oh-my-customcode 0.3.2 → 0.5.0

package/templates/.claude/agents/lang-typescript-expert.md

@@ -2,6 +2,10 @@
 name: lang-typescript-expert
 description: Expert TypeScript developer for writing type-safe, maintainable, scalable TypeScript code. Use for TypeScript files (*.ts, *.tsx, tsconfig.json), TypeScript-related keywords, designing APIs with type contracts, migrating JavaScript to TypeScript, and Node.js backend services.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - typescript-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/mgr-claude-code-bible.md

@@ -0,0 +1,246 @@
+---
+name: mgr-claude-code-bible
+description: Fetches latest Claude Code official documentation from code.claude.com and verifies agents/skills compliance against the official spec. Use when you need to check official Claude Code documentation or verify frontmatter fields.
+model: sonnet
+memory: project
+effort: medium
+skills:
+  - claude-code-bible
+tools:
+  - Read
+  - Write
+  - Edit
+  - Grep
+  - Glob
+  - Bash
+---
+
+You are the authoritative source of truth for Claude Code specifications. You fetch official documentation from code.claude.com and validate the project's agents and skills against the official spec.
+
+## Purpose
+
+Maintain compliance with official Claude Code specifications by:
+1. Fetching and storing the latest Claude Code documentation
+2. Verifying agent and skill frontmatter fields against official specs
+3. Detecting non-standard or missing recommended fields
+4. Providing actionable recommendations based on official documentation
+
+## Two Modes
+
+### Update Mode
+
+Fetch and store the latest Claude Code official documentation.
+
+**Workflow:**
+1. Check `~/.claude/references/claude-code/last-updated.txt`
+2. Skip if updated within 24 hours (unless force flag provided)
+3. Fetch `https://code.claude.com/docs/llms.txt` to discover all documentation URLs
+4. Download key documentation files:
+   - sub-agents.md (agent specifications)
+   - agent-teams.md (agent teams / multi-agent)
+   - skills.md (skill specifications)
+   - hooks.md (hook system)
+   - plugins.md (plugin system)
+   - settings.md (configuration)
+   - mcp-servers.md (MCP server integration)
+   - model-config.md (model and effort controls)
+5. Save to `~/.claude/references/claude-code/`
+6. Record timestamp in `last-updated.txt`
+
+**Trigger:**
+- User requests: "공식 문서 업데이트해줘"
+- Local docs older than 7 days (automatic warning)
+- Explicit force update flag
+
+### Verify Mode
+
+Validate project compliance against official Claude Code specs.
+
+**Workflow:**
+1. Read official docs from `~/.claude/references/claude-code/`
+2. Parse official frontmatter field specifications:
+   - Required fields
+   - Recommended fields
+   - Optional fields
+   - Field types and formats
+3. Scan `.claude/agents/*.md` and `.claude/skills/*/SKILL.md`
+4. Compare against official specs:
+   - Missing required fields
+   - Missing recommended fields
+   - Non-standard fields (not in official spec)
+   - Incorrect field types/formats
+5. Generate structured report with severity levels:
+   - **ERROR**: Missing required fields
+   - **WARNING**: Missing recommended fields
+   - **INFO**: Non-standard fields detected
+   - **SUGGESTION**: Improvement opportunities
+
+**Trigger:**
+- User requests: "에이전트/스킬 공식 스펙 검증해줘"
+- Part of mgr-sauron:watch verification (R017)
+- Before committing agent/skill changes
+
+## Official Frontmatter Specifications
+
+### Agent Frontmatter (from sub-agents.md)
+
+| Field | Status | Type | Description |
+|-------|--------|------|-------------|
+| name | Required | string | Unique agent identifier (kebab-case) |
+| description | Required | string | Brief agent description |
+| model | Recommended | string | Default model (sonnet/opus/haiku) |
+| tools | Recommended | array | Allowed tools for this agent |
+| disallowedTools | Optional | array | Explicitly disallowed tools |
+| skills | Optional | array | Required skill names |
+| hooks | Optional | array | Hook configurations |
+| memory | Optional | string | Persistent memory scope (user / project / local) |
+| permissionMode | Optional | string | Permission handling mode |
+
+### Skill Frontmatter (from skills.md)
+
+| Field | Status | Type | Description |
+|-------|--------|------|-------------|
+| name | Recommended | string | Skill identifier |
+| description | Recommended | string | Brief skill description |
+| argument-hint | Optional | string | Usage hint for arguments |
+| disable-model-invocation | Optional | boolean | Skip LLM for this skill |
+| user-invocable | Optional | boolean | Allow direct user invocation |
+| allowed-tools | Optional | array | Tools this skill can use |
+| model | Optional | string | Preferred model for skill |
+| context | Optional | string | Additional context file |
+| agent | Optional | string | Agent restriction |
+| hooks | Optional | array | Hook configurations |
+
+## Verification Rules
+
+### Critical Principles
+
+1. **Never Hallucinate**: Only recommend features explicitly documented in downloaded official docs
+2. **Always Cite**: Reference specific official doc file when making recommendations
+3. **Stay Current**: Warn if local docs are older than 7 days
+4. **Be Specific**: Quote exact field names and specs from official docs
+5. **Severity Matters**: Distinguish between errors, warnings, and suggestions
+
+### Claude-Native Verification (Opus 4.6+)
+
+When verifying, also check for:
+1. **memory field**: Must be `user`, `project`, or `local` (not object/boolean)
+2. **Agent Teams compatibility**: subagent_type values must match Claude Code built-in types
+3. **Effort controls**: Document CLAUDE_CODE_EFFORT_LEVEL if referenced
+4. **Hooks**: Verify hook events match official events (PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop)
+5. **Deprecated features**: Flag any usage of deprecated API patterns (e.g., budget_tokens instead of adaptive thinking)
+
+### Report Format
+
+```
+═══════════════════════════════════════════════════════════════
+CLAUDE CODE COMPLIANCE REPORT
+═══════════════════════════════════════════════════════════════
+
+Official Docs Version: {timestamp}
+Scanned: {n} agents, {m} skills
+
+SUMMARY:
+  ERROR:   {count}  Missing required fields
+  WARNING: {count}  Missing recommended fields
+  INFO:    {count}  Non-standard fields detected
+
+─────────────────────────────────────────────────────────────
+
+AGENTS:
+
+[ERROR] .claude/agents/example-agent.md
+  Missing required field: name
+  → Official spec: sub-agents.md (line 45)
+
+[WARNING] .claude/agents/another-agent.md
+  Missing recommended field: model
+  → Official spec: sub-agents.md (line 67)
+  → Suggestion: Add "model: sonnet" to frontmatter
+
+[INFO] .claude/agents/custom-agent.md
+  Non-standard field: custom_field
+  → Not found in official spec: sub-agents.md
+  → Consider: Remove or document in agent body
+
+─────────────────────────────────────────────────────────────
+
+SKILLS:
+
+[WARNING] .claude/skills/example-skill/SKILL.md
+  Missing recommended field: description
+  → Official spec: skills.md (line 34)
+
+═══════════════════════════════════════════════════════════════
+```
+
+## Usage Patterns
+
+### Update Official Docs
+
+```
+User: "Claude Code 공식 문서 업데이트해줘"
+
+Agent:
+1. Check last update timestamp
+2. Fetch llms.txt from code.claude.com
+3. Download all referenced documentation
+4. Save to ~/.claude/references/claude-code/
+5. Report: "Updated N docs, last checked: {timestamp}"
+```
+
+### Verify Compliance
+
+```
+User: "에이전트 공식 스펙 검증해줘"
+
+Agent:
+1. Check local docs age (warn if > 7 days)
+2. Read official frontmatter specs
+3. Scan all agents and skills
+4. Generate compliance report
+5. Provide actionable recommendations
+```
+
+### Integration with Sauron
+
+```
+mgr-sauron:watch workflow includes:
+  → mgr-claude-code-bible:verify
+  → Check compliance before push
+  → Block if ERROR-level issues found
+```
+
+## Storage Location
+
+```
+~/.claude/references/claude-code/
+├── last-updated.txt          # Timestamp of last fetch
+├── llms.txt                  # Index of all documentation
+├── sub-agents.md             # Agent specifications
+├── agent-teams.md            # Agent teams / multi-agent
+├── skills.md                 # Skill specifications
+├── hooks.md                  # Hook system
+├── plugins.md                # Plugin system
+├── settings.md               # Configuration
+├── model-config.md           # Model and effort controls
+└── mcp-servers.md            # MCP integration
+```
+
+## Error Handling
+
+| Situation | Action |
+|-----------|--------|
+| Network failure | Report error, use cached docs if available |
+| Parse failure | Report which doc failed, skip that section |
+| Missing local docs | Force update mode automatically |
+| Docs older than 7 days | Warn user, suggest update before verify |
+| Docs older than 30 days | Force update required |
+
+## Benefits
+
+1. **Compliance**: Ensure the project follows official Claude Code specs
+2. **Currency**: Stay updated with latest Claude Code features
+3. **Quality**: Catch missing required/recommended fields early
+4. **Documentation**: Reference official docs in verification reports
+5. **Automation**: Integrate with mgr-sauron for pre-push verification

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

@@ -2,6 +2,10 @@
 name: mgr-creator
 description: Use when you need to create new agents following design guidelines. Automatically researches authoritative references before agent creation to ensure high-quality knowledge base
 model: sonnet
+memory: project
+effort: high
+skills:
+  - create-agent
 tools:
   - Read
   - Write
@@ -76,6 +80,8 @@ For technology/language/framework agents, MUST research authoritative references
 name: agent-name
 description: Brief description
 model: sonnet
+skills:
+  - create-agent
 tools:
   - Read
   - Write

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

@@ -2,6 +2,9 @@
 name: mgr-gitnerd
 description: Use when you need to handle Git operations and GitHub workflow management, including commits, branches, PRs, and history management following best practices
 model: sonnet
+memory: project
+effort: medium
+skills: []
 tools:
   - Read
   - Write
@@ -81,7 +84,7 @@ Types: feat, fix, docs, style, refactor, test, chore
 
 ## Push Rules (R017 Compliance)
 
-**CRITICAL: All pushes in baekgom-agents require prior sauron verification.**
+**CRITICAL: All pushes require prior sauron verification.**
 
 Before executing `git push`:
 1. Confirm that mgr-sauron:watch has been run

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

@@ -2,6 +2,10 @@
 name: mgr-sauron
 description: Use when you need automated verification of R017 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds) before commits
 model: sonnet
+memory: project
+effort: high
+skills:
+  - sauron-watch
 tools:
   - Read
   - Write
@@ -18,11 +22,13 @@ You are an automated verification specialist that executes the mandatory R017 ve
 1. Execute mgr-supplier:audit automatically
 2. Execute mgr-sync-checker:check automatically
 3. Execute mgr-updater:docs automatically
-4. Verify workflow alignment
-5. Verify reference integrity
-6. Verify philosophy compliance (R006, R007, R008, R009, R010)
-7. Auto-fix simple issues (count mismatches, missing entries)
-8. Generate verification report
+4. Execute mgr-claude-code-bible:verify (official spec compliance)
+5. Verify workflow alignment
+6. Verify reference integrity (frontmatter, memory fields, skill refs)
+7. Verify philosophy compliance (R006-R011)
+8. Verify Claude-native compatibility
+9. Auto-fix simple issues (count mismatches, missing fields)
+10. Generate verification report
 
 ## Commands
 
@@ -46,40 +52,44 @@ You are an automated verification specialist that executes the mandatory R017 ve
 - mgr-updater:docs (if changes detected)
 
 **Round 5: Final Count Verification**
-- Agent count: CLAUDE.md vs actual
-- Command count: registry vs files
-- Skill count: registry vs files
+- Agent count: CLAUDE.md vs actual .md files in .claude/agents/
+- Skill count: CLAUDE.md vs actual SKILL.md files in .claude/skills/
+- Memory field distribution: project/user/none counts match CLAUDE.md
+- Display format: Task(subagent_type):model compliance in recent output
 
 ### Phase 2: Deep Review (3 rounds)
 
 **Round 1: Workflow Alignment**
 - Agent workflows match purpose
 - Command definitions match implementations
-- Pipeline definitions are valid
+- Routing skill patterns are valid
 
 **Round 2: Reference Verification**
-- All refs/ symlinks valid
-- All index.yaml references exist
-- No circular dependencies
+- All skill references in agent frontmatter exist in .claude/skills/
+- All agent files have valid frontmatter (name, description, model, tools)
+- memory field values are valid (user | project | local) where present
+- No orphaned agents (not referenced by any routing skill)
 
 **Round 3: Philosophy Compliance**
-- R006: Agent design rules
+- R006: Agent design rules (including memory field spec)
 - R007: Agent identification rules
-- R008: Tool identification rules
-- R009: Parallel execution rules
+- R008: Tool identification rules (Task(subagent_type):model format)
+- R009: Parallel execution rules (Task(subagent_type):model display)
 - R010: Orchestrator coordination rules
+- R011: Memory integration (native-first architecture)
 
 ### Phase 3: Auto-fix & Report
 
 **Auto-fixable Issues:**
 - Count mismatches in CLAUDE.md
-- Missing entries in index.yaml
-- Outdated command documentation
+- Missing memory field in agents that should have it
+- Outdated documentation references
 
 **Manual Review Required:**
 - Missing agent files
-- Broken symlinks to non-existent targets
+- Invalid memory scope values
 - Philosophy violations
+- Claude-native compatibility issues
 
 ## Output Format
 
@@ -90,11 +100,11 @@ You are an automated verification specialist that executes the mandatory R017 ve
 
 === Phase 1: Manager Verification ===
 [Round 1/5] mgr-supplier:audit
-  - 28 agents checked
+  - 34 agents checked
   - 3 issues found
 [Round 2/5] mgr-sync-checker:check
   - Documentation sync: OK
-  - Command registry: 2 missing
+  - Memory distribution: 24 project + 3 user + 7 none
 ...
 
 === Phase 2: Deep Review ===
@@ -109,8 +119,7 @@ You are an automated verification specialist that executes the mandatory R017 ve
 
 === Phase 3: Resolution ===
 [Auto-fixed]
-  - CLAUDE.md agent count: 27 -> 28
-  - commands/index.yaml: added 2 entries
+  - CLAUDE.md agent count: 33 -> 34
 
 [Manual Review Required]
   - .claude/agents/broken-agent.md: missing
@@ -127,9 +136,8 @@ You are an automated verification specialist that executes the mandatory R017 ve
 ```
 [Sauron] Quick Verification
 
-Agents: 28/28 OK
-Commands: 45/45 OK
-Skills: 18/18 OK
+Agents: 34/34 OK
+Skills: 40/40 OK
 Refs: 2 broken
 
 Status: ISSUES FOUND
@@ -142,4 +150,5 @@ Works with:
 - **mgr-supplier**: Dependency validation
 - **mgr-sync-checker**: Documentation sync
 - **mgr-updater**: Documentation updates
+- **mgr-claude-code-bible**: Official spec compliance verification
 - **secretary**: Orchestration coordination

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

@@ -2,6 +2,10 @@
 name: mgr-supplier
 description: Use when you need to validate and manage skills/guides dependencies for agents, detect missing/broken refs, and ensure agents have proper resources
 model: haiku
+memory: local
+effort: low
+skills:
+  - audit-agents
 tools:
   - Read
   - Write

package/templates/.claude/agents/mgr-sync-checker.md

@@ -2,6 +2,10 @@
 name: mgr-sync-checker
 description: Use when you need to verify documentation and workflow synchronization, ensuring all docs, configs, and workflow definitions remain synchronized with the project structure
 model: haiku
+memory: local
+effort: low
+skills:
+  - update-docs
 tools:
   - Read
   - Write

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

@@ -2,6 +2,10 @@
 name: mgr-updater
 description: Use when you need to update external agents, skills, and guides from their upstream sources, checking versions and applying updates
 model: sonnet
+memory: project
+effort: medium
+skills:
+  - update-external
 tools:
   - Read
   - Write

package/templates/.claude/agents/qa-engineer.md

@@ -2,6 +2,9 @@
 name: qa-engineer
 description: Use when you need to execute tests based on detailed plans and documentation, perform manual and automated testing, report defects, and validate fixes
 model: sonnet
+memory: project
+effort: medium
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/qa-planner.md

@@ -2,6 +2,9 @@
 name: qa-planner
 description: Use when you need to create detailed QA plans from requirements and specifications, including test strategy design, risk-based prioritization, test scenario identification, and acceptance criteria definition
 model: sonnet
+memory: project
+effort: high
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/qa-writer.md

@@ -2,6 +2,9 @@
 name: qa-writer
 description: Use when you need to create comprehensive QA documentation from detailed plans, including test cases, test reports, and quality documentation
 model: sonnet
+memory: project
+effort: medium
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/sys-memory-keeper.md

@@ -2,6 +2,12 @@
 name: sys-memory-keeper
 description: Use when you need to manage session memory persistence using claude-mem, save context before compaction, restore context on session start, or query past memories
 model: sonnet
+memory: project
+effort: medium
+skills:
+  - memory-management
+  - memory-save
+  - memory-recall
 tools:
   - Read
   - Write
@@ -39,7 +45,7 @@ You are a session memory management specialist that ensures context survives acr
    - Important code changes
 
 2. **Format with metadata**
-   - project: "baekgom-agents"
+   - project: "my-project"
    - session: {date}-{uuid}
    - tags: [session, task, decision, ...]
    - timestamp: current time
@@ -50,7 +56,7 @@ You are a session memory management specialist that ensures context survives acr
 ### Recall Operation
 
 1. **Build semantic query**
-   - Include project prefix: "baekgom-agents"
+   - Include project prefix: "my-project"
    - Add relevant keywords from current task
    - Include date if temporal search needed
 
@@ -68,10 +74,10 @@ You are a session memory management specialist that ensures context survives acr
 
 | Query Type | Example |
 |------------|---------|
-| Task-based | `"baekgom-agents agent creation workflow"` |
-| Temporal | `"baekgom-agents 2025-01-24 bug fix"` |
-| Topic-based | `"baekgom-agents memory system architecture"` |
-| Decision-based | `"baekgom-agents decision parallel execution"` |
+| Task-based | `"my-project agent creation workflow"` |
+| Temporal | `"my-project 2025-01-24 bug fix"` |
+| Topic-based | `"my-project memory system architecture"` |
+| Decision-based | `"my-project decision parallel execution"` |
 
 ### Query Don'ts
 
@@ -90,7 +96,7 @@ document:
     - Decisions: [list of decisions]
     - Notes: [additional context]
   metadata:
-    project: baekgom-agents
+    project: my-project
     session: {date}-{uuid}
     tags: [session, task, decision]
     created_at: {timestamp}
@@ -107,5 +113,5 @@ document:
 
 - Provider: claude-mem
 - Collection: claude_memories
-- Project tag: baekgom-agents
+- Project tag: my-project
 - Archive path: ~/.claude-mem/archives/

package/templates/.claude/agents/sys-naggy.md

@@ -2,6 +2,9 @@
 name: sys-naggy
 description: Use when you need TODO list management and task tracking with proactive reminders, helping maintain project momentum by monitoring stale tasks and deadlines
 model: sonnet
+memory: local
+effort: low
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/tool-bun-expert.md

@@ -2,6 +2,9 @@
 name: tool-bun-expert
 description: Use for Bun runtime development, bunfig.toml configuration, Bun test runner, fast bundling, and Node.js to Bun migrations
 model: sonnet
+memory: project
+effort: medium
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/tool-npm-expert.md

@@ -2,6 +2,12 @@
 name: tool-npm-expert
 description: Use for npm package publishing workflows, semantic versioning (major/minor/patch), package.json optimization, and dependency audits
 model: sonnet
+memory: project
+effort: medium
+skills:
+  - npm-audit
+  - npm-publish
+  - npm-version
 tools:
   - Read
   - Write

package/templates/.claude/agents/tool-optimizer.md

@@ -2,6 +2,12 @@
 name: tool-optimizer
 description: Use for bundle size analysis, tree-shaking verification, performance profiling, dead code detection, and build optimization recommendations
 model: sonnet
+memory: project
+effort: medium
+skills:
+  - optimize-analyze
+  - optimize-bundle
+  - optimize-report
 tools:
   - Read
   - Write

package/templates/.claude/hooks/hooks.json

@@ -47,7 +47,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "~/.claude/hooks/strategic-compact/suggest-compact.sh"
+            "command": "#!/bin/bash\nCOUNTER_FILE=\"/tmp/claude-tool-count-$$\"\nTHRESHOLD=${COMPACT_THRESHOLD:-50}\nif [ -f \"$COUNTER_FILE\" ]; then COUNT=$(cat \"$COUNTER_FILE\"); COUNT=$((COUNT + 1)); else COUNT=1; fi\necho \"$COUNT\" > \"$COUNTER_FILE\"\nif [ \"$COUNT\" -eq \"$THRESHOLD\" ]; then echo '[StrategicCompact] Reached '$THRESHOLD' tool calls' >&2; echo '[StrategicCompact] Consider /compact if at a logical breakpoint' >&2; fi\nif [ \"$COUNT\" -gt \"$THRESHOLD\" ] && [ $(((COUNT - THRESHOLD) % 25)) -eq 0 ]; then echo \"[StrategicCompact] $COUNT tool calls - /compact reminder\" >&2; fi\ncat"
           }
         ],
         "description": "Suggest manual compaction at logical intervals"
@@ -57,34 +57,10 @@
         "hooks": [
           {
             "type": "command",
-            "command": "#!/bin/bash\ninput=$(cat)\nagent=$(echo \"$input\" | jq -r '.tool_input.description // \"agent\"' | head -c 30)\n~/.claude/hooks/hud/update-status.sh \"$agent\" \"\" \"1\"\necho \"$input\""
+            "command": "#!/bin/bash\ninput=$(cat)\nagent_type=$(echo \"$input\" | jq -r '.tool_input.subagent_type // \"unknown\"')\nmodel=$(echo \"$input\" | jq -r '.tool_input.model // \"inherit\"')\ndesc=$(echo \"$input\" | jq -r '.tool_input.description // \"\"' | head -c 40)\nresume=$(echo \"$input\" | jq -r '.tool_input.resume // empty')\nif [ -n \"$resume\" ]; then\n  echo \"─── [Resume] ${agent_type}:${model} | ${desc} ───\" >&2\nelse\n  echo \"─── [Spawn] ${agent_type}:${model} | ${desc} ───\" >&2\nfi\necho \"$input\""
           }
         ],
-        "description": "HUD statusline - show agent spawn via Task tool"
-      }
-    ],
-    "PreCompact": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "~/.claude/hooks/memory-persistence/pre-compact.sh"
-          }
-        ],
-        "description": "Save state before context compaction"
-      }
-    ],
-    "SessionStart": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "~/.claude/hooks/memory-persistence/session-start.sh"
-          }
-        ],
-        "description": "Load previous context on new session"
+        "description": "HUD statusline - show subagent_type, model, and description on Task spawn"
       }
     ],
     "PostToolUse": [
@@ -169,16 +145,6 @@
           }
         ],
         "description": "Final audit for console.log in modified files before session ends"
-      },
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "~/.claude/hooks/memory-persistence/session-end.sh"
-          }
-        ],
-        "description": "Persist session state on end"
       }
     ]
   }

package/templates/.claude/install-hooks.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 # Claude Code Hooks & Contexts Installer
 # Source: https://github.com/affaan-m/everything-claude-code
-# Adapted for baekgom-agents project
+# Hook installation script
 
 set -e