oh-my-customcode 0.16.4 → 0.17.0

package/README.md

@@ -21,7 +21,7 @@ Like oh-my-zsh transformed shell customization, oh-my-customcode makes personali
 
 | Feature | Description |
 |---------|-------------|
-| **Batteries Included** | 42 agents, 55 skills, 22 guides, 18 rules, 2 hooks, 4 contexts, ontology graph - ready to use out of the box |
+| **Batteries Included** | 41 agents, 55 skills, 22 guides, 18 rules, 2 hooks, 4 contexts, ontology graph - ready to use out of the box |
 | **Sub-Agent Model** | Supports hierarchical agent orchestration with specialized roles |
 | **Dead Simple Customization** | Create a folder + markdown file = new agent or skill |
 | **Mix and Match** | Use built-in components, create your own, or combine both |
@@ -85,8 +85,7 @@ Claude Code selects the appropriate model and parallelizes independent tasks (up
 ```
 /create-agent
   ├── mgr-creator:sonnet       — agent scaffolding
-  ├── mgr-supplier:haiku       — dependency check
-  └── mgr-sync-checker:haiku   — registry verification
+  └── mgr-supplier:haiku       — dependency check
 
 /code-review
   ├── lang-golang-expert:sonnet — Go implementation
@@ -108,11 +107,11 @@ Claude Code selects the appropriate model and parallelizes independent tasks (up
 
 ## What's Included
 
-### Agents (42)
+### Agents (41)
 
 | Category | Count | Agents |
 |----------|-------|--------|
-| **Managers** | 7 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron, mgr-claude-code-bible |
+| **Managers** | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible |
 | **System** | 2 | sys-memory-keeper, sys-naggy |
 | **Languages** | 6 | lang-golang-expert, lang-python-expert, lang-rust-expert, lang-kotlin-expert, lang-typescript-expert, lang-java21-expert |
 | **Frontend** | 3 | fe-vercel-agent, fe-vuejs-agent, fe-svelte-agent |
@@ -123,7 +122,7 @@ Claude Code selects the appropriate model and parallelizes independent tasks (up
 | **Architecture** | 2 | arch-documenter, arch-speckit-agent |
 | **Infrastructure** | 2 | infra-docker-expert, infra-aws-expert |
 | **QA** | 3 | qa-planner, qa-writer, qa-engineer |
-| **Total** | **42** | |
+| **Total** | **41** | |
 
 ### Skills (55)
 
@@ -221,7 +220,7 @@ your-project/
     ├── rules/             # Behavior rules (18 total)
     ├── hooks/             # Event hooks (2 total)
     ├── contexts/          # Context files (4 total)
-    ├── agents/            # Agent definitions (42 flat .md files)
+    ├── agents/            # Agent definitions (41 flat .md files)
     │   ├── lang-golang-expert.md
     │   ├── be-fastapi-expert.md
     │   ├── mgr-creator.md

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.16.4",
+  "version": "0.17.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

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

@@ -1,6 +1,6 @@
 ---
 name: mgr-sauron
-description: Use when you need automated verification of R016 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds) before commits
+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
@@ -15,26 +15,25 @@ tools:
   - Bash
 ---
 
-You are an automated verification specialist that executes the mandatory R016 verification process, acting as the "all-seeing eye" that ensures system integrity through comprehensive multi-round verification.
+You are an automated verification specialist that executes the mandatory R017 verification process, acting as the "all-seeing eye" that ensures system integrity through comprehensive multi-round verification.
 
 ## Core Capabilities
 
 1. Execute mgr-supplier:audit automatically
-2. Execute mgr-sync-checker:check automatically
-3. Execute mgr-updater:docs automatically
-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
+2. Execute mgr-updater:docs automatically
+3. Execute mgr-claude-code-bible:verify (official spec compliance)
+4. Verify workflow alignment
+5. Verify reference integrity (frontmatter, memory fields, skill refs)
+6. Verify philosophy compliance (R006-R011)
+7. Verify Claude-native compatibility
+8. Auto-fix simple issues (count mismatches, missing fields)
+9. Generate verification report
 
 ## Commands
 
 | Command | Description |
 |---------|-------------|
-| `mgr-sauron:watch` | Full R016 verification (5+3 rounds) |
+| `mgr-sauron:watch` | Full R017 verification (5+3 rounds) |
 | `mgr-sauron:quick` | Quick verification (single pass) |
 | `mgr-sauron:report` | Generate verification status report |
 
@@ -43,13 +42,12 @@ You are an automated verification specialist that executes the mandatory R016 ve
 ### Phase 1: Manager Verification (5 rounds)
 
 **Round 1-2: Basic Checks**
-- mgr-supplier:audit (all agents)
-- mgr-sync-checker:check
+- mgr-supplier:audit (all agents, dependency validation)
+- mgr-updater:docs (documentation sync check)
 
 **Round 3-4: Re-verify + Update**
 - Re-run mgr-supplier:audit
-- Re-run mgr-sync-checker:check
-- mgr-updater:docs (if changes detected)
+- Re-run mgr-updater:docs (apply any detected changes)
 
 **Round 5: Final Count Verification**
 - Agent count: CLAUDE.md vs actual .md files
@@ -116,7 +114,7 @@ You are an automated verification specialist that executes the mandatory R016 ve
 [Round 1/5] mgr-supplier:audit
   - 34 agents checked
   - 3 issues found
-[Round 2/5] mgr-sync-checker:check
+[Round 2/5] mgr-updater:docs
   - Documentation sync: OK
 ...
 
@@ -155,7 +153,6 @@ Run 'mgr-sauron:watch' for full verification
 
 Works with:
 - **mgr-supplier**: Dependency validation
-- **mgr-sync-checker**: Documentation sync
-- **mgr-updater**: Documentation updates
+- **mgr-updater**: Documentation updates and sync
 - **mgr-claude-code-bible**: Official spec compliance
 - **secretary**: Orchestration coordination

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

@@ -6,6 +6,7 @@ memory: project
 effort: medium
 skills:
   - update-external
+  - update-docs
 tools:
   - Read
   - Write

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

@@ -1,6 +1,6 @@
 ---
 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
+description: Use when you need to manage session memory persistence using claude-mem, save context before compaction, restore context on session start, query past memories, or perform session-end dual-system auto-save
 model: sonnet
 memory: project
 effort: medium
@@ -41,3 +41,18 @@ Always include project name. Use task-based, temporal, or topic-based queries. A
 ## Config
 
 Provider: claude-mem | Collection: claude_memories | Archive: ~/.claude-mem/archives/
+
+## Session-End Auto-Save
+
+When triggered by session-end signal from orchestrator:
+
+1. **Collect** session summary: completed tasks, key decisions, open items
+2. **Save to claude-mem** (if available): `mcp__claude-mem__save_memory` with project name, session date, and summary
+3. **Verify episodic-memory** (if available): `mcp__episodic-memory__search` to confirm session is indexed
+4. **Report** results to orchestrator: saved/skipped/failed per system
+
+### Failure Handling
+
+- claude-mem unavailable → skip, report warning
+- episodic-memory unavailable → skip, report warning
+- Both unavailable → warn orchestrator, do not block session end

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

@@ -68,9 +68,13 @@
           {
             "type": "command",
             "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\""
+          },
+          {
+            "type": "command",
+            "command": "bash .claude/hooks/scripts/git-delegation-guard.sh"
           }
         ],
-        "description": "HUD statusline - show subagent_type, model, and description on Task spawn"
+        "description": "HUD statusline + R010 git delegation guard on Task spawn"
       }
     ],
     "PostToolUse": [

package/templates/.claude/ontology/agents.yaml

@@ -33,7 +33,7 @@ classes:
     agents: [qa-planner, qa-writer, qa-engineer]
     description: "QA and testing"
   ManagerAgent:
-    agents: [mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron, mgr-claude-code-bible]
+    agents: [mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible]
     description: "System management agents"
   SystemAgent:
     agents: [sys-memory-keeper, sys-naggy]
@@ -485,18 +485,6 @@ agents:
     keywords: [git, github, commit, branch, pull-request, conventional-commits, rebase, merge]
     file_patterns: [".git/*", ".github/*"]
 
-  mgr-sync-checker:
-    class: ManagerAgent
-    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, Edit, Grep, Glob, Bash]
-    summary: "Documentation synchronization validator for project structure consistency"
-    keywords: [synchronization, documentation, verification, consistency, agent-count, commands]
-    file_patterns: ["CLAUDE.md", ".claude/agents/*.md", "commands/index.yaml"]
-
   mgr-sauron:
     class: ManagerAgent
     description: "Use when you need automated verification of R017 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds) before commits"

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

@@ -39,7 +39,6 @@
     "mgr-updater": ["update-external"],
     "mgr-supplier": ["audit-agents"],
     "mgr-gitnerd": [],
-    "mgr-sync-checker": ["update-docs"],
     "mgr-sauron": ["sauron-watch"],
     "mgr-claude-code-bible": ["claude-code-bible"],
     "sys-memory-keeper": ["memory-management", "memory-save", "memory-recall"],
@@ -77,7 +76,7 @@
     "create-agent": ["mgr-creator"],
     "update-external": ["mgr-updater"],
     "audit-agents": ["mgr-supplier"],
-    "update-docs": ["mgr-sync-checker"],
+    "update-docs": ["mgr-updater"],
     "sauron-watch": ["mgr-sauron"],
     "claude-code-bible": ["mgr-claude-code-bible"],
     "memory-management": ["sys-memory-keeper"],

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

@@ -39,7 +39,6 @@
     "mgr-updater": { "type": "Agent", "class": "ManagerAgent" },
     "mgr-supplier": { "type": "Agent", "class": "ManagerAgent" },
     "mgr-gitnerd": { "type": "Agent", "class": "ManagerAgent" },
-    "mgr-sync-checker": { "type": "Agent", "class": "ManagerAgent" },
     "mgr-sauron": { "type": "Agent", "class": "ManagerAgent" },
     "mgr-claude-code-bible": { "type": "Agent", "class": "ManagerAgent" },
     "sys-memory-keeper": { "type": "Agent", "class": "SystemAgent" },
@@ -146,7 +145,6 @@
     { "source": "mgr-creator", "target": "create-agent", "relation": "requires" },
     { "source": "mgr-updater", "target": "update-external", "relation": "requires" },
     { "source": "mgr-supplier", "target": "audit-agents", "relation": "requires" },
-    { "source": "mgr-sync-checker", "target": "update-docs", "relation": "requires" },
     { "source": "mgr-sauron", "target": "sauron-watch", "relation": "requires" },
     { "source": "mgr-claude-code-bible", "target": "claude-code-bible", "relation": "requires" },
     { "source": "sys-memory-keeper", "target": "memory-management", "relation": "requires" },
@@ -164,7 +162,6 @@
     { "source": "secretary-routing", "target": "mgr-updater", "relation": "routes_to" },
     { "source": "secretary-routing", "target": "mgr-supplier", "relation": "routes_to" },
     { "source": "secretary-routing", "target": "mgr-gitnerd", "relation": "routes_to" },
-    { "source": "secretary-routing", "target": "mgr-sync-checker", "relation": "routes_to" },
     { "source": "secretary-routing", "target": "mgr-sauron", "relation": "routes_to" },
     { "source": "secretary-routing", "target": "mgr-claude-code-bible", "relation": "routes_to" },
     { "source": "secretary-routing", "target": "sys-memory-keeper", "relation": "routes_to" },
@@ -352,10 +349,6 @@
       "requires": [],
       "routed_by": ["secretary-routing"]
     },
-    "mgr-sync-checker": {
-      "requires": ["update-docs"],
-      "routed_by": ["secretary-routing"]
-    },
     "mgr-sauron": {
       "requires": ["sauron-watch"],
       "routed_by": ["secretary-routing"]
@@ -497,7 +490,7 @@
       "depends_on": []
     },
     "update-docs": {
-      "required_by": ["mgr-sync-checker"],
+      "required_by": ["mgr-updater"],
       "depends_on": []
     },
     "sauron-watch": {
@@ -521,7 +514,7 @@
       "depends_on": ["R011"]
     },
     "secretary-routing": {
-      "routes_to": ["mgr-creator", "mgr-updater", "mgr-supplier", "mgr-gitnerd", "mgr-sync-checker", "mgr-sauron", "mgr-claude-code-bible", "sys-memory-keeper", "sys-naggy"],
+      "routes_to": ["mgr-creator", "mgr-updater", "mgr-supplier", "mgr-gitnerd", "mgr-sauron", "mgr-claude-code-bible", "sys-memory-keeper", "sys-naggy"],
       "depends_on": []
     },
     "dev-lead-routing": {

package/templates/.claude/ontology/graphs/routing.json

@@ -8,7 +8,6 @@
         "mgr-updater",
         "mgr-supplier",
         "mgr-gitnerd",
-        "mgr-sync-checker",
         "mgr-sauron",
         "mgr-claude-code-bible",
         "sys-memory-keeper",
@@ -70,7 +69,6 @@
     "mgr-updater": "secretary-routing",
     "mgr-supplier": "secretary-routing",
     "mgr-gitnerd": "secretary-routing",
-    "mgr-sync-checker": "secretary-routing",
     "mgr-sauron": "secretary-routing",
     "mgr-claude-code-bible": "secretary-routing",
     "sys-memory-keeper": "secretary-routing",

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

@@ -448,7 +448,7 @@ skills:
     model_invocable: true
     summary: "Routes agent management tasks to appropriate manager agents"
     keywords: [routing, management, agent-creation, git, memory, verification]
-    routes_to: [mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron, mgr-claude-code-bible, sys-memory-keeper, sys-naggy]
+    routes_to: [mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible, sys-memory-keeper, sys-naggy]
     rule_references: []
 
   snowflake-best-practices:

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

@@ -30,6 +30,32 @@ The main conversation is the **sole orchestrator**. It uses routing skills to de
 ╚══════════════════════════════════════════════════════════════════╝
 ```
 
+## Self-Check (Mandatory Before Delegating Tasks)
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  BEFORE DELEGATING A TASK TO ANY AGENT, ASK YOURSELF:            ║
+║                                                                   ║
+║  1. Does the task prompt contain git commands?                   ║
+║     (commit, push, revert, merge, rebase, checkout, branch,     ║
+║      reset, cherry-pick, tag)                                    ║
+║     YES → The git part MUST go to mgr-gitnerd                   ║
+║     NO  → Proceed                                                ║
+║                                                                   ║
+║  2. Am I bundling git operations with file editing?              ║
+║     YES → STOP. Split into separate delegations:                 ║
+║           - File editing → appropriate specialist                ║
+║           - Git operations → mgr-gitnerd                         ║
+║     NO  → Good. Continue.                                        ║
+║                                                                   ║
+║  3. Is the target agent mgr-gitnerd for ALL git operations?     ║
+║     YES → Good. Continue.                                        ║
+║     NO  → STOP. This is a VIOLATION. Re-route to mgr-gitnerd.   ║
+║                                                                   ║
+║  If ANY answer is wrong → SPLIT THE TASK                         ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
 ## Architecture
 
 ```
@@ -72,6 +98,22 @@ Main Conversation (orchestrator)
 
 ✓ CORRECT: Always delegate, no matter how small
    Task(appropriate-agent) → create config file
+
+❌ WRONG: Bundling git operations with file editing in non-gitnerd agent
+   Main conversation → Task(general-purpose) → "git revert + edit file + git commit"
+   Main conversation → Task(lang-typescript-expert) → "fix bug and commit"
+
+✓ CORRECT: Separate file editing from git operations
+   Main conversation → Task(lang-typescript-expert) → "fix bug" (file edit only)
+   Main conversation → Task(mgr-gitnerd) → "git commit" (git operation only)
+
+❌ WRONG: Including git commands in non-gitnerd agent prompt for "convenience"
+   Task(general-purpose, prompt="revert the last commit, edit the file, then commit the fix")
+
+✓ CORRECT: Split into separate delegations
+   Task(mgr-gitnerd, prompt="revert the last commit")
+   Task(appropriate-expert, prompt="edit the file to fix the issue")
+   Task(mgr-gitnerd, prompt="commit the fix")
 ```
 
 ## Session Continuity

package/templates/.claude/rules/MUST-sync-verification.md

@@ -14,8 +14,8 @@ Every `git push` requires: `mgr-sauron:watch` → all pass → `git push`
 
 | Round | Actions |
 |-------|---------|
-| 1-2 | mgr-supplier:audit, mgr-sync-checker:check, fix issues |
-| 3-4 | Re-verify + mgr-updater:docs, fix remaining |
+| 1-2 | mgr-supplier:audit, mgr-updater:docs (sync check), fix issues |
+| 3-4 | Re-verify mgr-supplier:audit + re-run mgr-updater:docs, fix remaining |
 | 5 | Final: all counts match, frontmatter valid, skill refs exist, memory scopes valid, routing patterns updated |
 
 Also run: mgr-claude-code-bible:verify (official spec compliance)

package/templates/.claude/rules/SHOULD-hud-statusline.md

@@ -2,26 +2,33 @@
 
 > **Priority**: SHOULD | **ID**: R012
 
-## Format
+## Two-System Architecture
 
-```
-─── [Agent] {name} | [Progress] {n}/{total} | [Parallel] {count} ───
-```
-
-## When to Display
+| Aspect | HUD Events | Statusline API |
+|--------|-----------|----------------|
+| Channel | stderr (hooks) | stdout (dedicated statusline) |
+| Location | Inline in conversation log | Persistent bar at screen bottom |
+| Trigger | PreToolUse (Task matcher) | Message update cycle (~300ms) |
+| Role | Event notifications | Persistent session status |
 
-Multi-step tasks, parallel execution, long-running operations. Skip for single brief operations.
-
-## Hook Implementation
+## HUD Events (Hook-based)
 
-Implemented in `.claude/hooks/hooks.json` (PreToolUse → Task matcher):
+### Format
 
 ```
 ─── [Spawn] {subagent_type}:{model} | {description} ───
 ─── [Resume] {subagent_type}:{model} | {description} ───
 ```
 
-## Display with Parallel
+### When to Display
+
+Multi-step tasks, parallel execution, long-running operations. Skip for single brief operations.
+
+### Implementation
+
+Implemented in `.claude/hooks/hooks.json` (PreToolUse → Task matcher).
+
+### Parallel Display
 
 ```
 ─── [Agent] secretary | [Parallel] 4 ───
@@ -29,4 +36,41 @@ Implemented in `.claude/hooks/hooks.json` (PreToolUse → Task matcher):
   [2] Task(lang-golang-expert):haiku → Code review
 ```
 
+## Statusline API (Command-based)
+
+### Format
+
+```
+{Cost} | {project} | {branch} | CTX:{usage}%
+```
+
+Example: `$0.05 | my-project | develop | CTX:42%`
+
+### Configuration
+
+```json
+{
+  "statusLine": {
+    "type": "command",
+    "command": ".claude/statusline.sh",
+    "padding": 0
+  }
+}
+```
+
+Set in `.claude/settings.local.json`. The command receives JSON via stdin with model, workspace, context window, and cost data.
+
+### Color Coding
+
+| Element | Condition | Color |
+|---------|-----------|-------|
+| Cost | < $1.00 | Green |
+| Cost | $1.00 - $4.99 | Yellow |
+| Cost | >= $5.00 | Red |
+| Context | < 60% | Green |
+| Context | 60-79% | Yellow |
+| Context | >= 80% | Red |
+
+## Integration
+
 Integrates with R007 (Agent ID), R008 (Tool ID), R009 (Parallel).

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

@@ -37,3 +37,35 @@ Agent frontmatter `memory: project|user|local` enables persistent memory:
 - Keep MEMORY.md under 200 lines
 - Do not store sensitive data or duplicate CLAUDE.md content
 - Memory write failures should not block main task
+
+## Session-End Auto-Save
+
+### Trigger
+
+Session-end detected when user says: "끝", "종료", "마무리", "done", "wrap up", "end session", or explicitly requests session save.
+
+### Flow
+
+```
+User signals session end
+  → Orchestrator delegates to sys-memory-keeper
+    → sys-memory-keeper performs dual-system save:
+       1. claude-mem save (if available)
+       2. episodic-memory verification (if available)
+    → Reports result to orchestrator
+  → Orchestrator confirms to user
+```
+
+### Dual-System Save
+
+| System | Tool | Action | Required |
+|--------|------|--------|----------|
+| claude-mem | `mcp__claude-mem__save_memory` | Save session summary with project, tasks, decisions | No (best-effort) |
+| episodic-memory | `mcp__episodic-memory__search` | Verify session is indexed for future retrieval | No (best-effort) |
+
+### Failure Policy
+
+- Both saves are **non-blocking**: memory failure MUST NOT prevent session from ending
+- If claude-mem unavailable: skip, log warning
+- If episodic-memory unavailable: skip, log warning
+- If both unavailable: warn user, proceed with session end

package/templates/.claude/skills/claude-code-bible/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: claude-code-bible
-description: Fetch and verify Claude Code official documentation. Use when checking official spec compliance or updating local reference docs.
+description: Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.
 disable-model-invocation: true
 ---
 
@@ -10,7 +10,7 @@ Official documentation reference management for Claude Code.
 
 ## Purpose
 
-Maintain up-to-date local copies of Claude Code official documentation and verify that agents/skills comply with the official specifications.
+Maintain up-to-date local copies of Claude Code official documentation.
 
 ## Commands
 
@@ -50,56 +50,6 @@ node .claude/skills/claude-code-bible/scripts/fetch-docs.js --output /path/to/ou
 - `0`: Success (or cache is fresh)
 - `1`: Fatal error
 
-### /claude-code-bible verify
-
-Verify agents and skills against official Claude Code specifications.
-
-**What it checks:**
-- Agent structure compliance (frontmatter fields, file format)
-- Skill structure compliance (SKILL.md format, disable-model-invocation usage)
-- Tool usage patterns match official recommendations
-- Workflow patterns align with Claude Code best practices
-- Agent/skill naming conventions follow official guidelines
-
-**Usage:**
-```bash
-# Verify all agents and skills
-/claude-code-bible verify
-
-# Verify specific agent
-/claude-code-bible verify --agent mgr-creator
-
-# Verify specific skill
-/claude-code-bible verify --skill go-best-practices
-
-# Verbose output
-/claude-code-bible verify --verbose
-```
-
-**Verification rules:**
-1. **Agent frontmatter** must include:
-   - `name`: kebab-case identifier
-   - `description`: one-line summary
-   - `model`: sonnet | opus | haiku
-   - `tools`: array of allowed tools
-   - `skills`: array of skill names
-
-2. **Skill frontmatter** must include:
-   - `name`: kebab-case identifier
-   - `description`: when/why to use this skill
-   - `disable-model-invocation`: true (if skill is procedural/scripted)
-
-3. **Agent files** should NOT contain:
-   - Detailed skill instructions (belongs in .claude/skills/)
-   - Reference documentation (belongs in guides/)
-   - Implementation scripts (belongs in .claude/skills/{name}/scripts/)
-
-4. **Skill files** should contain:
-   - Clear purpose statement
-   - Usage examples
-   - Input/output specifications
-   - Integration points with agents
-
 ## Implementation Notes
 
 ### Fetch Script (fetch-docs.js)
@@ -121,60 +71,21 @@ Verify agents and skills against official Claude Code specifications.
 - Continues on individual page failures
 - Prints summary of successes and failures
 
-### Verify Command (future implementation)
-
-The verify command should:
-1. Read official specs from `~/.claude/references/claude-code/`
-2. Parse all agents in `.claude/agents/*.md`
-3. Parse all skills in `.claude/skills/*/SKILL.md`
-4. Check each against official requirements
-5. Report violations with suggestions for fixes
-
 ## Integration with Other Skills
 
-### create-agent
-- Should verify new agents against official spec
-- Use `/claude-code-bible verify --agent <name>` after creation
-
 ### update-docs
 - Should update local docs first: `/claude-code-bible update`
-- Then verify sync with: `/claude-code-bible verify`
 
 ### dev-review
 - Can reference official docs for best practices
-- Verify code patterns against Claude Code recommendations
 
 ## Benefits
 
-1. **Compliance**: Ensure agents/skills match official specifications
-2. **Up-to-date**: Always have latest documentation locally
-3. **Offline access**: Work with docs even without internet
-4. **Automation**: Verify compliance automatically before commits
-5. **Learning**: Reference official patterns when creating new components
-
-## Example Workflow
-
-```bash
-# 1. Update local docs
-node .claude/skills/claude-code-bible/scripts/fetch-docs.js
-
-# 2. Create a new agent
-/create-agent my-new-agent
-
-# 3. Verify it matches official spec
-/claude-code-bible verify --agent my-new-agent
-
-# 4. Fix any violations
-
-# 5. Verify again
-/claude-code-bible verify --agent my-new-agent
-
-# 6. Commit when all checks pass
-```
+1. **Up-to-date**: Always have latest documentation locally
+2. **Offline access**: Work with docs even without internet
+3. **Learning**: Reference official patterns when creating new components
 
 ## Notes
 
-- The verify command implementation is left for future work
 - The fetch script is production-ready and can be used immediately
 - Consider running `/claude-code-bible update` weekly to stay current
-- Add this as a pre-commit hook to enforce compliance automatically

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

@@ -297,14 +297,6 @@ agents:
     supported_actions: [commit, branch, pr, sync, status, push, pull, merge]
     base_confidence: 40
 
-  mgr-sync-checker:
-    keywords:
-      korean: [동기화, 싱크, 검증]
-      english: [sync, synchronization, check, verify]
-    file_patterns: ["index.yaml", "CLAUDE.md", "COMMANDS.md"]
-    supported_actions: [check, agents, commands, docs, fix]
-    base_confidence: 40
-
   mgr-sauron:
     keywords:
       korean: [검증, 전체검증, 무결성, 사우론]

package/templates/.claude/skills/sauron-watch/SKILL.md

@@ -1,75 +1,89 @@
 ---
 name: sauron-watch
-description: Full R016 verification (5+3 rounds) before commit
+description: Full R017 verification (5+3 rounds) before commit
 disable-model-invocation: true
 ---
 
 # Sauron Watch Skill
 
-Execute full R016 verification process with 5 rounds of manager agent verification and 3 rounds of deep review.
+Execute full R017 verification process with 5 rounds of manager agent verification and 3 rounds of deep review.
 
 ## Purpose
 
-Ensure complete synchronization of agents, commands, documentation, and project structure before committing changes.
+Ensure complete synchronization of agents, skills, documentation, and project structure before committing changes.
 
 ## Workflow
 
 ### Phase 1: Manager Agent Verification (5 rounds)
 
-#### Round 1-2: Basic Sync
+#### Round 1-2: Basic Checks
 ```
-□ /audit-agents - Check all agent dependencies
-□ /sync-check - Verify registry synchronization
+□ mgr-supplier:audit - Check all agent dependencies and skill refs
+□ mgr-updater:docs - Verify documentation sync
 □ Fix any issues found
 ```
 
-#### Round 3-4: Deep Sync
+#### Round 3-4: Re-verify + Update
 ```
-□ /audit-agents - Re-verify after fixes
-□ /sync-check - Re-verify registries
-□ /update-docs - Check documentation sync
+□ mgr-supplier:audit - Re-verify after fixes
+□ mgr-updater:docs - Re-run and apply any detected changes
 □ Fix any remaining issues
 ```
 
-#### Round 5: Final Verification
+#### Round 5: Final Count Verification
 ```
-□ All agent counts match (CLAUDE.md, index.yaml, actual files)
-□ All symlinks valid
-□ All command registries updated
-□ All intent-detection triggers present
+□ Agent count matches: CLAUDE.md vs actual .md files
+□ Skill count matches: CLAUDE.md vs actual SKILL.md files
+□ Memory field distribution correct
+□ Hook/context/guide/rule counts match
+□ All frontmatter valid
+□ All skill refs exist
+□ All memory scopes valid (project|user|local)
+□ Routing patterns updated
 ```
 
 ### Phase 2: Deep Review (3 rounds)
 
 #### Deep Round 1: Workflow Alignment
 ```
-□ Agent creation workflow documented and functional
-□ Development workflow uses proper orchestrators
-□ Deployment workflow defined (if applicable)
-□ All orchestrators have complete `manages:` sections
+□ Agent workflows match purpose
+□ Command definitions match implementations
+□ Routing skill patterns are valid
+□ All routing skills have complete agent mappings
 ```
 
 #### Deep Round 2: Reference Verification
 ```
-□ All orchestrators properly reference their managed agents
-□ All rules are properly referenced
-□ No orphaned agents (not managed by any orchestrator)
+□ All skill references exist
+□ All agent frontmatter valid
+□ memory field values valid (user | project | local)
+□ No orphaned agents
 □ No circular references
 ```
 
 #### Deep Round 3: Philosophy Compliance
 ```
-□ R006: Separation of concerns (AGENT.md = role only, no details)
-□ R009: Parallel execution enabled for orchestrators
-□ R010: Multi-agent tasks use orchestrators
-□ R007/R008: Agent/tool identification documented
+□ R006: Agent design rules (including memory field spec)
+□ R007: Agent identification rules
+□ R008: Tool identification rules
+□ R009: Parallel execution rules
+□ R010: Orchestrator coordination rules
+□ R011: Memory integration (native-first architecture)
 □ All MUST rules enforced, SHOULD rules recommended
 ```
 
+### Phase 2.5: Documentation Accuracy
+```
+□ Every agent name in CLAUDE.md matches actual filename
+□ All counts cross-verified against filesystem
+□ Every slash command has corresponding skill
+□ Every agent reachable through routing skills
+```
+
 ### Phase 3: Fix Issues
 ```
-□ All issues from Phase 1 fixed
-□ All issues from Phase 2 fixed
+□ Auto-fix: count mismatches, missing fields, outdated refs
+□ Report: missing files, invalid scopes, philosophy violations
 □ Re-run verification if major fixes made
 ```
 
@@ -84,43 +98,41 @@ Ensure complete synchronization of agents, commands, documentation, and project
 ```
 [mgr-sauron:watch]
 
-Starting full R016 verification...
+Starting full R017 verification...
 
 ═══════════════════════════════════════════════════════════
  PHASE 1: Manager Agent Verification (5 rounds)
 ═══════════════════════════════════════════════════════════
 
-[Round 1/5] Basic sync - /audit-agents
-  ✓ All agents have valid dependencies
+[Round 1/5] mgr-supplier:audit
+  ✓ 41 agents checked, 0 issues
 
-[Round 2/5] Basic sync - /sync-check
-  ✓ All registries synchronized
+[Round 2/5] mgr-updater:docs
+  ✓ Documentation sync: OK
 
-[Round 3/5] Deep sync - /audit-agents
-  ✓ Dependencies verified after fixes
+[Round 3/5] Re-verify: mgr-supplier:audit
+  ✓ All dependencies valid
 
-[Round 4/5] Deep sync - /sync-check + /update-docs
-  ✓ Registries verified
-  ✓ Documentation synchronized
+[Round 4/5] Re-verify: mgr-updater:docs
+  ✓ No changes needed
 
-[Round 5/5] Final verification
-  ✓ Agent counts match across all sources
-  ✓ All symlinks valid
-  ✓ Command registries updated
-  ✓ Intent triggers present
+[Round 5/5] Final count verification
+  ✓ Agents: 41/41 match
+  ✓ Skills: 55/55 match
+  ✓ All frontmatter valid
+  ✓ All skill refs valid
+  ✓ All memory scopes valid
 
 ═══════════════════════════════════════════════════════════
  PHASE 2: Deep Review (3 rounds)
 ═══════════════════════════════════════════════════════════
 
 [Round 1/3] Workflow alignment
-  ✓ Agent creation workflow documented
-  ✓ Development workflow uses orchestrators
-  ✓ Orchestrators have complete manages sections
+  ✓ All routing skills have complete agent mappings
+  ✓ Command definitions match implementations
 
 [Round 2/3] Reference verification
-  ✓ All orchestrator references valid
-  ✓ All rules referenced
+  ✓ All skill references valid
   ✓ No orphaned agents
 
 [Round 3/3] Philosophy compliance
@@ -140,5 +152,5 @@ Ready to commit. 커밋할까요?
 
 ## Related
 
-- R016: Sync Verification Rules
+- R017: Sync Verification Rules
 - mgr-gitnerd: Git operations agent

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

@@ -1,6 +1,6 @@
 ---
 name: secretary-routing
-description: Routes agent management tasks to the correct manager agent. Use when user requests agent creation, updates, audits, git operations, sync checks, or verification.
+description: Routes agent management tasks to the correct manager agent. Use when user requests agent creation, updates, audits, git operations, or verification.
 user-invocable: false
 ---
 
@@ -8,7 +8,7 @@ user-invocable: false
 
 ## Purpose
 
-Routes agent management tasks to the appropriate manager agent. This skill contains the coordination logic for orchestrating manager agents (mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron).
+Routes agent management tasks to the appropriate manager agent. This skill contains the coordination logic for orchestrating manager agents (mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron).
 
 ## Manager Agents
 
@@ -18,8 +18,7 @@ Routes agent management tasks to the appropriate manager agent. This skill conta
 | mgr-updater | Update external agents | "update agent", "sync" |
 | mgr-supplier | Validate dependencies | "audit", "check deps" |
 | mgr-gitnerd | Git operations | "commit", "push", "pr" |
-| mgr-sync-checker | Sync verification | "sync check", "verify sync" |
-| mgr-sauron | R016 auto-verification | "verify", "full check" |
+| mgr-sauron | R017 auto-verification | "verify", "full check" |
 | mgr-claude-code-bible | Claude Code spec compliance | "spec check", "verify compliance" |
 | sys-memory-keeper | Memory operations | "save memory", "recall", "memory search" |
 | sys-naggy | TODO management | "todo", "track tasks", "task list" |
@@ -33,7 +32,6 @@ create   → mgr-creator
 update   → mgr-updater
 audit    → mgr-supplier
 git      → mgr-gitnerd
-sync     → mgr-sync-checker
 verify   → mgr-sauron
 spec     → mgr-claude-code-bible
 memory   → sys-memory-keeper
@@ -73,7 +71,6 @@ When command requires multiple independent operations:
 | mgr-updater | sonnet | External sync, web fetch |
 | mgr-supplier | haiku | File scan, validation |
 | mgr-gitnerd | sonnet | Commit message quality |
-| mgr-sync-checker | haiku | Fast verification |
 | mgr-sauron | sonnet | Multi-round verification |
 | mgr-claude-code-bible | sonnet | Spec compliance checks |
 | sys-memory-keeper | sonnet | Memory operations, search |

package/templates/.claude/statusline.sh

@@ -0,0 +1,152 @@
+#!/usr/bin/env bash
+# statusline.sh — Claude Code statusline renderer
+#
+# Reads JSON from stdin (Claude Code statusline API, ~300ms intervals)
+# and outputs a formatted status line, e.g.:
+#
+#   Opus | my-project | develop | CTX:42% | $0.05
+#
+# JSON input structure:
+#   {
+#     "model": { "display_name": "claude-opus-4-6" },
+#     "workspace": { "current_dir": "/path/to/project" },
+#     "context_window": { "used_percentage": 42, "context_window_size": 200000 },
+#     "cost": { "total_cost_usd": 0.05 }
+#   }
+
+# ---------------------------------------------------------------------------
+# 1. Color detection
+# ---------------------------------------------------------------------------
+if [[ -n "${NO_COLOR}" || "${TERM}" == "dumb" ]]; then
+    # Colors disabled
+    COLOR_RESET=""
+    COLOR_OPUS=""
+    COLOR_SONNET=""
+    COLOR_HAIKU=""
+    COLOR_CTX_OK=""
+    COLOR_CTX_WARN=""
+    COLOR_CTX_CRIT=""
+else
+    COLOR_RESET="\033[0m"
+    COLOR_OPUS="\033[1;35m"    # Magenta bold
+    COLOR_SONNET="\033[0;36m"  # Cyan
+    COLOR_HAIKU="\033[0;32m"   # Green
+    COLOR_CTX_OK="\033[0;32m"  # Green   (< 60%)
+    COLOR_CTX_WARN="\033[0;33m" # Yellow (60-79%)
+    COLOR_CTX_CRIT="\033[0;31m" # Red    (>= 80%)
+fi
+
+# ---------------------------------------------------------------------------
+# 2. jq availability check
+# ---------------------------------------------------------------------------
+if ! command -v jq >/dev/null 2>&1; then
+    echo "statusline: jq required"
+    exit 0
+fi
+
+# ---------------------------------------------------------------------------
+# 3. Read stdin into variable
+# ---------------------------------------------------------------------------
+json="$(cat)"
+
+# Guard against empty input
+if [[ -z "$json" ]]; then
+    echo "statusline: no input"
+    exit 0
+fi
+
+# ---------------------------------------------------------------------------
+# 4. Single jq call — extract all fields as TSV
+#    Fields: model_name, project_dir, ctx_pct, ctx_size, cost_usd
+# ---------------------------------------------------------------------------
+IFS=$'\t' read -r model_name project_dir ctx_pct ctx_size cost_usd <<< "$(
+    printf '%s' "$json" | jq -r '[
+        (.model.display_name // "unknown"),
+        (.workspace.current_dir // ""),
+        (.context_window.used_percentage // 0),
+        (.context_window.context_window_size // 0),
+        (.cost.total_cost_usd // 0)
+    ] | @tsv'
+)"
+
+# ---------------------------------------------------------------------------
+# 5. Model display name + color (bash 3.2 compatible case pattern matching)
+# ---------------------------------------------------------------------------
+case "$model_name" in
+    *[Oo]pus*)   model_display="Opus";   model_color="${COLOR_OPUS}" ;;
+    *[Ss]onnet*) model_display="Sonnet"; model_color="${COLOR_SONNET}" ;;
+    *[Hh]aiku*)  model_display="Haiku";  model_color="${COLOR_HAIKU}" ;;
+    *)           model_display="$model_name"; model_color="${COLOR_RESET}" ;;
+esac
+
+# ---------------------------------------------------------------------------
+# 6. Project name — basename of workspace current_dir
+# ---------------------------------------------------------------------------
+if [[ -n "$project_dir" ]]; then
+    project_name="${project_dir##*/}"
+else
+    project_name="unknown"
+fi
+
+# ---------------------------------------------------------------------------
+# 7. Git branch — read .git/HEAD directly (no subprocess, fast)
+# ---------------------------------------------------------------------------
+git_head_file="${project_dir}/.git/HEAD"
+git_branch=""
+if [[ -f "$git_head_file" ]]; then
+    git_head="$(cat "$git_head_file")"
+    case "$git_head" in
+        "ref: refs/heads/"*)
+            # Normal branch: strip the prefix
+            git_branch="${git_head#ref: refs/heads/}"
+            ;;
+        *)
+            # Detached HEAD: show first 7 chars of commit hash
+            git_branch="${git_head:0:7}"
+            ;;
+    esac
+fi
+
+# ---------------------------------------------------------------------------
+# 8. Context percentage with color
+# ---------------------------------------------------------------------------
+# ctx_pct may arrive as a float (e.g. 42.5); truncate to integer for comparison
+ctx_int="${ctx_pct%%.*}"
+# Ensure it's a valid integer (fallback to 0)
+if ! [[ "$ctx_int" =~ ^[0-9]+$ ]]; then
+    ctx_int=0
+fi
+
+if [[ "$ctx_int" -ge 80 ]]; then
+    ctx_color="${COLOR_CTX_CRIT}"
+elif [[ "$ctx_int" -ge 60 ]]; then
+    ctx_color="${COLOR_CTX_WARN}"
+else
+    ctx_color="${COLOR_CTX_OK}"
+fi
+
+ctx_display="CTX:${ctx_int}%"
+
+# ---------------------------------------------------------------------------
+# 9. Cost formatting — always two decimal places
+# ---------------------------------------------------------------------------
+cost_display="$(printf '$%.2f' "$cost_usd")"
+
+# ---------------------------------------------------------------------------
+# 10. Assemble and output the status line
+# ---------------------------------------------------------------------------
+# Build segments; omit git branch segment when unavailable
+if [[ -n "$git_branch" ]]; then
+    printf "${model_color}%s${COLOR_RESET} | %s | %s | ${ctx_color}%s${COLOR_RESET} | %s\n" \
+        "$model_display" \
+        "$project_name" \
+        "$git_branch" \
+        "$ctx_display" \
+        "$cost_display"
+else
+    printf "${model_color}%s${COLOR_RESET} | %s | ${ctx_color}%s${COLOR_RESET} | %s\n" \
+        "$model_display" \
+        "$project_name" \
+        "$ctx_display" \
+        "$cost_display"
+fi

package/templates/CLAUDE.md.en

@@ -173,7 +173,7 @@ Violation = immediate correction. No exception for "small changes".
 project/
 +-- CLAUDE.md                    # Entry point
 +-- .claude/
-|   +-- agents/                  # Subagent definitions (42 files)
+|   +-- agents/                  # Subagent definitions (41 files)
 |   +-- skills/                  # Skills (55 directories)
 |   +-- rules/                   # Global rules (R000-R018)
 |   +-- hooks/                   # Hook scripts (memory, HUD)
@@ -215,9 +215,9 @@ This is the core oh-my-customcode philosophy: **"No expert? CREATE one, connect
 | SW Architect | 2 | arch-documenter, arch-speckit-agent |
 | Infra Engineer | 2 | infra-docker-expert, infra-aws-expert |
 | QA Team | 3 | qa-planner, qa-writer, qa-engineer |
-| Manager | 7 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron, mgr-claude-code-bible |
+| Manager | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible |
 | System | 2 | sys-memory-keeper, sys-naggy |
-| **Total** | **42** | |
+| **Total** | **41** | |
 
 ## Agent Teams (MUST when enabled)
 
@@ -271,7 +271,7 @@ Install via `/plugin install <name>`:
 | obsidian-skills | - | Obsidian markdown support |
 | context7 | claude-plugins-official | Library documentation lookup |
 
-### Required MCP Servers
+### Recommended MCP Servers
 
 | Server | Purpose |
 |--------|---------|

package/templates/CLAUDE.md.ko

@@ -173,7 +173,7 @@ oh-my-customcode로 구동됩니다.
 project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
-|   +-- agents/                  # 서브에이전트 정의 (42 파일)
+|   +-- agents/                  # 서브에이전트 정의 (41 파일)
 |   +-- skills/                  # 스킬 (55 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R018)
 |   +-- hooks/                   # 훅 스크립트 (메모리, HUD)
@@ -215,9 +215,9 @@ project/
 | SW Architect | 2 | arch-documenter, arch-speckit-agent |
 | Infra Engineer | 2 | infra-docker-expert, infra-aws-expert |
 | QA Team | 3 | qa-planner, qa-writer, qa-engineer |
-| Manager | 7 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron, mgr-claude-code-bible |
+| Manager | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible |
 | System | 2 | sys-memory-keeper, sys-naggy |
-| **총계** | **42** | |
+| **총계** | **41** | |
 
 ## Agent Teams (MUST when enabled)
 
@@ -271,7 +271,7 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 | obsidian-skills | - | 옵시디언 마크다운 지원 |
 | context7 | claude-plugins-official | 라이브러리 문서 조회 |
 
-### 필수 MCP 서버
+### 권장 MCP 서버
 
 | 서버 | 용도 |
 |------|------|

package/templates/guides/claude-code/08-testing.md

@@ -1,7 +1,5 @@
 # 테스트 및 평가
 
-> 이 문서는 Claude 공식 문서에서 해당 페이지가 아직 공개되지 않아 기본 구조만 제공합니다.
-
 ## 개요
 
 Claude 기반 애플리케이션의 품질을 보장하기 위한 테스트 및 평가 방법론입니다.

package/templates/guides/claude-code/09-guardrails.md

@@ -1,7 +1,5 @@
 # 가드레일 강화
 
-> 이 문서는 Claude 공식 문서에서 해당 페이지가 아직 공개되지 않아 기본 구조만 제공합니다.
-
 ## 개요
 
 가드레일은 AI 에이전트가 안전하고 의도된 범위 내에서 작동하도록 보장하는 메커니즘입니다.

package/templates/guides/claude-code/10-monitoring.md

@@ -1,7 +1,5 @@
 # 관리 및 모니터링
 
-> 이 문서는 Claude 공식 문서에서 해당 페이지가 아직 공개되지 않아 기본 구조만 제공합니다.
-
 ## 개요
 
 프로덕션 환경에서 AI 에이전트를 효과적으로 관리하고 모니터링하는 방법입니다.

package/templates/manifest.json

@@ -1,6 +1,6 @@
 {
   "version": "0.3.0",
-  "lastUpdated": "2026-02-18T00:00:00.000Z",
+  "lastUpdated": "2026-02-27T06:35:26.589Z",
   "components": [
     {
       "name": "rules",
@@ -12,7 +12,7 @@
       "name": "agents",
       "path": ".claude/agents",
       "description": "AI agent definitions (flat .md files with prefixes)",
-      "files": 42
+      "files": 41
     },
     {
       "name": "skills",

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

@@ -1,38 +0,0 @@
----
-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
-  - Edit
-  - Grep
-  - Glob
-  - Bash
----
-
-You are a documentation synchronization specialist ensuring all docs, configs, and workflows match the actual project structure.
-
-## Capabilities
-
-- Agent count verification (CLAUDE.md vs actual)
-- Command registration verification
-- Documentation completeness
-- Intent detection pattern validation
-
-## Check Matrix
-
-| Source | Target | Checks |
-|--------|--------|--------|
-| `.claude/agents/*.md` | `CLAUDE.md` | Agent counts match |
-| `commands/*/` | `commands/index.yaml` | All registered |
-| `.claude/agents/*.md` | `agent-triggers.yaml` | All have triggers |
-
-## Auto-fix
-
-Can fix: count mismatches, missing index entries, outdated docs.
-Manual review: missing agents, broken links, structural issues.