory/MEMORY.md + agent frontmatter `memory:`). claude-mem and agentmemory MCP are NOT used in this project. Decision: issue #1253.
 
-**Primary**: Native auto memory (`memory` field in agent frontmatter). No external dependencies.
-**Supplementary**: claude-mem MCP (optional, for cross-session search and temporal queries).
+## Architecture
 
-Rule: If native auto memory can handle it, do NOT use claude-mem.
+**Sole backend**: Native auto memory (`memory` field in agent frontmatter). No external MCP dependencies.
 
 ## Native Auto Memory
 
@@ -22,15 +21,6 @@ Agent frontmatter `memory: project|user|local` enables persistent memory:
 | `project` | `.claude/agent-memory/<name>/` | Yes |
 | `local` | `.claude/agent-memory-local/<name>/` | No |
 
-## When to Use claude-mem
-
-| Scenario | Native | claude-mem |
-|----------|--------|------------|
-| Agent learns project patterns | Yes | |
-| Search across sessions | | Yes |
-| Temporal queries | | Yes |
-| Cross-agent sharing | | Yes |
-
 ## Best Practices
 
 - Consult memory before starting work
@@ -311,9 +301,9 @@ Related records from session v0.87.2~v0.88.0 (issue #869):
 
 Session-end detected when user says: "끝", "종료", "마무리", "done", "wrap up", "end session", or explicitly requests session save.
 
-See flow diagram, responsibility split, and dual-system save table via Read tool.
+See flow diagram and responsibility split via Read tool.
 
-<!-- DETAIL: Session-End Flow, Responsibility Split, Dual-System Save
+<!-- DETAIL: Session-End Flow, Responsibility Split
 ### Flow
 
 ```
@@ -323,35 +313,20 @@ User signals session end
        1. Collect session summary (tasks, decisions, open items)
        2. Update native auto-memory (MEMORY.md)
        3. Return formatted summary to orchestrator
-  → Orchestrator performs MCP saves directly:
-       1. claude-mem save (if available via ToolSearch)
-       (episodic-memory auto-indexes after session — no action needed)
   → Orchestrator confirms to user
 ```
 
 ### Responsibility Split
 
-MCP tools (claude-mem, episodic-memory) are **orchestrator-scoped** and not inherited by subagents. Therefore:
-
 | Responsibility | Owner | Reason |
 |----------------|-------|--------|
 | Session summary collection | sys-memory-keeper | Domain expertise in memory formatting |
 | Native auto-memory (MEMORY.md) | sys-memory-keeper | Has Write access to memory directory |
-| claude-mem MCP save | Orchestrator | MCP tools only available at orchestrator level |
-| episodic-memory | Automatic | Conversations are auto-indexed after session ends — no manual action needed |
-
-### Dual-System Save
-
-| System | Owner | Tool | Action | Required |
-|--------|-------|------|--------|----------|
-| Native auto-memory | sys-memory-keeper | Write | Update MEMORY.md with session learnings | Yes |
-| claude-mem | Orchestrator | `mcp__plugin_claude-mem_mcp-search__save_memory` | Save session summary with project, tasks, decisions | No (best-effort) |
-| episodic-memory | Automatic | (auto-indexed) | No action needed — conversations are indexed automatically after session ends | N/A |
 -->
 
 ### Session-End Self-Check (MANDATORY)
 
-(1) sys-memory-keeper updated MEMORY.md? (2) claude-mem save attempted? (3) If `omcustom-feedback` skill is active, model MAY draft a retrospective feedback issue for user approval — or prompt user to trigger it manually. All three required before confirming to user. See full self-check via Read tool.
+(1) sys-memory-keeper updated MEMORY.md? (2) If `omcustom-feedback` skill is active, model MAY draft a retrospective feedback issue for user approval — or prompt user to trigger it manually. Both required before confirming to user. See full self-check via Read tool.
 
 <!-- DETAIL: Session-End Self-Check (MANDATORY)
 ```
@@ -362,23 +337,14 @@ MCP tools (claude-mem, episodic-memory) are **orchestrator-scoped** and not inhe
 ║     YES → Continue                                               ║
 ║     NO  → Delegate to sys-memory-keeper first                    ║
 ║                                                                   ║
-║  2. Did I attempt claude-mem save?                               ║
-║     YES → Continue (even if it failed)                           ║
-║     NO  → ToolSearch + save now                                  ║
-║                                                                   ║
-║  3. Is omcustom-feedback skill available in this project?        ║
+║  2. Is omcustom-feedback skill available in this project?        ║
 ║     YES → If notable friction/learning observed: MODEL DRAFTS    ║
 ║          retrospective issue → presents via Phase 4A preview     ║
 ║          gate for user approval. Otherwise: prompt user to       ║
 ║          trigger manually. Accept skip either way.               ║
 ║     NO  → Skip                                                    ║
 ║                                                                   ║
-║  Note: episodic-memory auto-indexes conversations after session  ║
-║  ends. No manual action needed — do NOT search as "verification" ║
-║                                                                   ║
 ║  ALL steps must be completed before confirming to user.          ║
-║  "Attempted" means called the tool — failure is OK, skipping     ║
-║  is NOT.                                                          ║
 ╚══════════════════════════════════════════════════════════════════╝
 ```
 -->
@@ -412,49 +378,5 @@ References: #1226 (item 3), #1227.
 
 ### Failure Policy
 
-- MCP saves are **non-blocking**: memory failure MUST NOT prevent session from ending
-- If claude-mem unavailable: skip, log warning
-- episodic-memory: no action needed (auto-indexed after session)
-
-## Dual-Backend Advisory (AgentMemory + claude-mem)
-
-#1169 Phase 1 (COEXIST) 단계에서 두 memory backend 동시 활성 가능:
-
-| 상황 | 권장 |
-|------|------|
-| claude-mem 단독 | 기본값 — 현 운영 유지 |
-| AgentMemory 단독 | Phase 2 (SWITCH) 이후 진행 |
-| 둘 다 활성 (COEXIST) | Phase 1 한정 — `memory-aggregator`가 결과 병합 |
-
-### 충돌 감지
-
-`.mcp.json`에 두 서버(`claude-mem`, `agentmemory`) 동시 등록 시 첫 호출 시점에 advisory 출력 권장:
-
-```
-[Advisory] Dual memory backend detected (Phase 1 COEXIST)
-  - claude-mem: active (Chroma)
-  - agentmemory: active (SQLite)
-  Phase 2 SWITCH 진입 전까지 두 backend 유지
-  가이드: guides/agentmemory-migration/phase-1-coexist.md
-```
-
-이 advisory는 경고가 아닙니다. Phase 1 COEXIST에서는 정상 상태입니다.
-
-### Session-End Self-Check (COEXIST 확장)
-
-Phase 1 COEXIST 기간 중 세션 종료 시:
-
-1. sys-memory-keeper가 MEMORY.md 갱신? → YES: 계속
-2. claude-mem 저장 시도? → YES (기존 항목)
-3. AgentMemory 저장 시도? → YES (COEXIST 추가)
-4. omcustom-feedback 처리? → YES (활성 시, notable friction 있으면 model draft → Phase 4A gate; 없으면 사용자 권유) / 스킵 (비활성 시)
-네 단계 모두 완료 후 사용자에게 확인. 둘 중 하나 실패해도 비차단.
-
-### Phase 2 진입 전 필수 조건
-
-- 1주 measure 결과 (`scripts/measure-claude-mem-usage.sh`) GO 판정
-- 자산 처리표 사용자 검토 완료 (12 plugin skill 처리 방향 결정)
-- 30분 롤백 절차 검증 (Chroma 백업 + 복원 테스트)
-
-Refs: #1169 본문 조치 3 (택1 강제), 조치 4 (롤백 절차),
-      `guides/agentmemory-migration/phase-1-coexist.md`.
+- Memory write failure is **non-blocking**: MUST NOT prevent session from ending
+- If sys-memory-keeper fails to write MEMORY.md: log warning, confirm to user anyway

package/templates/.claude/skills/agent-eval-framework/SKILL.md

@@ -112,8 +112,7 @@ oh-my-customcode uses existing infrastructure for trajectory capture:
 
 | Component | Role | How |
 |-----------|------|-----|
-| claude-mem | Capture step/tool sequences | `mcp__plugin_claude-mem_mcp-search__save_memory` with task_id + observed metrics |
-| episodic-memory | Cross-session trajectory comparison | Auto-indexed after session; query for historical baselines |
+| native MEMORY.md (R011) | Persist eval metrics across sessions | Write `## Metrics` section with task_id + observed metrics to agent-memory MEMORY.md |
 | statusline.sh (R012) | Real-time step counter during eval runs | Extend statusline with `STEPS=n` segment |
 | `.claude/outputs/evals/` | Artifact storage for eval results | Per-session eval reports in `sessions/{YYYY-MM-DD}/` |
 
@@ -121,7 +120,7 @@ oh-my-customcode uses existing infrastructure for trajectory capture:
 ```
 task start → record tool_calls[] + timestamps → task end
 → compute ratios against ideal trajectory
-→ save to claude-mem: {task_id, capability, correctness, step_ratio, tool_call_ratio, latency_ratio}
+→ write to native MEMORY.md ## Metrics: {task_id, capability, correctness, step_ratio, tool_call_ratio, latency_ratio}
 ```
 
 ### Persistent Storage (added v0.116.0, #1036)

package/templates/.claude/skills/crg-integration/SKILL.md

@@ -125,15 +125,7 @@ CRG는 recall 최적화 도구다. 다음 사항을 반드시 숙지한다:
 |------|----------|
 | `dev-review` | CRG로 영향 범위 파악 → dev-review로 상세 리뷰 |
 | `adversarial-review` | CRG `get_minimal_context` → adversarial-review 입력 최적화 |
-| `claude-mem:smart-explore` | CRG `query_graph`로 대체 가능 (Phase β 시퀀싱 — #1169 참조) |
-| `claude-mem:pathfinder` | CRG `get_impact_radius`로 대체 가능 (Phase β 시퀀싱 — #1169 참조) |
-
-### 마이그레이션 예정 (Phase β)
-
-- `claude-mem:smart-explore` → CRG `query_graph` (#1169)
-- `claude-mem:pathfinder` → CRG `get_impact_radius` (#1169)
-
-Phase β 완료 전까지는 두 자산을 병행 사용한다.
+| `semble-integration` | Semble (의미) + CRG (구조) 결합으로 완전한 코드 이해 |
 
 ## R013 Ecomode와의 관계
 
@@ -159,5 +151,4 @@ R013 ecomode가 자동 활성화되는 시점 (context 사용량 ≥ 60%)에서
 
 - 상세 설치/설정: `guides/token-efficiency/crg.md`
 - 관련 이슈: #1171 (scout:integrate CRG)
-- Phase β 시퀀싱: #1169 (AgentMemory 전환 계획)
 - 기술 출처: [tirth8205/code-review-graph](https://github.com/tirth8205/code-review-graph)

package/templates/.claude/skills/dev-review/SKILL.md

@@ -152,8 +152,7 @@ Reference: `feedback_sensitive_path_tmp_bypass.md`, R006 sensitive-path handling
 
 CRG MCP 미연결 시 자동 fallback:
 1. grep/Grep 도구로 영향 범위 추적
-2. `claude-mem:smart-explore` (Phase β 이후 deprecated)
-3. 전체 디렉토리 읽기 (R013 ecomode 트리거 가능성)
+2. 전체 디렉토리 읽기 (R013 ecomode 트리거 가능성)
 
 ### R013 Ecomode 정합
 

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

@@ -49,7 +49,7 @@ Example: `/goal Add a /weekly-summary command that aggregates last 7 days of git
 
 | Scenario | Use Instead |
 |----------|-------------|
-| Pure research/analysis | `research`, `idea`, `memory-recall` |
+| Pure research/analysis | `research`, `idea` |
 | Specialist domain task | Routing skills (`dev-lead-routing`, `de-lead-routing`, `qa-lead-routing`) |
 | Trivial single-file edit | Delegate directly to specialist agent |
 | Bug debugging | `superpowers:systematic-debugging` |

package/templates/.claude/skills/instinct-extractor/SKILL.md

@@ -171,6 +171,4 @@ R016 트리거 감지 시 오케스트레이터는 두 스킬을 순차 실행
 ## 한계
 
 - **transcript 형식 의존**: CC `session-*.jsonl` 스키마 변경 시 파싱 재구현 필요.
-  AgentMemory 마이그레이션(#1169, Phase 3 DECOUPLE) 완료 후 transcript 경로/형식 재검토 예정.
 - **클러스터링 정확도**: 키워드 기반 클러스터링으로 의미적 동의어 처리 제한.
-- **Phase γ 제약**: #1169 AgentMemory Phase 3 이전에는 transcript 형식 불안정 — `--dry-run` 권장.

package/templates/.claude/skills/intent-detection/patterns/agent-triggers.yaml

@@ -601,25 +601,6 @@ agents:
     base_confidence: 75
     routing_rule: "Invoke dev-refactor skill"
 
-  # Memory skills
-  skill-memory-save:
-    keywords:
-      korean: [메모리 저장, 기억해, 저장해]
-      english: ["save memory", "remember this", "store this"]
-    file_patterns: []
-    supported_actions: [save, store, remember]
-    base_confidence: 85
-    routing_rule: "Invoke memory-management skill"
-
-  skill-memory-recall:
-    keywords:
-      korean: [메모리 검색, 기억 찾기, 회상]
-      english: ["recall memory", "search memory", "find memory", "what did we"]
-    file_patterns: []
-    supported_actions: [recall, search, find]
-    base_confidence: 85
-    routing_rule: "Invoke memory-recall skill"
-
   # Harness management skills
   skill-analysis:
     keywords:

package/templates/.claude/skills/peer-messaging/SKILL.md

@@ -17,7 +17,6 @@ Enables cross-session coordination between multiple Claude Code instances throug
 |-------|-----------|-------|----------|
 | Intra-session agents | Agent Teams (R018) | TeamCreate, SendMessage | Single session multi-agent collaboration |
 | Cross-session instances | claude-peers-mcp | list_peers, send_message | Multi-terminal/project real-time coordination |
-| Cross-session memory | claude-mem | save_memory, search | Async memory persistence |
 
 > **Important**: R018's `SendMessage` and claude-peers-mcp's `send_message` are different tools with different scopes. Do not confuse them.
 
@@ -54,6 +53,5 @@ claude mcp add claude-peers-mcp -- npx claude-peers-mcp
 ## Integration
 
 - Works with R018 Agent Teams (different scope, complementary)
-- Works with claude-mem (async vs sync messaging)
 - Works with `omcustom:status` (peer discovery)
 - Broker runs on localhost:7899 (SQLite-backed)

package/templates/.claude/skills/semble-integration/SKILL.md

@@ -147,7 +147,6 @@ R013 ecomode가 자동 활성화되는 시점 (context 사용량 ≥ 60%)에서
 
 | 기존 방식 | Semble 대체 가능 여부 |
 |----------|---------------------|
-| `claude-mem:smart-explore` 의 자연어 탐색 | 일부 대체 가능 — 구조 탐색은 CRG 유지 |
 | grep + Read 조합의 패턴 검색 | 대체 권장 (98% 토큰 절감) |
 
 ## 트러블슈팅

package/templates/CLAUDE.md

@@ -81,7 +81,7 @@ oh-my-customcode로 구동됩니다.
 |----|------|------|
 | R003 | 상호작용 규칙 | 응답 원칙, 상태 형식 |
 | R004 | 오류 처리 | 오류 수준, 복구 전략 |
-| R011 | 메모리 통합 | claude-mem을 통한 세션 지속성 |
+| R011 | 메모리 통합 | 세션 메모리 지속성 |
 | R012 | HUD 상태줄 | 실시간 상태 표시 |
 | R013 | Ecomode | 배치 작업 토큰 효율성 |
 | R019 | Ontology-RAG 라우팅 | 라우팅 스킬의 ontology-RAG enrichment |
@@ -104,7 +104,6 @@ oh-my-customcode로 구동됩니다.
 | 검증 | `/omcustom:sauron-watch`, `/deep-verify`, `/adversarial-review` | R017 검증, 릴리즈 품질, 보안 리뷰 |
 | 릴리즈 | `/pipeline auto-dev`, `/omcustom-release-notes`, `/release-plan` | 자동 개발, 릴리즈 노트 |
 | 리서치 | `/research`, `/scout`, `/deep-plan`, `/omcustom:agora` | 병렬 분석, URL 평가, 연구 계획 |
-| 메모리 | `/memory-save`, `/memory-recall` | 세션 메모리 관리 |
 | 최적화 | `/token-efficiency-audit` | 토큰 효율 감사 (5계층 방어 스택) |
 | 시스템 | `/omcustom:lists`, `/omcustom:status`, `/omcustom:help` | 전체 목록, 상태, 도움말 |
 
@@ -117,11 +116,11 @@ project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (49 파일)
-|   +-- skills/                  # 스킬 (121 디렉토리)
+|   +-- skills/                  # 스킬 (118 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R023)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
-+-- guides/                      # 레퍼런스 문서 (58 토픽)
++-- guides/                      # 레퍼런스 문서 (57 토픽)
 ```
 
 ## 오케스트레이션
@@ -211,10 +210,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 # 코드 리뷰
 /dev-review src/main.go
 
-# 메모리 관리
-/memory-save
-/memory-recall authentication
-
 # 검증
 /omcustom:sauron-watch
 ```
@@ -245,8 +240,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 
 | 서버 | 용도 |
 |------|------|
-| claude-mem | 세션 메모리 영속성 (Chroma 기반) — Phase β (#1169) COEXIST 진행 중 |
-| **agentmemory** | claude-mem 대체 후보 (SQLite 기반, 4-tier consolidation) — Phase 1 COEXIST (#1169) |
 | code-review-graph | Token-efficient AST 기반 context retrieval (8.2× 토큰 절감) — wrapper: `crg-integration` 스킬 (#1171) |
 | semble | Semantic code search via embeddings (98% 토큰 절감, NDCG@10=0.854) — wrapper: `semble-integration` 스킬 (#1173) |
 
@@ -261,16 +254,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 /plugin install superpowers-developing-for-claude-code
 /plugin install elements-of-style
 
-# MCP 설정 (claude-mem)
-npm install -g claude-mem
-claude-mem setup
-
-# AgentMemory MCP 설치 (claude-mem 대체 후보, COEXIST)
-pip install agentmemory
-claude mcp add agentmemory -- agentmemory mcp
-# 또는 .mcp.json 수동 편집 (R001 auto-install 금지)
-# Phase 1 COEXIST 가이드: guides/agentmemory-migration/phase-1-coexist.md
-
 # CRG MCP 설치 (token efficiency)
 pipx install code-review-graph
 # .mcp.json 에 code-review-graph 서버 수동 추가 (R001 auto-install 금지)

package/templates/CLAUDE.md.en

@@ -78,7 +78,7 @@ NO EXCEPTIONS. NO EXCUSES.
 |----|------|-------------|
 | R003 | Interaction Rules | Response principles, status format |
 | R004 | Error Handling | Error levels, recovery strategy |
-| R011 | Memory Integration | Session persistence with claude-mem |
+| R011 | Memory Integration | Session memory persistence |
 | R012 | HUD Statusline | Real-time status display |
 | R013 | Ecomode | Token efficiency for batch ops |
 | R019 | Ontology-RAG Routing | Ontology-RAG enrichment for routing skills |
@@ -103,8 +103,6 @@ NO EXCEPTIONS. NO EXCUSES.
 | `/omcustom-takeover` | Extract canonical spec from existing agent/skill |
 | `/dev-review` | Review code for best practices |
 | `/dev-refactor` | Refactor code |
-| `/memory-save` | Save session context to claude-mem |
-| `/memory-recall` | Search and recall memories |
 | `/omcustom:monitoring-setup` | Enable/disable OTel console monitoring |
 | `/omcustom:npm-publish` | Publish package to npm registry |
 | `/omcustom:npm-version` | Manage semantic versions |
@@ -129,7 +127,7 @@ project/
 +-- CLAUDE.md                    # Entry point
 +-- .claude/
 |   +-- agents/                  # Subagent definitions (44 files)
-|   +-- skills/                  # Skills (74 directories)
+|   +-- skills/                  # Skills (118 directories)
 |   +-- rules/                   # Global rules (R000-R020)
 |   +-- hooks/                   # Hook scripts (security, validation, HUD)
 |   +-- contexts/                # Context files (ecomode)
@@ -208,10 +206,6 @@ Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
 # Code review
 /dev-review src/main.go
 
-# Memory management
-/memory-save
-/memory-recall authentication
-
 # Verification
 /omcustom:sauron-watch
 ```
@@ -230,12 +224,6 @@ Install via `/plugin install <name>`:
 | obsidian-skills | - | Obsidian markdown support |
 | context7 | claude-plugins-official | Library documentation lookup |
 
-### Recommended MCP Servers
-
-| Server | Purpose |
-|--------|---------|
-| claude-mem | Session memory persistence (Chroma-based) |
-
 ### Setup Commands
 
 ```bash
@@ -246,10 +234,6 @@ Install via `/plugin install <name>`:
 /plugin install superpowers
 /plugin install superpowers-developing-for-claude-code
 /plugin install elements-of-style
-
-# MCP setup (claude-mem)
-npm install -g claude-mem
-claude-mem setup
 ```
 
 <!-- omcustom:git-workflow -->

package/templates/CLAUDE.md.ko

@@ -78,7 +78,7 @@ oh-my-customcode로 구동됩니다.
 |----|------|------|
 | R003 | 상호작용 규칙 | 응답 원칙, 상태 형식 |
 | R004 | 오류 처리 | 오류 수준, 복구 전략 |
-| R011 | 메모리 통합 | claude-mem을 통한 세션 지속성 |
+| R011 | 메모리 통합 | 세션 메모리 지속성 |
 | R012 | HUD 상태줄 | 실시간 상태 표시 |
 | R013 | Ecomode | 배치 작업 토큰 효율성 |
 | R019 | Ontology-RAG 라우팅 | 라우팅 스킬의 ontology-RAG enrichment |
@@ -103,8 +103,6 @@ oh-my-customcode로 구동됩니다.
 | `/omcustom-takeover` | 기존 에이전트/스킬에서 canonical spec 추출 |
 | `/dev-review` | 코드 베스트 프랙티스 리뷰 |
 | `/dev-refactor` | 코드 리팩토링 |
-| `/memory-save` | 세션 컨텍스트를 claude-mem에 저장 |
-| `/memory-recall` | 메모리 검색 및 리콜 |
 | `/omcustom:monitoring-setup` | OTel 콘솔 모니터링 활성화/비활성화 |
 | `/omcustom:npm-publish` | npm 레지스트리에 패키지 배포 |
 | `/omcustom:npm-version` | 시맨틱 버전 관리 |
@@ -129,7 +127,7 @@ project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (44 파일)
-|   +-- skills/                  # 스킬 (74 디렉토리)
+|   +-- skills/                  # 스킬 (118 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R020)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
@@ -208,10 +206,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 # 코드 리뷰
 /dev-review src/main.go
 
-# 메모리 관리
-/memory-save
-/memory-recall authentication
-
 # 검증
 /omcustom:sauron-watch
 ```
@@ -230,12 +224,6 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 | obsidian-skills | - | 옵시디언 마크다운 지원 |
 | context7 | claude-plugins-official | 라이브러리 문서 조회 |
 
-### 권장 MCP 서버
-
-| 서버 | 용도 |
-|------|------|
-| claude-mem | 세션 메모리 영속성 (Chroma 기반) |
-
 ### 설치 명령어
 
 ```bash
@@ -246,10 +234,6 @@ 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
-
-# MCP 설정 (claude-mem)
-npm install -g claude-mem
-claude-mem setup
 ```
 
 <!-- omcustom:git-workflow -->