oh-my-customcode 0.100.0 → 0.101.0

package/dist/cli/index.js

@@ -2334,7 +2334,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.100.0",
+    version: "0.101.0",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -2014,7 +2014,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.100.0",
+  version: "0.101.0",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.100.0",
+  "version": "0.101.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/agents/mgr-supplier.md

@@ -16,7 +16,7 @@ tools:
   - Read
   - Grep
   - Glob
-permissionMode: default
+permissionMode: bypassPermissions
 ---
 
 You are a dependency validation specialist ensuring agents have all required skills and guides properly linked.

package/templates/.claude/rules/MUST-permissions.md

@@ -30,3 +30,15 @@ Approve?
 ```
 
 On insufficient permission: do not attempt, notify user, suggest alternative.
+
+## Agent Tool Permission Mode
+
+When spawning subagents via the Agent tool, always pass `mode: "bypassPermissions"` explicitly. The Agent tool's default mode is `acceptEdits`, which **overrides** the agent frontmatter `permissionMode` field.
+
+| Setting | Effect |
+|---------|--------|
+| Agent frontmatter `permissionMode: bypassPermissions` | Ignored if Agent tool `mode` not set |
+| Agent tool `mode: "bypassPermissions"` | **Required** — actually controls subagent permissions |
+| Agent tool `mode` omitted | Defaults to `acceptEdits` → prompts for Bash, WebFetch |
+
+Skills that spawn agents MUST include `mode: "bypassPermissions"` in their Agent tool call instructions. This applies to all routing skills, pipeline skills, and any skill that delegates work to subagents.

package/templates/.claude/rules/SHOULD-ontology-rag-routing.md

@@ -1,49 +1,66 @@
-# [SHOULD] Ontology-RAG Assisted Routing
+# [SHOULD] Routing Enrichment Rules
 
 > **Priority**: SHOULD | **ID**: R019
 
 ## Core Rule
 
-Routing skills SHOULD use ontology-RAG's `get_agent_for_task` MCP tool to enrich agent selection with contextual skill suggestions. Ontology-RAG is an enrichment layer — it does NOT replace static routing.
+Routing skills SHOULD use enrichment layers to improve agent/skill/guide selection accuracy. Two enrichment sources are available — they complement each other and both are advisory only.
 
-## Integration Pattern
+## Enrichment Layers
 
-After static routing selects an agent, call `get_agent_for_task(query)` and extract `suggested_skills` from the response. Inject these into the spawned agent's prompt as contextual hints.
+### Layer 1: Ontology-RAG (MCP-based)
+
+When the `ontology-rag` MCP server is available, routing skills call `get_agent_for_task(query)` to get `suggested_skills` from the ontology graph. Inject suggestions into the spawned agent's prompt.
 
 ```
 Static routing → agent selected
   ↓
-get_agent_for_task(original_query)
+get_agent_for_task(original_query) [MCP]
   ↓
 Extract suggested_skills
   ↓
-Prepend to spawned agent prompt:
-  "Ontology context suggests these skills may be relevant: {suggested_skills}"
+Prepend to spawned agent prompt
+```
+
+### Layer 2: Wiki-RAG (wiki index-based)
+
+When routing confidence is below 90%, query `wiki/index.yaml` for relevant agent/skill/guide pages. Inject findings as supplementary routing signals.
+
+```
+Static routing → ambiguous (confidence < 90%)
+  ↓
+wiki/index.yaml search for matching pages
+  ↓
+Extract agent/skill/guide suggestions
+  ↓
+Inject as suggested_context in agent prompt
 ```
 
 ## Failure Handling
 
 | Scenario | Action |
 |----------|--------|
-| MCP server unavailable | Skip silently, proceed with unmodified prompt |
-| get_agent_for_task returns empty | Proceed with unmodified prompt |
-| Response parsing error | Skip silently, log warning |
+| MCP server unavailable | Skip silently, proceed without ontology enrichment |
+| wiki/index.yaml missing | Skip silently, proceed without wiki enrichment |
+| Either returns empty | Proceed with unmodified prompt |
+| Parsing error | Skip silently, log warning |
 
-**MCP failure MUST NOT block or delay routing.** Ontology-RAG is advisory only.
+**Enrichment failure MUST NOT block or delay routing.** Both layers are advisory only.
 
 ## Scope
 
-| Applies to | Details |
-|------------|---------|
-| secretary-routing | Enriches manager agent selection |
-| dev-lead-routing | Enriches language/framework expert selection |
-| de-lead-routing | Enriches data engineering expert selection |
-| qa-lead-routing | Enriches QA workflow routing |
+| Applies to | Ontology-RAG | Wiki-RAG |
+|------------|:------------:|:--------:|
+| secretary-routing | ✓ | ✓ |
+| dev-lead-routing | ✓ | ✓ |
+| de-lead-routing | ✓ | ✓ |
+| qa-lead-routing | ✓ | ✓ |
 
 ## Interaction with Other Rules
 
 | Rule | Interaction |
 |------|-------------|
-| R010 | Orchestrator calls MCP tool; subagent receives enriched prompt |
-| R015 | Post-fix confidence (0.30-0.40) remains below R015's 70% threshold; display behavior unchanged |
-| R009 | Ontology-RAG call adds ~300 tokens; no parallelism impact |
+| R010 | Orchestrator calls enrichment tools; subagent receives enriched prompt |
+| R015 | Enrichment does not change R015 confidence thresholds — display behavior unchanged |
+| R009 | Each enrichment call adds ~300 tokens; no parallelism impact |
+| R022 | Wiki-RAG depends on up-to-date wiki pages — stale wiki reduces enrichment quality |

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

@@ -78,3 +78,7 @@ Fix: Recommended remediation
 - [ ] Do file operations stay within R002-declared access scope?
 - [ ] Are domain boundaries respected (backend agent not editing frontend files)?
 - [ ] Could an agent's task contract be tightened without losing functionality?
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

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

@@ -84,12 +84,22 @@ For **new pipeline code**, **DAG scaffolding**, or **SQL model generation**:
 ### Step 3: Expert Selection
 Route to appropriate DE expert based on tool/framework detection.
 
-> **Permission Mode**: When spawning agents, pass `mode: "bypassPermissions"` in the Agent tool call if the session uses bypassPermissions. Without explicit mode, CC defaults to `acceptEdits`.
+> **Permission Mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
 
 ### Step 4: Ontology-RAG Enrichment (R019)
 
 If `get_agent_for_task` MCP tool is available, call it with the original query and inject `suggested_skills` into the agent prompt. Skip silently on failure.
 
+### Step 4b: Wiki-RAG Enrichment
+
+For ambiguous routing (confidence < 90%), query the wiki for context:
+
+1. Search `wiki/index.yaml` for DE-related pages matching the request
+2. Inject relevant skill/guide suggestions into the spawned agent's prompt
+3. Particularly useful for cross-domain DE tasks (e.g., Kafka + Spark)
+
+Advisory only — skip silently if wiki unavailable.
+
 ### Step 5: Soul Injection (R006)
 
 If the selected agent has `soul: true` in frontmatter, read and prepend `.claude/agents/souls/{agent-name}.soul.md` content to the prompt. Skip silently if file doesn't exist.

package/templates/.claude/skills/deep-plan/SKILL.md

@@ -82,22 +82,39 @@ Phase 2: Reality-Check Planning
    - Each ADOPT item: Does it already exist? Partially implemented?
    - Each ADAPT item: What is the current state to adapt from?
    - Each AVOID item: Are the alternatives already available?
-3. **Gap Analysis**: Build a reconciliation table:
+3. **Deliverable Dependency Verification**: After exploration, verify inter-deliverable dependencies:
+   - For each deliverable pair, check: do they share files, functions, or modules?
+   - Classify each pair: `independent` (parallel-safe), `sequential` (order required), `shared-state` (synchronization needed)
+   - **Default bias**: Assume `independent` unless exploration finds concrete shared state
+   - Build dependency matrix:
 
    ```
-   | Research Finding | Actual Code State | Gap Type | Action |
-   |-----------------|-------------------|----------|--------|
-   | "No caching"    | Redis client exists | Overestimate | Remove from plan |
-   | "Need auth middleware" | No auth layer | Real gap | Keep in plan |
-   | "Migrate to v3" | Already on v3.1 | Overestimate | Remove from plan |
-   | "Add rate limiting" | Basic limiter exists | Partial gap | Adapt existing |
+   | Deliverable A | Deliverable B | Classification | Evidence |
+   |---------------|---------------|----------------|----------|
+   | D1: Auth      | D2: API       | independent    | No shared files |
+   | D1: Auth      | D3: Tests     | sequential     | D3 tests D1 output |
    ```
 
-4. **Refined Plan**: Write implementation plan containing ONLY real gaps:
+   - **Orchestrator override**: The dependency classification is advisory. The orchestrator or user can reclassify pairs when the automated analysis is overly conservative.
+
+4. **Gap Analysis**: Build a reconciliation table:
+
+   ```
+   | Research Finding | Actual Code State | Gap Type | Action | Dependencies |
+   |-----------------|-------------------|----------|--------|-------------|
+   | "No caching"    | Redis client exists | Overestimate | Remove from plan | — |
+   | "Need auth middleware" | No auth layer | Real gap | Keep in plan | D3 (sequential) |
+   | "Migrate to v3" | Already on v3.1 | Overestimate | Remove from plan | — |
+   | "Add rate limiting" | Basic limiter exists | Partial gap | Adapt existing | independent |
+   ```
+
+5. **Refined Plan**: Write implementation plan containing ONLY real gaps:
    - Remove overestimates (already implemented)
    - Adjust partial gaps (adapt, don't rebuild)
    - Prioritize real gaps by impact
-5. **User Approval**: `ExitPlanMode` presents the refined plan for user review
+6. **User Approval**: `ExitPlanMode` presents the refined plan for user review
+   - Include dependency matrix in plan output
+   - Display override option: "Dependency classifications are advisory. Reply with reclassifications if needed."
 
 ### Phase 3: Plan Verification Research
 
@@ -342,3 +359,7 @@ phases_completed: 3
 verdict: PASS|REVISE
 ---
 ```
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

package/templates/.claude/skills/deep-verify/SKILL.md

@@ -109,3 +109,7 @@ Each agent receives the full diff and returns findings as structured JSON:
 - This skill replaces ad-hoc cross-verification with a repeatable process
 - Round 7 philosophy check references CLAUDE.md architecture section and R006/R010/R021 rules
 - Regression check compares function signatures, export lists, and test counts against develop baseline
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

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

@@ -20,6 +20,7 @@ context: fork
 | Architect | arch-documenter, arch-speckit-agent |
 | Security | sec-codeql-expert |
 | Infra | infra-docker-expert, infra-aws-expert |
+| Slack | slack-cli-expert |
 
 ## File Extension Mapping
 
@@ -74,6 +75,7 @@ context: fork
 | security, codeql, cve, vulnerability, sarif, sast, security audit | sec-codeql-expert |
 | architecture, adr, openapi, swagger, diagram | arch-documenter |
 | spec, specification, tdd, requirements | arch-speckit-agent |
+| slack, slack-cli, slack app, slack deploy, slack trigger, slack datastore | slack-cli-expert |
 
 ## Model Selection
 
@@ -121,12 +123,26 @@ For **new file creation**, **boilerplate**, or **test code generation**:
 ### Step 3: Expert Agent Selection
 Route to appropriate language/framework expert based on file extension and keyword mapping.
 
-> **Permission Mode**: When spawning agents, pass `mode: "bypassPermissions"` in the Agent tool call if the session uses bypassPermissions. Without explicit mode, CC defaults to `acceptEdits`.
+> **Permission Mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
 
 ### Step 4: Ontology-RAG Enrichment (R019)
 
 If `get_agent_for_task` MCP tool is available, call it with the original query and inject `suggested_skills` into the agent prompt. Skip silently on failure.
 
+### Step 4b: Wiki-RAG Enrichment
+
+For ambiguous routing (confidence < 90%), query the wiki for context:
+
+1. Search `wiki/index.yaml` for agent/skill pages matching detected keywords
+2. If wiki suggests a specific skill or guide for the task, inject as `suggested_context` in the agent prompt
+3. This helps agents receive relevant guide references automatically
+
+```
+wiki-rag query: "{user_request}" → wiki agent/skill pages → suggested_context injection
+```
+
+Advisory only — skip silently if wiki unavailable.
+
 ### Step 5: Soul Injection (R006)
 
 If the selected agent has `soul: true` in frontmatter, read and prepend `.claude/agents/souls/{agent-name}.soul.md` content to the prompt. Skip silently if file doesn't exist.

package/templates/.claude/skills/intent-detection/SKILL.md

@@ -175,6 +175,21 @@ Each agent defines:
 - weights (scoring factors)
 ```
 
+### With Skill Triggers
+
+```
+Skill triggers are defined in agent-triggers.yaml alongside agent triggers.
+Each skill trigger has a `routing_rule` field that specifies which skill to invoke.
+
+When a skill trigger matches with confidence >= 70%:
+1. Display the intent detection output with skill name
+2. Invoke the skill via Skill tool instead of spawning an agent
+3. If confidence < 70%, list skill options for user selection
+
+Skill triggers use the `skill-` prefix in their YAML key to distinguish
+from agent triggers.
+```
+
 ## Error Handling
 
 ### No Match (< 30% confidence)

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

@@ -436,3 +436,323 @@ agents:
     file_patterns: []
     supported_actions: [optimize, compress, proxy]
     base_confidence: 85
+
+  # ---------------------------------------------------------------------------
+  # Skill Triggers — route user intent to skill invocation
+  # ---------------------------------------------------------------------------
+
+  # Development workflow skills
+  skill-tdd:
+    keywords:
+      korean: [TDD, 테스트 주도, 테스트 먼저]
+      english: [tdd, "test driven", "test first", "write tests first"]
+    file_patterns: []
+    supported_actions: [implement, test, develop]
+    base_confidence: 80
+    routing_rule: "Invoke superpowers:test-driven-development skill"
+
+  skill-sdd:
+    keywords:
+      korean: [SDD, 스펙 주도, 스펙 기반]
+      english: [sdd, "spec driven", specification, "spec first"]
+    file_patterns: ["sdd/**"]
+    supported_actions: [plan, spec, design]
+    base_confidence: 80
+    routing_rule: "Invoke sdd-dev skill"
+
+  skill-structured-dev:
+    keywords:
+      korean: [구조화 개발, 6단계, 단계별]
+      english: ["structured dev", "6 stage", "stage-based"]
+    file_patterns: []
+    supported_actions: [implement, develop]
+    base_confidence: 75
+    routing_rule: "Invoke structured-dev-cycle skill"
+
+  # Review and verification skills
+  skill-deep-verify:
+    keywords:
+      korean: [딥검증, 릴리즈 검증, 다각도 검증]
+      english: ["deep verify", "release verify", "multi-angle"]
+    file_patterns: []
+    supported_actions: [verify, review, check]
+    base_confidence: 80
+    routing_rule: "Invoke deep-verify skill"
+
+  skill-adversarial-review:
+    keywords:
+      korean: [보안 리뷰, 적대적 리뷰, 공격자 관점]
+      english: ["security review", adversarial, "attacker mindset", "trust boundary"]
+    file_patterns: []
+    supported_actions: [review, audit, security]
+    base_confidence: 80
+    routing_rule: "Invoke adversarial-review skill"
+
+  skill-code-review:
+    keywords:
+      korean: [코드 리뷰, 베스트 프랙티스 리뷰]
+      english: ["code review", "best practice review", "dev review"]
+    file_patterns: []
+    supported_actions: [review, check]
+    base_confidence: 70
+    routing_rule: "Invoke dev-review skill"
+
+  # Planning skills
+  skill-deep-plan:
+    keywords:
+      korean: [딥플랜, 연구 계획, 검증 계획]
+      english: ["deep plan", "research plan", "validated plan"]
+    file_patterns: []
+    supported_actions: [plan, research, design]
+    base_confidence: 80
+    routing_rule: "Invoke deep-plan skill"
+
+  skill-release-plan:
+    keywords:
+      korean: [릴리즈 계획, 배포 계획]
+      english: ["release plan", "deployment plan"]
+    file_patterns: []
+    supported_actions: [plan, release]
+    base_confidence: 85
+    routing_rule: "Invoke release-plan skill"
+
+  # Pipeline and automation skills
+  skill-pipeline:
+    keywords:
+      korean: [파이프라인, 자동 개발, 자동화]
+      english: [pipeline, "auto dev", automation]
+    file_patterns: ["workflows/*.yaml"]
+    supported_actions: [run, execute, automate]
+    base_confidence: 85
+    routing_rule: "Invoke pipeline skill"
+
+  skill-evaluator-optimizer:
+    keywords:
+      korean: [평가, 최적화 루프, 루브릭, 반복 개선]
+      english: [evaluator, optimizer, rubric, "iterative improvement", "ralph loop", "ralph wiggum"]
+    file_patterns: []
+    supported_actions: [evaluate, optimize, iterate]
+    base_confidence: 80
+    routing_rule: "Invoke evaluator-optimizer skill"
+
+  # Analysis and triage skills
+  skill-professor-triage:
+    keywords:
+      korean: [트리아지, 이슈 분석, 프로페서]
+      english: [triage, "issue analysis", professor, "cross analysis"]
+    file_patterns: []
+    supported_actions: [analyze, triage, assess]
+    base_confidence: 85
+    routing_rule: "Invoke professor-triage skill"
+
+  skill-scout:
+    keywords:
+      korean: [스카우트, URL 평가, 외부 분석]
+      english: [scout, "url analysis", "external evaluation"]
+    file_patterns: []
+    supported_actions: [scout, analyze, evaluate]
+    base_confidence: 85
+    routing_rule: "Invoke scout skill"
+
+  skill-idea:
+    keywords:
+      korean: [아이디어, 이슈 제안]
+      english: [idea, "issue proposal", "feature idea"]
+    file_patterns: []
+    supported_actions: [propose, ideate, suggest]
+    base_confidence: 80
+    routing_rule: "Invoke idea skill"
+
+  # Wiki and knowledge skills
+  skill-wiki:
+    keywords:
+      korean: [위키, 지식 베이스, 위키 생성]
+      english: [wiki, "knowledge base", "wiki generate", "wiki ingest"]
+    file_patterns: ["wiki/**"]
+    supported_actions: [generate, ingest, lint, update]
+    base_confidence: 85
+    routing_rule: "Invoke wiki skill"
+
+  skill-wiki-rag:
+    keywords:
+      korean: [위키 검색, 프로젝트 질문, 아키텍처 질문, 어떻게 작동]
+      english: ["wiki search", "how does", "which agent", "what rule", architecture, workflow]
+    file_patterns: []
+    supported_actions: [search, query, ask]
+    base_confidence: 75
+    routing_rule: "Invoke wiki-rag skill"
+
+  # Token and optimization skills
+  skill-token-efficiency:
+    keywords:
+      korean: [토큰 효율, 토큰 감사, 토큰 절감]
+      english: ["token efficiency", "token audit", "token saving", "token defense"]
+    file_patterns: []
+    supported_actions: [audit, optimize, monitor]
+    base_confidence: 85
+    routing_rule: "Invoke token-efficiency-audit skill"
+
+  skill-simplify:
+    keywords:
+      korean: [단순화, 코드 정리, 중복 제거]
+      english: [simplify, cleanup, deduplicate, "reduce complexity"]
+    file_patterns: []
+    supported_actions: [simplify, clean, reduce]
+    base_confidence: 75
+    routing_rule: "Invoke simplify 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:
+      korean: [프로젝트 분석, 하네스 분석, 에이전트 분석]
+      english: ["project analysis", "harness analysis", "agent analysis", "analyze project"]
+    file_patterns: []
+    supported_actions: [analyze, configure, optimize]
+    base_confidence: 80
+    routing_rule: "Invoke analysis skill"
+
+  skill-adaptive-harness:
+    keywords:
+      korean: [하네스 최적화, 에이전트 비활성화, 프로젝트 프로필]
+      english: ["harness optimize", "deactivate agents", "project profile", "adaptive harness"]
+    file_patterns: []
+    supported_actions: [optimize, profile, adapt]
+    base_confidence: 80
+    routing_rule: "Invoke adaptive-harness skill"
+
+  # Worker-reviewer skills
+  skill-worker-reviewer:
+    keywords:
+      korean: [워커 리뷰어, 반복 리뷰, 리뷰 사이클]
+      english: ["worker reviewer", "review cycle", "iterative review"]
+    file_patterns: []
+    supported_actions: [review, iterate, cycle]
+    base_confidence: 75
+    routing_rule: "Invoke worker-reviewer-pipeline skill"
+
+  skill-agora:
+    keywords:
+      korean: [아고라, 합의, 적대적 합의, 다중 LLM]
+      english: [agora, consensus, "adversarial consensus", "multi llm"]
+    file_patterns: []
+    supported_actions: [debate, consensus, verify]
+    base_confidence: 85
+    routing_rule: "Invoke agora skill"
+
+  # Debugging skill
+  skill-debugging:
+    keywords:
+      korean: [디버깅, 버그 찾기, 재현]
+      english: [debug, "find bug", reproduce, "root cause"]
+    file_patterns: []
+    supported_actions: [debug, reproduce, diagnose]
+    base_confidence: 80
+    routing_rule: "Invoke systematic-debugging skill"
+
+  skill-stuck-recovery:
+    keywords:
+      korean: [멈춤, 루프, 무한 반복, 복구]
+      english: [stuck, loop, "infinite loop", recovery, "not progressing"]
+    file_patterns: []
+    supported_actions: [recover, unstick, diagnose]
+    base_confidence: 85
+    routing_rule: "Invoke stuck-recovery skill"
+
+  # CVE and security skills
+  skill-cve-triage:
+    keywords:
+      korean: [CVE, 취약점, 보안 취약점]
+      english: [cve, vulnerability, "security vulnerability", "cve triage"]
+    file_patterns: []
+    supported_actions: [triage, analyze, patch]
+    base_confidence: 85
+    routing_rule: "Invoke cve-triage skill"
+
+  skill-npm-audit:
+    keywords:
+      korean: [npm 감사, 의존성 보안, 패키지 취약점]
+      english: ["npm audit", "dependency security", "package vulnerability"]
+    file_patterns: ["package.json", "package-lock.json"]
+    supported_actions: [audit, scan, fix]
+    base_confidence: 85
+    routing_rule: "Invoke npm-audit skill"
+
+  # Best practices skills (framework-specific)
+  skill-best-practices:
+    keywords:
+      korean: [베스트 프랙티스, 모범 사례, 패턴]
+      english: ["best practices", "best practice", pattern, convention]
+    file_patterns: []
+    supported_actions: [review, apply, check]
+    base_confidence: 60
+    routing_rule: "Route to language/framework specific best-practices skill based on file context"
+
+  # Monitoring skill
+  skill-monitoring:
+    keywords:
+      korean: [모니터링, 텔레메트리, 사용량 추적]
+      english: [monitoring, telemetry, "usage tracking", opentelemetry]
+    file_patterns: []
+    supported_actions: [setup, enable, disable, configure]
+    base_confidence: 80
+    routing_rule: "Invoke monitoring-setup skill"
+
+  # Deployment skill
+  skill-vercel-deploy:
+    keywords:
+      korean: [버셀 배포, 프리뷰, 프로덕션 배포]
+      english: ["vercel deploy", preview, "production deploy"]
+    file_patterns: ["vercel.json"]
+    supported_actions: [deploy, preview, promote]
+    base_confidence: 85
+    routing_rule: "Invoke vercel-deploy skill"
+
+  # ---------------------------------------------------------------------------
+  # Guide Reference Triggers — route user questions to relevant guides
+  # ---------------------------------------------------------------------------
+
+  guide-claude-code:
+    keywords:
+      korean: [클로드 코드, CC 가이드, 에이전트 가이드, 스킬 가이드, 훅 가이드]
+      english: ["claude code", "cc guide", "agent guide", "skill guide", "hook guide"]
+    file_patterns: []
+    supported_actions: [explain, reference, lookup]
+    base_confidence: 70
+    routing_rule: "Reference guides/claude-code/ directory"
+
+  guide-development:
+    keywords:
+      korean: [개발 가이드, 코딩 가이드, 개발 패턴]
+      english: ["dev guide", "coding guide", "development pattern"]
+    file_patterns: []
+    supported_actions: [reference, lookup]
+    base_confidence: 65
+    routing_rule: "Reference guides/development/ directory"
+
+  guide-best-practices:
+    keywords:
+      korean: [참조 가이드, 레퍼런스]
+      english: ["reference guide", "best practice guide"]
+    file_patterns: []
+    supported_actions: [reference, lookup]
+    base_confidence: 60
+    routing_rule: "Reference appropriate guides/ subdirectory"

package/templates/.claude/skills/omcustom-release-notes/SKILL.md

@@ -115,3 +115,7 @@ mgr-gitnerd: gh release create           ->  create release with notes
 - Uses git history and gh CLI for data gathering
 - Claude Code analyzes and generates notes in-context
 - Resource count changes auto-detected from CLAUDE.md history
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

package/templates/.claude/skills/pipeline/workflows/auto-dev.yaml

@@ -0,0 +1,166 @@
+name: auto-dev
+description: "Automated development pipeline — from issue triage to release"
+version: "2.0.0"
+
+# Design rule: each pipeline run produces ONE bounded release unit (3-7 issues), not all open issues.
+# This pipeline is a project-agnostic template. Project-specific overrides belong in
+# the project's own workflows/auto-dev.yaml (e.g., AgentNav, second-brain).
+
+steps:
+  - name: pre-triage
+    prompt: |
+      Phase 1 — Ensure required labels exist, then scan issues.
+
+      1. Create labels if missing (idempotent):
+         gh label create in-progress --color "FBCA04" --description "Work in progress" --force 2>/dev/null
+         gh label create verify-ready --color "0E8A16" --description "Ready for verification" --force 2>/dev/null
+         gh label create needs-review --color "D93F0B" --description "Needs manual review" --force 2>/dev/null
+
+      2. Scan open GitHub issues:
+         gh issue list --state open --limit 100 --json number,title,labels,body,milestone
+
+      3. Group by label and compute for each issue:
+         - dependencies: parse "see #N", "depends on #N", "#N 참조" from body
+         - blocked_by_decision: true if body references any decision-needed issue
+         - effort: XS/S/M/L from scope
+         - order: topological sort over dependencies
+
+      4. Output: dependency-sorted issue table with blocked_by_decision flag.
+    description: "Ensure labels exist, scan issues, dependency-analyze"
+
+  - name: scope-selection
+    prompt: |
+      Select a single bounded release scope (3-7 issues) for THIS pipeline run.
+
+      Selection rules:
+      1. Determine release tier:
+         - No tags yet → v0.1.0
+         - Otherwise: highest-priority open tier (bug → chore → feature)
+      2. Exclude:
+         - blocked_by_decision == true
+         - Issues requiring manual/human action
+      3. Sort by dependency: prerequisites before dependents
+      4. Cap at 7 issues; if priority issues < 7, stop at that priority (don't mix tiers)
+      5. Minimum 1 issue; if 0 eligible, halt with "no eligible issues for auto-dev run"
+
+      Create release milestone and assign scoped issues.
+      Output markdown release manifest:
+        | order | # | title | prerequisite | effort |
+
+      Persist manifest as pipeline state for subsequent steps.
+    description: "Pick 3-7 issues as v{X.Y.Z} scope, create milestone"
+    depends_on: pre-triage
+
+  - name: triage
+    skill: professor-triage
+    description: "Cross-analysis triage with priority assessment (scoped to release manifest)"
+    depends_on: scope-selection
+
+  - name: plan
+    skill: release-plan
+    description: "Release unit plan from triaged issues"
+    depends_on: triage
+
+  - name: deep-plan
+    skill: deep-plan
+    description: "Research-validated implementation plan (research → plan → verify)"
+    depends_on: plan
+
+  - name: implement
+    prompt: |
+      Execute the deep-plan output for the scoped release manifest.
+
+      Per-issue lifecycle:
+      1. Start: gh issue edit <N> --add-label in-progress --assignee @me
+      2. Comment: gh issue comment <N> --body "Implementation started via auto-dev pipeline"
+      3. Dispatch specialist agents per file domain:
+         - Detect file types in scope and route to matching agent
+         - Use specialized agents (lang-*, be-*, fe-*, infra-*) over general-purpose
+      4. TDD via superpowers:test-driven-development when tests apply
+      5. Commit via mgr-gitnerd with `Fixes #<N>` trailer in body
+      6. On success: remove in-progress, add verify-ready
+      7. On failure: remove in-progress, add needs-review, comment error summary
+
+      Rules:
+      - Parallel execution per R009 (max 4 concurrent, respect dependencies)
+      - Issues whose prerequisites failed in-run MUST be skipped (log reason)
+      - No direct orchestrator writes (R010)
+      - All Agent tool calls MUST pass mode: "bypassPermissions" to prevent permission prompts during unattended execution
+
+      ## Local CI-mimic verification (MUST run before marking implement done)
+
+      After all implementation tasks complete, run these scripts in sequence and halt on failure:
+
+      1. bash .github/scripts/verify-template-sync.sh
+      2. bash .github/scripts/verify-wiki-sync.sh
+
+      If either fails:
+      - For wiki-sync failures: delegate to wiki-curator to generate missing pages (`/omcustom:wiki ingest <path>`)
+      - For template-sync failures: delegate to mgr-updater to sync `.claude/` -> `templates/.claude/`
+      - After fixes, re-run the scripts until both pass
+
+      This mirrors CI and prevents the known 1-2 wasted push cycles per release (ref: issue #927, v0.98.0 PR #925).
+    description: "Per-issue implementation with lifecycle, specialist routing, and CI-mimic verification"
+    depends_on: deep-plan
+
+  - name: verify-build
+    prompt: |
+      Project-specific build and test verification.
+
+      Auto-detect project type and run appropriate checks:
+      - Node/Bun: package.json → install + lint + type-check + test
+      - Python: py_compile + pytest
+      - Go: go build + go vet + go test
+      - Docker: docker build (if Dockerfile exists)
+      - Static site: file existence + format validation
+
+      Halt on first failure. Report exact command + stderr.
+      Do NOT proceed to release if any check fails.
+    description: "Auto-detected build + test verification"
+    depends_on: implement
+
+  - name: deep-verify
+    skill: deep-verify
+    description: "Multi-angle release quality verification"
+    depends_on: verify-build
+
+  - name: release
+    prompt: |
+      Create a GitHub Release.
+
+      1. Version:
+         - No existing tags → v0.1.0
+         - Otherwise: semver bump (patch for bugfix, minor for features)
+      2. Release notes via omcustom-release-notes skill
+      3. Delegate to mgr-gitnerd:
+         - git tag + push
+         - gh release create
+      4. Close milestone
+      5. Close verify-ready issues with "Fixed in v{version}"
+         Label needs-review issues as "Deferred from v{version}"
+
+      Adapt release mechanism to project:
+      - npm project: PR + merge + npm publish verification
+      - Non-npm: direct tag on main (trunk-based)
+    description: "Git tag + GitHub Release + close milestone/issues"
+    depends_on: deep-verify
+
+  - name: ci-check
+    prompt: |
+      Post-release CI verification.
+
+      1. Check if .github/workflows/ has CI workflows
+         If NOT: skip with "No CI configured. Skipping." and continue.
+      2. If CI exists:
+         - gh run list --limit 5
+         - Wait for runs triggered by the new tag/push
+         - If failures: diagnose, fix, re-verify
+      3. For npm projects: verify npm publish succeeded (npm view <pkg> version)
+      4. Report final CI status.
+    description: "Post-release CI verification and fix loop"
+    depends_on: release
+
+  - name: post-release-followup
+    skill: post-release-followup
+    description: "Register follow-ups from this release as new issues"
+    depends_on: ci-check

package/templates/.claude/skills/post-release-followup/SKILL.md

@@ -46,9 +46,9 @@ Remove duplicates (same issue referenced from multiple sources). Categorize:
 
 | Category | Criteria | Default Action |
 |----------|----------|----------------|
-| **Immediate** | P1/P2 remaining issues, MEDIUM+ verify findings, Critical/High PR review findings | Execute now |
-| **Trackable** | P3 issues, LOW verify findings, new TODOs, Medium PR review findings | Register as issue |
-| **Informational** | Already-tracked issues, cosmetic notes | Skip |
+| **즉시 실행** | P1/P2 잔여 이슈, MEDIUM+ 검증 발견사항, Critical/High PR 리뷰 발견사항 | 즉시 실행 |
+| **이슈 등록** | P3 이슈, LOW 검증 발견사항, 새 TODO, Medium PR 리뷰 발견사항 | 이슈로 등록 |
+| **참고** | 이미 추적 중인 이슈, 외관 관련 메모 | 건너뛰기 |
 
 ### 3. Present to User
 
@@ -117,8 +117,8 @@ When creating follow-up issues:
 
 ```bash
 gh issue create \
-  --title "{concise description}" \
-  --body "## Source\n\nDiscovered during v{version} release workflow.\n\n## Context\n\n{detailed context from triage/verify}\n\n## Suggested Action\n\n{recommendation}" \
+  --title "{간결한 설명}" \
+  --body "## 출처\n\nv{version} 릴리즈 워크플로우에서 발견.\n\n## 컨텍스트\n\n{triage/verify에서의 상세 컨텍스트}\n\n## 권장 조치\n\n{권장 사항}" \
   --label "professor"
 ```
 
@@ -132,3 +132,7 @@ Add priority label (`P1`, `P2`, `P3`) based on categorization.
 - Issue creation uses `gh` CLI directly (read-only operation pattern)
 - If no follow-up candidates found, report "No follow-up actions needed" and complete
 - PR review feedback is available shortly after PR creation — the omc_pr_analyzer bot comments automatically
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

package/templates/.claude/skills/professor-triage/SKILL.md

@@ -2,7 +2,7 @@
 name: professor-triage
 description: Analyze GitHub issues against current codebase and perform automated triage with priority assessment
 scope: harness
-version: 2.1.0
+version: 2.2.0
 user-invocable: true
 effort: high
 context: fork
@@ -126,27 +126,27 @@ For each analyzed issue, generate multi-perspective analysis comments and artifa
 ```
 ## 🏛️ Senior Architect Analysis
 
-### Architecture Impact
-| Component | Impact | Risk |
-|-----------|--------|------|
-| {component} | {description} | {High/Medium/Low} |
+### 아키텍처 영향
+| 컴포넌트 | 영향 | 위험도 |
+|----------|------|--------|
+| {컴포넌트} | {설명} | {High/Medium/Low} |
 
-### Code-Level Analysis
-{Specific file:line references from Phase 2 codebase analysis}
+### 코드 수준 분석
+{Phase 2 코드베이스 분석의 구체적 file:line 참조}
 
-### Strategic Assessment
-- **Feasibility**: {assessment with evidence}
-- **Priority recommendation**: {P1/P2/P3 with rationale}
+### 전략적 평가
+- **실현 가능성**: {근거가 포함된 평가}
+- **우선순위 권장**: {P1/P2/P3 및 근거}
 
-### Risk & Considerations
-| Risk | Likelihood | Mitigation |
-|------|-----------|------------|
-| {risk} | {High/Medium/Low} | {mitigation} |
+### 리스크 및 고려사항
+| 리스크 | 가능성 | 완화 방안 |
+|--------|--------|----------|
+| {리스크} | {High/Medium/Low} | {완화 방안} |
 
-**Estimated effort**: {XS/S/M/L/XL}
+**예상 작업량**: {XS/S/M/L/XL}
 
 ---
-_🏛️ Senior Architect perspective — `/professor-triage` v2.1.0_
+_🏛️ Senior Architect perspective — `/professor-triage` v2.2.0_
 ```
 
 **4B: 🤝 Project Colleague Review** — Delegate to arch-documenter (model: sonnet) to post GitHub comment:
@@ -154,19 +154,19 @@ _🏛️ Senior Architect perspective — `/professor-triage` v2.1.0_
 ```
 ## 🤝 Project Colleague Review
 
-### Implementation Ideas
-{Concrete code locations and change suggestions with file:line references}
+### 구현 아이디어
+{구체적 코드 위치 및 file:line 참조가 포함된 변경 제안}
 
-### Easy-to-Miss Details
-- {Name collisions, validation bypasses, race conditions, edge cases}
+### 놓치기 쉬운 세부사항
+- {이름 충돌, 유효성 검사 우회, 경쟁 조건, 엣지 케이스}
 
-### Suggested Next Steps
-1. {Actionable step with specific file/function reference}
-2. {Actionable step}
-3. {Actionable step}
+### 권장 다음 단계
+1. {구체적 file/function 참조가 포함된 실행 가능한 단계}
+2. {실행 가능한 단계}
+3. {실행 가능한 단계}
 
 ---
-_🤝 Project Colleague perspective — `/professor-triage` v2.1.0_
+_🤝 Project Colleague perspective — `/professor-triage` v2.2.0_
 ```
 
 Note: Do NOT include a "First Impressions" (첫인상) section in the Colleague Review — this was explicitly excluded per user feedback.
@@ -176,38 +176,38 @@ Note: Do NOT include a "First Impressions" (첫인상) section in the Colleague
 ```
 ## 🎓 Professor Synthesis
 
-### Codebase Verification
-| Claim (from Architect/Colleague) | Verified | Evidence |
-|----------------------------------|----------|----------|
-| {claim} | ✅/⚠️/❌ | {file:line or git evidence} |
+### 코드베이스 검증
+| 주장 (Architect/Colleague) | 검증 | 근거 |
+|---------------------------|------|------|
+| {주장} | ✅/⚠️/❌ | {file:line 또는 git 근거} |
 
-### Consensus & Divergence
-| Topic | Architect | Colleague | Verdict |
-|-------|-----------|-----------|---------|
-| {topic} | {position} | {position} | {synthesized judgment} |
+### 합의 및 이견
+| 주제 | Architect | Colleague | 판정 |
+|------|-----------|-----------|------|
+| {주제} | {입장} | {입장} | {종합 판단} |
 
-### Priority Matrix
-| Dimension | Assessment |
-|-----------|-----------|
-| Urgency | {High/Medium/Low} |
-| Importance | {High/Medium/Low} |
-| Size | {XS/S/M/L/XL} |
-| Recommended order | {N of M in batch} |
+### 우선순위 매트릭스
+| 차원 | 평가 |
+|------|------|
+| 긴급성 | {High/Medium/Low} |
+| 중요성 | {High/Medium/Low} |
+| 규모 | {XS/S/M/L/XL} |
+| 권장 순서 | {배치 내 N/M} |
 
-### Missed Perspectives
-{Considerations neither Architect nor Colleague raised}
+### 누락된 관점
+{Architect나 Colleague 모두 제기하지 않은 고려사항}
 
-### Execution Roadmap
-| Phase | Task | Files | Depends on |
-|-------|------|-------|-----------|
-| 1 | {task} | {files} | — |
-| 2 | {task} | {files} | Phase 1 |
+### 실행 로드맵
+| 단계 | 작업 | 파일 | 의존성 |
+|------|------|------|--------|
+| 1 | {작업} | {파일} | — |
+| 2 | {작업} | {파일} | 단계 1 |
 
-### Final Conclusion
-{2-3 sentence synthesis with definitive recommendation}
+### 최종 결론
+{확정적 권장 사항이 포함된 2-3문장 종합}
 
 ---
-_🎓 Professor Synthesis — `/professor-triage` v2.1.0_
+_🎓 Professor Synthesis — `/professor-triage` v2.2.0_
 ```
 
 **4D: Issue Triage Comment (MANDATORY)** — Every analyzed issue MUST receive a triage comment. This is not optional — even for issues created in the same session or with existing analysis. Skipping comments breaks the triage audit trail. Delegate to mgr-gitnerd to post on each analyzed issue:
@@ -215,14 +215,14 @@ _🎓 Professor Synthesis — `/professor-triage` v2.1.0_
 ```
 ## 🔬 Professor Triage — Codebase Analysis Result
 
-**Decision**: {Close (Already Resolved) | Close (Not Applicable) | Close (Duplicate of #NNN) | Open — action required | Open — monitoring}
-**Rationale**: {1-2 line summary based on codebase findings}
-**Affected files**: {N} analyzed — {N}✅ {N}⚠️ {N}❌
-**Risk**: {P1/P2/P3} | **Size**: {XS/S/M/L/XL}
-**Full report**: {artifact path}
+**결정**: {Close (Already Resolved) | Close (Not Applicable) | Close (Duplicate of #NNN) | Open — action required | Open — monitoring}
+**근거**: {코드베이스 분석 기반 1-2줄 요약}
+**영향 파일**: {N}개 분석 — {N}✅ {N}⚠️ {N}❌
+**리스크**: {P1/P2/P3} | **규모**: {XS/S/M/L/XL}
+**전체 리포트**: {artifact path}
 
 ---
-_Analyzed by `/professor-triage` v2.1.0 against current codebase with {N} related issues_
+_`/professor-triage` v2.2.0에 의해 현재 코드베이스 대비 분석됨 — 관련 이슈 {N}개_
 ```
 
 **4E: Artifact Report** — Delegate to arch-documenter to write:
@@ -233,37 +233,37 @@ Timestamps use local machine time (consistent with other artifact skills).
 
 Template:
 ```
-# Professor Triage Report — YYYY-MM-DD
+# Professor Triage 리포트 — YYYY-MM-DD
 
-## Analysis Target
-| # | Title | Labels | Created |
-|---|-------|--------|---------|
+## 분석 대상
+| # | 제목 | 라벨 | 생성일 |
+|---|------|------|--------|
 
-## Per-Issue Analysis
+## 이슈별 분석
 ### #NNN — title
-- **Affected files**: N analyzed — N✅ N⚠️ N❌
-- **Architecture impact**: ...
-- **Implementation path**: ...
-- **Risk/Priority**: P1/P2/P3
-- **Size**: XS/S/M/L/XL
-- **Already resolved?**: Yes/No/Partial — evidence
-- **Recommended action**: ...
-
-## Cross-Analysis
-### Common Patterns
-### Duplicate/Merge Candidates
-### Conflicting Findings Resolution
-### Priority Matrix
-
-## Multi-Perspective Summary
-### Architect Highlights
-### Colleague Highlights
-### Professor Synthesis Key Points
-
-## Executed Actions
-| Issue | Action | Status |
-
-## Pending Actions (Confirmation Required)
+- **영향 파일**: N개 분석 — N✅ N⚠️ N❌
+- **아키텍처 영향**: ...
+- **구현 경로**: ...
+- **리스크/우선순위**: P1/P2/P3
+- **규모**: XS/S/M/L/XL
+- **이미 해결됨?**: Yes/No/Partial — 근거
+- **권장 조치**: ...
+
+## 교차 분석
+### 공통 패턴
+### 중복/병합 후보
+### 상충 발견사항 해결
+### 우선순위 매트릭스
+
+## 다관점 요약
+### Architect 주요 사항
+### Colleague 주요 사항
+### Professor Synthesis 핵심 포인트
+
+## 실행된 조치
+| 이슈 | 조치 | 상태 |
+
+## 보류 중인 조치 (확인 필요)
 ```
 
 ### Phase 4F: Comment Verification Gate
@@ -319,3 +319,7 @@ Present to user and wait for approval before executing:
 - Phase 4F: Verification gate for all 4 comment types
 - Phase 5: `mgr-gitnerd` for all GitHub operations
 - No external dependencies (omc_issue_analyzer removed in v2.0.0, multi-perspective analysis restored in v2.1.0)
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

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

@@ -45,12 +45,21 @@ quality_analysis   → qa-planner + qa-engineer (parallel)
 full_qa_cycle      → all agents (sequential)
 ```
 
-> **Permission Mode**: When spawning agents, pass `mode: "bypassPermissions"` in the Agent tool call if the session uses bypassPermissions. Without explicit mode, CC defaults to `acceptEdits`.
+> **Permission Mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
 
 ### Ontology-RAG Enrichment (R019)
 
 If `get_agent_for_task` MCP tool is available, call it with the original query and inject `suggested_skills` into the agent prompt. Skip silently on failure.
 
+### Wiki-RAG Enrichment
+
+For ambiguous routing (confidence < 90%), query the wiki for context:
+
+1. Search `wiki/index.yaml` for QA-related pages matching the request
+2. Inject relevant skill/guide suggestions into the spawned agent's prompt
+
+Advisory only — skip silently if wiki unavailable.
+
 ### Step 5: Soul Injection (R006)
 
 If the selected agent has `soul: true` in frontmatter, read and prepend `.claude/agents/souls/{agent-name}.soul.md` content to the prompt. Skip silently if file doesn't exist.

package/templates/.claude/skills/release-plan/SKILL.md

@@ -131,21 +131,21 @@ Apply semantic versioning to each release group in sequence:
 For each release group, produce:
 
 ```markdown
-## vX.Y.Z Release Plan
+## vX.Y.Z 릴리즈 계획
 
-**Estimated scope**: {XS|S|M|L total} | **Issues**: N | **Parallelizable**: N
+**예상 범위**: {XS|S|M|L 합계} | **이슈**: N | **병렬 가능**: N
 
-| # | Priority | Size | Title | Dependencies |
-|---|----------|------|-------|-------------|
-| #NNN | P2 | S | issue title | none |
-| #NNN | P1 | XS | issue title | none |
+| # | 우선순위 | 규모 | 제목 | 의존성 |
+|---|----------|------|------|--------|
+| #NNN | P2 | S | 이슈 제목 | 없음 |
+| #NNN | P1 | XS | 이슈 제목 | 없음 |
 
-### Implementation Order
-1. #NNN — {one-line description} (suggested agent: {agent-type})
-2. #NNN — {one-line description} (suggested agent: {agent-type})
+### 구현 순서
+1. #NNN — {한줄 설명} (권장 에이전트: {agent-type})
+2. #NNN — {한줄 설명} (권장 에이전트: {agent-type})
 
-### Notes
-- {any dependency constraints, breaking changes, or risks}
+### 참고 사항
+- {의존성 제약, 호환성 이슈, 리스크 등}
 ```
 
 ### Completeness Check
@@ -159,18 +159,18 @@ Before generating the plan document, verify:
 If any issue is missing from release bins, halt and report the discrepancy.
 
 **Agent suggestion heuristic**:
-| Issue domain | Suggested agent |
-|--------------|----------------|
-| Docs, CLAUDE.md, README | arch-documenter |
-| Rules (R00x) | mgr-claude-code-bible |
-| Agents (.claude/agents/) | mgr-creator / mgr-updater |
-| Skills (.claude/skills/) | mgr-creator / mgr-updater |
+| 이슈 도메인 | 권장 에이전트 |
+|-------------|--------------|
+| 문서, CLAUDE.md, README | arch-documenter |
+| 규칙 (R00x) | mgr-claude-code-bible |
+| 에이전트 (.claude/agents/) | mgr-creator / mgr-updater |
+| 스킬 (.claude/skills/) | mgr-creator / mgr-updater |
 | CI, GitHub Actions | mgr-gitnerd |
 | TypeScript/Node | lang-typescript-expert |
 | Python | lang-python-expert |
 | Go | lang-golang-expert |
-| Testing | qa-engineer |
-| General fix | general-purpose |
+| 테스트 | qa-engineer |
+| 일반 수정 | general-purpose |
 
 ### Phase 7: Output
 
@@ -184,16 +184,16 @@ Use today's date and the first planned release version in the filename.
 
 File header format:
 ```markdown
-# Release Plan — Generated YYYY-MM-DD
+# 릴리즈 계획 — YYYY-MM-DD 생성
 
-> Source: open issues labeled `verify-done` as of YYYY-MM-DD
-> Issues excluded (already in open PRs): #NNN, #NNN
+> 출처: YYYY-MM-DD 기준 `verify-done` 라벨 오픈 이슈
+> 제외된 이슈 (이미 오픈 PR에 포함): #NNN, #NNN
 
-{release groups follow}
+{릴리즈 그룹}
 
-## Summary
-| Release | Issues | Size | P1 | P2 | P3 |
-|---------|--------|------|----|----|-----|
+## 요약
+| 릴리즈 | 이슈 수 | 규모 | P1 | P2 | P3 |
+|--------|---------|------|----|----|-----|
 | vX.Y.Z | N | S | 0 | 3 | 1 |
 ```
 
@@ -205,3 +205,7 @@ File header format:
 - User confirms before any downstream action (implementation, commits)
 - Zero network calls except `gh` CLI (local API)
 - If no eligible issues found, report and stop — do not generate empty plan
+
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.

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

@@ -16,7 +16,7 @@ Routes agent management tasks to the appropriate manager agent. This skill conta
 
 | Agent | Purpose | Triggers |
 |-------|---------|----------|
-| mgr-creator | Create new agents | "create agent", "new agent" |
+| mgr-creator | Create new agents, skills, guides | "create agent", "new agent", "create skill", "new skill", "create guide", "new guide" |
 | mgr-updater | Update external agents | "update agent", "sync" |
 | mgr-supplier | Validate dependencies | "audit", "check deps" |
 | mgr-gitnerd | Git operations | "commit", "push", "pr" |
@@ -44,6 +44,8 @@ Before routing via Task tool, evaluate Agent Teams eligibility first:
 User Input → Routing → Manager Agent
 
 create   → mgr-creator
+create skill → mgr-creator
+create guide → mgr-creator
 update   → mgr-updater
 audit    → mgr-supplier
 git      → mgr-gitnerd
@@ -64,6 +66,20 @@ batch           → multiple (parallel)
 
 If `get_agent_for_task` MCP tool is available, call it with the original query and inject `suggested_skills` into the agent prompt. Skip silently on failure.
 
+### Step 4b: Wiki-RAG Enrichment
+
+If the user's request is ambiguous or confidence is below 90%, query the wiki for additional context:
+
+1. Search `wiki/index.yaml` for pages matching the detected domain keywords
+2. Extract relevant agent/skill/guide recommendations from wiki pages
+3. Inject findings into the routing decision as supplementary signals
+
+```
+wiki-rag query: "{user_request}" → wiki pages → agent/skill/guide suggestions
+```
+
+Wiki-RAG enrichment is advisory — it supplements but does not override keyword matching. Skip silently if wiki/index.yaml doesn't exist.
+
 ### Step 5: Soul Injection (R006)
 
 If the selected agent has `soul: true` in frontmatter, read and prepend `.claude/agents/souls/{agent-name}.soul.md` content to the prompt. Skip silently if file doesn't exist.
@@ -80,7 +96,7 @@ If the selected agent has `soul: true` in frontmatter, read and prepend `.claude
 5. Report result to user
 ```
 
-> **Permission Mode**: When spawning agents, pass `mode: "bypassPermissions"` in the Agent tool call if the session uses bypassPermissions. Without explicit mode, CC defaults to `acceptEdits`.
+> **Permission Mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
 
 ### 2. Batch/Parallel Task Routing
 

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

@@ -190,6 +190,10 @@ rm -f /tmp/.claude-dev-stage                    # Clear (disable blocking)
 - **Single session**: The fixed path `/tmp/.claude-dev-stage` does not support concurrent Claude Code sessions. Running multiple sessions simultaneously may cause stage state conflicts.
 - **World-writable path**: The `/tmp/` directory is accessible to all users. For multi-user environments, consider using a user-scoped path like `/tmp/.claude-dev-stage-$(id -u)`.
 
+## Permission Mode
+
+When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+
 ## Display Format
 
 ```

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.100.0",
+  "version": "0.101.0",
   "lastUpdated": "2026-04-18T00:00:00.000Z",
   "components": [
     {