oh-my-customcode 0.1.2 → 0.1.4

package/README.md

@@ -14,7 +14,8 @@ Like oh-my-zsh transformed shell customization, oh-my-customcode makes personali
 
 | Feature | Description |
 |---------|-------------|
-| **Batteries Included** | 36 agents, 17 skills, 18 rules - ready to use out of the box |
+| **Batteries Included** | 37 agents, 17 skills, 12 guides - synced with baekgom-agents templates |
+| **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 |
 | **Non-Destructive** | Your customizations live alongside defaults, never overwritten |
@@ -27,7 +28,7 @@ npm install -g oh-my-customcode
 
 # Initialize in your project
 cd your-project
-omcc init
+omcustom init
 ```
 
 That's it. You now have a fully configured Claude Code environment.
@@ -183,36 +184,48 @@ your-project/
 
 ## What's Included
 
-### Agents (36)
-
-| Category | Agents |
-|----------|--------|
-| Orchestrators | planner, secretary, dev-lead, qa-lead |
-| Managers | creator, updater, supplier, gitnerd, sync-checker, sauron |
-| System | memory-keeper, naggy |
-| Languages | golang, python, rust, kotlin, typescript, java21 |
-| Frontend | vercel-agent, vuejs-agent, svelte-agent |
-| Backend | fastapi, springboot, go-backend, express, nestjs |
-| Tooling | npm-expert, optimizer, bun-expert |
-| Architecture | documenter, speckit-agent |
-| Infrastructure | docker-expert, aws-expert |
-| QA | qa-planner, qa-writer, qa-engineer |
+> **Templates synced from [baekgom-agents](https://github.com/baekenough/baekgom-agents)** - Battle-tested agent system with sub-agent orchestration support.
+
+### Agents (37)
+
+| Category | Count | Agents |
+|----------|-------|--------|
+| **Orchestrators** | 4 | planner, secretary, dev-lead, qa-lead |
+| **Managers** | 6 | creator, updater, supplier, gitnerd, sync-checker, sauron |
+| **System** | 2 | memory-keeper, naggy |
+| **Languages** | 6 | golang, python, rust, kotlin, typescript, java21 |
+| **Frontend** | 3 | vercel-agent, vuejs-agent, svelte-agent |
+| **Backend** | 5 | fastapi, springboot, go-backend, express, nestjs |
+| **Tooling** | 3 | npm-expert, optimizer, bun-expert |
+| **Architecture** | 2 | documenter, speckit-agent |
+| **Infrastructure** | 2 | docker-expert, aws-expert |
+| **QA** | 3 | qa-planner, qa-writer, qa-engineer |
+| **Tutor** | 1 | go-tutor |
+| **Total** | **37** | |
 
 ### Skills (17)
 
-- **Development**: Go, Python, TypeScript, Kotlin, Rust, Java, React, Vercel
-- **Backend**: FastAPI, Spring Boot, Express, NestJS, Go Backend
-- **Infrastructure**: Docker, AWS
-- **System**: Memory management, result aggregation
-- **Orchestration**: Pipeline execution, intent detection
+- **Development** (8): Go, Python, TypeScript, Kotlin, Rust, Java, React, Vercel
+- **Backend** (5): FastAPI, Spring Boot, Express, NestJS, Go Backend
+- **Infrastructure** (2): Docker, AWS
+- **System** (2): Memory management, result aggregation
+- **Orchestration** (2): Pipeline execution, intent detection
+
+### Guides (12)
+
+Comprehensive reference documentation covering:
+- Agent creation and management
+- Skill development
+- Pipeline workflows
+- Best practices and patterns
 
 ### Rules (18)
 
 | Priority | Count | Purpose |
 |----------|-------|---------|
-| MUST | 10 | Safety, permissions, agent design (enforced) |
-| SHOULD | 6 | Interactions, error handling (recommended) |
-| MAY | 2 | Optimization guidelines (optional) |
+| **MUST** | 10 | Safety, permissions, agent design (enforced) |
+| **SHOULD** | 6 | Interactions, error handling (recommended) |
+| **MAY** | 2 | Optimization guidelines (optional) |
 
 ---
 
@@ -220,19 +233,19 @@ your-project/
 
 | Command | Description |
 |---------|-------------|
-| `omcc init` | Initialize in current project |
-| `omcc init --lang ko` | Initialize with Korean language |
-| `omcc update` | Update to latest version |
-| `omcc list` | List all installed components |
-| `omcc list agents` | List agents only |
-| `omcc doctor` | Verify installation health |
-| `omcc doctor --fix` | Auto-fix common issues |
+| `omcustom init` | Initialize in current project |
+| `omcustom init --lang ko` | Initialize with Korean language |
+| `omcustom update` | Update to latest version |
+| `omcustom list` | List all installed components |
+| `omcustom list agents` | List agents only |
+| `omcustom doctor` | Verify installation health |
+| `omcustom doctor --fix` | Auto-fix common issues |
 
 ---
 
 ## Project Structure
 
-After `omcc init`:
+After `omcustom init`:
 
 ```
 your-project/

package/dist/cli/index.js

@@ -11450,7 +11450,7 @@ var en_default = {
   cli: {
     description: "Batteries-included agent harness for Claude Code",
     versionOption: "Show version number",
-    usage: "Usage: omcc <command> [options]",
+    usage: "Usage: omcustom <command> [options]",
     commands: "Commands",
     options: "Options",
     examples: "Examples",
@@ -11472,7 +11472,7 @@ var en_default = {
       symlinking: "Creating symlinks...",
       verifying: "Verifying installation...",
       success: "Successfully initialized oh-my-customcode!",
-      verificationFailed: "Installation verification failed. Run 'omcc doctor' for details.",
+      verificationFailed: "Installation verification failed. Run 'omcustom doctor' for details.",
       failed: "Failed to initialize:",
       alreadyInitialized: "oh-my-customcode is already initialized in this directory",
       configCreated: "Configuration created at {{path}}",
@@ -11488,7 +11488,7 @@ var en_default = {
       description: "Update agents and configurations to latest version",
       checking: "Checking for updates...",
       notInstalled: "oh-my-customcode is not installed in this directory.",
-      runInitFirst: "Run 'omcc init' first to install.",
+      runInitFirst: "Run 'omcustom init' first to install.",
       alreadyLatest: "Already at the latest version.",
       updating: "Updating from {{from}} to {{to}}...",
       success: "Successfully updated to the latest version!",
@@ -11537,7 +11537,7 @@ var en_default = {
       fixed: "{{name}} has been fixed",
       passed: "All checks passed!",
       failed: "Some checks failed.",
-      runWithFix: "Run 'omcc doctor --fix' to fix {{count}} issue(s) automatically.",
+      runWithFix: "Run 'omcustom doctor --fix' to fix {{count}} issue(s) automatically.",
       summary: "Summary: {{pass}} passed, {{warn}} warnings, {{fail}} failed, {{fixed}} fixed",
       running: "Running health checks...",
       checkingConfig: "Checking configuration...",
@@ -11697,7 +11697,7 @@ var ko_default = {
   cli: {
     description: "Claude Code를 위한 올인원 에이전트 하네스",
     versionOption: "버전 번호 표시",
-    usage: "사용법: omcc <명령어> [옵션]",
+    usage: "사용법: omcustom <명령어> [옵션]",
     commands: "명령어",
     options: "옵션",
     examples: "예제",
@@ -11719,7 +11719,7 @@ var ko_default = {
       symlinking: "심볼릭 링크 생성 중...",
       verifying: "설치 확인 중...",
       success: "oh-my-customcode 초기화 완료!",
-      verificationFailed: "설치 확인 실패. 'omcc doctor'를 실행하여 자세한 내용을 확인하세요.",
+      verificationFailed: "설치 확인 실패. 'omcustom doctor'를 실행하여 자세한 내용을 확인하세요.",
       failed: "초기화 실패:",
       alreadyInitialized: "이 디렉토리에 oh-my-customcode가 이미 초기화되어 있습니다",
       configCreated: "설정 파일 생성됨: {{path}}",
@@ -11735,7 +11735,7 @@ var ko_default = {
       description: "에이전트 및 설정을 최신 버전으로 업데이트",
       checking: "업데이트 확인 중...",
       notInstalled: "이 디렉토리에 oh-my-customcode가 설치되어 있지 않습니다.",
-      runInitFirst: "먼저 'omcc init'을 실행하여 설치하세요.",
+      runInitFirst: "먼저 'omcustom init'을 실행하여 설치하세요.",
       alreadyLatest: "이미 최신 버전입니다.",
       updating: "{{from}}에서 {{to}}로 업데이트 중...",
       success: "최신 버전으로 업데이트 완료!",
@@ -11784,7 +11784,7 @@ var ko_default = {
       fixed: "{{name}}이(가) 수정되었습니다",
       passed: "모든 검사 통과!",
       failed: "일부 검사 실패.",
-      runWithFix: "'omcc doctor --fix'를 실행하여 {{count}}개 문제를 자동으로 수정할 수 있습니다.",
+      runWithFix: "'omcustom doctor --fix'를 실행하여 {{count}}개 문제를 자동으로 수정할 수 있습니다.",
       summary: "요약: {{pass}}개 통과, {{warn}}개 경고, {{fail}}개 실패, {{fixed}}개 수정됨",
       running: "상태 검사 실행 중...",
       checkingConfig: "설정 확인 중...",
@@ -12034,10 +12034,6 @@ async function isDirectory(targetPath) {
 }
 async function isValidSymlink(symlinkPath) {
   try {
-    const stat = await fs.lstat(symlinkPath);
-    if (!stat.isSymbolicLink()) {
-      return true;
-    }
     await fs.stat(symlinkPath);
     return true;
   } catch {
@@ -12096,12 +12092,8 @@ async function findRefsSymlinks(dir2) {
   return results;
 }
 async function countDirectories(dirPath) {
-  try {
-    const entries = await fs.readdir(dirPath, { withFileTypes: true });
-    return entries.filter((e) => e.isDirectory()).length;
-  } catch {
-    return 0;
-  }
+  const entries = await fs.readdir(dirPath, { withFileTypes: true });
+  return entries.filter((e) => e.isDirectory()).length;
 }
 async function countAgentsInTypeDir(typePath) {
   let count = 0;
@@ -12741,7 +12733,7 @@ function success(messageKey, params) {
 
 // src/core/config.ts
 import { join as join2 } from "node:path";
-var CONFIG_FILE = ".omccrc.json";
+var CONFIG_FILE = ".omcustomrc.json";
 var CURRENT_CONFIG_VERSION = 1;
 function getDefaultConfig() {
   return {
@@ -13525,7 +13517,7 @@ var require2 = createRequire2(import.meta.url);
 var packageJson = require2("../../package.json");
 function createProgram() {
   const program2 = new Command;
-  program2.name("omcc").description(i18n.t("cli.description")).version(packageJson.version, "-v, --version", i18n.t("cli.versionOption"));
+  program2.name("omcustom").description(i18n.t("cli.description")).version(packageJson.version, "-v, --version", i18n.t("cli.versionOption"));
   program2.command("init").description(i18n.t("cli.init.description")).option("-l, --lang <language>", i18n.t("cli.init.langOption"), "en").action(async (options) => {
     await initCommand(options);
   });

package/dist/index.js

@@ -324,7 +324,7 @@ function success(messageKey, params) {
 }
 
 // src/core/config.ts
-var CONFIG_FILE = ".omccrc.json";
+var CONFIG_FILE = ".omcustomrc.json";
 var CURRENT_CONFIG_VERSION = 1;
 function getDefaultConfig() {
   return {
@@ -684,7 +684,7 @@ async function backupExistingInstallation(targetDir) {
 }
 // src/core/updater.ts
 import { join as join4 } from "node:path";
-var CUSTOMIZATION_MANIFEST_FILE = ".omcc-customizations.json";
+var CUSTOMIZATION_MANIFEST_FILE = ".omcustom-customizations.json";
 function createUpdateResult() {
   return {
     success: false,
@@ -862,7 +862,7 @@ function getComponentPath(component) {
 }
 async function backupInstallation(targetDir) {
   const timestamp = new Date().toISOString().replace(/[:.]/g, "-");
-  const backupDir = join4(targetDir, `.omcc-backup-${timestamp}`);
+  const backupDir = join4(targetDir, `.omcustom-backup-${timestamp}`);
   const fs = await import("node:fs/promises");
   await ensureDirectory(backupDir);
   const dirsToBackup = [".claude", "agents", "skills", "guides", "pipelines", "commands"];

package/package.json

@@ -1,10 +1,10 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {
-    "omcc": "./dist/cli/index.js"
+    "omcustom": "./dist/cli/index.js"
   },
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",

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

@@ -226,6 +226,74 @@ CORRECT:
 | memory-keeper | agents/system/memory-keeper/ | Memory operations |
 | naggy | agents/system/naggy/ | TODO management |
 
+## CRITICAL: Use Specialized Expert Agents for Code Work
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  CODE WORK MUST USE SPECIALIZED EXPERT AGENTS                    ║
+║                                                                   ║
+║  Language/Framework           → Required Agent                   ║
+║  ─────────────────────────────────────────────────               ║
+║  Python/FastAPI backend       → python-expert or fastapi-expert  ║
+║  TypeScript/Next.js frontend  → typescript-expert or vercel-agent║
+║  Go code                      → golang-expert                    ║
+║  Kotlin/Spring                → kotlin-expert or springboot-expert║
+║                                                                   ║
+║  WRONG:                                                          ║
+║    secretary → Task(general-purpose) → writes Python code        ║
+║                                                                   ║
+║  CORRECT:                                                        ║
+║    secretary → Task(python-expert) → writes Python code          ║
+║                                                                   ║
+║  general-purpose should ONLY be used when:                       ║
+║  - No specialized agent exists for the task                      ║
+║  - Task is truly generic (file moves, simple scripts)            ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
+## CRITICAL: Sub-agent Model Specification
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  TASK TOOL MODEL PARAMETER (RECOMMENDED)                         ║
+║                                                                   ║
+║  Claude Code Task tool supports `model` parameter to specify     ║
+║  which model the sub-agent should use.                           ║
+║                                                                   ║
+║  Available models:                                                ║
+║    - opus   : Complex reasoning, architecture design             ║
+║    - sonnet : Balanced performance (default)                     ║
+║    - haiku  : Fast, simple tasks, file search                    ║
+║    - inherit: Use parent conversation's model                    ║
+║                                                                   ║
+║  Usage:                                                          ║
+║    Task(                                                         ║
+║      subagent_type: "general-purpose",                           ║
+║      prompt: "Analyze architecture",                             ║
+║      model: "opus"                                               ║
+║    )                                                             ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
+### Model Selection by Task Type
+
+| Task Type | Recommended Model | Reason |
+|-----------|-------------------|--------|
+| Architecture analysis | `opus` | Deep reasoning required |
+| Code review | `opus` or `sonnet` | Quality judgment |
+| Code implementation | `sonnet` | Balanced performance |
+| File search/read | `haiku` | Fast, simple operation |
+| Simple validation | `haiku` | Low latency |
+
+### Model Selection by Agent Type
+
+| Agent Category | Model | Examples |
+|----------------|-------|----------|
+| Orchestrator judgment | `opus` | Complex routing decisions |
+| Manager agents | `sonnet` | creator, updater, supplier |
+| Simple utilities | `haiku` | File operations, search |
+| Expert agents | `sonnet` | golang-expert, python-expert |
+
 ## CRITICAL: Git Operations Delegation
 
 ```

package/templates/.claude/rules/MUST-parallel-execution.md

@@ -178,6 +178,41 @@ requirements:
   - Each instance has isolated context
 ```
 
+### 4. Model Specification (RECOMMENDED)
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  USE MODEL PARAMETER FOR COST/PERFORMANCE OPTIMIZATION           ║
+║                                                                   ║
+║  Task tool supports `model` parameter:                           ║
+║                                                                   ║
+║    Task(                                                         ║
+║      subagent_type: "general-purpose",                           ║
+║      prompt: "...",                                              ║
+║      model: "haiku"  ← Specify model                             ║
+║    )                                                             ║
+║                                                                   ║
+║  Model Selection:                                                ║
+║    - opus   : Complex reasoning (expensive, powerful)            ║
+║    - sonnet : General tasks (default, balanced)                  ║
+║    - haiku  : Simple tasks (fast, cheap)                         ║
+║                                                                   ║
+║  Parallel Task Optimization:                                     ║
+║    - Use haiku for file search/validation tasks                  ║
+║    - Use sonnet for code generation tasks                        ║
+║    - Use opus only when deep reasoning is required               ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
+Example with model specification:
+```
+# Parallel tasks with appropriate models
+Task(prompt: "Search for auth files", model: "haiku")      ┐
+Task(prompt: "Implement feature A", model: "sonnet")       ├─ Optimized
+Task(prompt: "Implement feature B", model: "sonnet")       │
+Task(prompt: "Analyze architecture", model: "opus")        ┘
+```
+
 ## Instance Model
 
 ### Instantiation
@@ -310,7 +345,7 @@ requirements:
 
 ## Display Format
 
-When parallel execution occurs:
+When parallel execution occurs, MUST display `{task-name}:{model}` format:
 
 ```
 ┌─ Agent: secretary (orchestrator)
@@ -318,21 +353,43 @@ When parallel execution occurs:
 
 [Parallel] Spawning 4 instances...
 
-[Instance 1] creator → golang-expert
-[Instance 2] creator → python-expert
-[Instance 3] creator → rust-expert
-[Instance 4] creator → typescript-expert
+[Instance 1] creator-golang:sonnet → golang-expert
+[Instance 2] creator-python:sonnet → python-expert
+[Instance 3] creator-rust:sonnet → rust-expert
+[Instance 4] creator-typescript:sonnet → typescript-expert
 
 [Progress] ████████░░░░ 2/4
 
-[Instance 1] ✓ golang-expert created
-[Instance 2] ✓ python-expert created
-[Instance 3] ✓ rust-expert created
-[Instance 4] ✓ typescript-expert created
+[Instance 1] creator-golang:sonnet ✓ golang-expert created
+[Instance 2] creator-python:sonnet ✓ python-expert created
+[Instance 3] creator-rust:sonnet ✓ rust-expert created
+[Instance 4] creator-typescript:sonnet ✓ typescript-expert created
 
 [Summary] 4/4 tasks completed successfully
 ```
 
+### Display Format Rules
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  PARALLEL AGENT DISPLAY FORMAT (MANDATORY)                       ║
+║                                                                   ║
+║  When announcing parallel agents, MUST show:                     ║
+║                                                                   ║
+║    {task-name}:{model}                                           ║
+║                                                                   ║
+║  Examples:                                                       ║
+║    [Instance 1] readme-update:sonnet ✓ README updated            ║
+║    [Instance 2] code-review:haiku ✓ Review complete              ║
+║    [Instance 3] architecture:opus ✓ Analysis done                ║
+║                                                                   ║
+║  This allows users to:                                           ║
+║    - See which model is used for each task                       ║
+║    - Understand cost implications                                ║
+║    - Debug model selection issues                                ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
 ## Benefits
 
 1. **Throughput**: N tasks complete in ~1/N time

package/templates/.claude/rules/MUST-tool-identification.md

@@ -6,39 +6,99 @@
 
 ## CRITICAL
 
-**EVERY tool call MUST be prefixed with agent identification. This is NON-NEGOTIABLE.**
+**EVERY tool call MUST be prefixed with agent and model identification. This is NON-NEGOTIABLE.**
 
 ```
 Before EVERY tool call, output:
-[agent-name] → Tool: <tool-name>
-[agent-name] → Target: <file/path/url>
+[agent-name][model] → Tool: <tool-name>
+[agent-name][model] → Target: <file/path/url>
 ```
 
 Failure to identify tool usage = Rule violation = Must be corrected immediately.
 
+### Self-Check Before EVERY Tool Call
+
+```
+╔══════════════════════════════════════════════════════════════════╗
+║  BEFORE INVOKING ANY TOOL, ASK YOURSELF:                         ║
+║                                                                   ║
+║  1. Did I output the tool identification line with MODEL?        ║
+║     [agent-name][model] → Tool: <tool-name>                      ║
+║     [agent-name][model] → Target: <target>                       ║
+║                                                                   ║
+║  2. Am I about to call multiple tools in parallel?               ║
+║     → EACH tool needs its own identification line                ║
+║     → List all identifications BEFORE the tool calls             ║
+║                                                                   ║
+║  If NO to #1 → STOP. Output identification FIRST.                ║
+╚══════════════════════════════════════════════════════════════════╝
+```
+
+### Model Values
+
+| Model | When to Use |
+|-------|-------------|
+| `opus` | Complex reasoning, architecture design |
+| `sonnet` | General tasks, code generation (default) |
+| `haiku` | Fast simple tasks, file search |
+
+### Common Violations to Avoid
+
+```
+❌ WRONG: Calling tools without identification
+   "먼저 JD 내용을 확인하겠습니다."
+   <tool_call>WebFetch(...)</tool_call>
+
+❌ WRONG: Missing model in identification
+   [secretary] → Tool: WebFetch
+   [secretary] → Fetching: https://example.com/jd.md
+
+✓ CORRECT: Always identify with agent AND model
+   "먼저 JD 내용을 확인하겠습니다."
+   [secretary][opus] → Tool: WebFetch
+   [secretary][opus] → Fetching: https://example.com/jd.md
+   <tool_call>WebFetch(...)</tool_call>
+
+❌ WRONG: Parallel calls without listing all identifications
+   <tool_call>WebFetch(url1)</tool_call>
+   <tool_call>WebFetch(url2)</tool_call>
+   <tool_call>Bash(cmd)</tool_call>
+
+✓ CORRECT: List all identifications with models, then call
+   [secretary][opus] → Tool: WebFetch
+   [secretary][opus] → Fetching: url1
+   [secretary][opus] → Tool: WebFetch
+   [secretary][opus] → Fetching: url2
+   [secretary][opus] → Tool: Bash
+   [secretary][opus] → Running: cmd
+   <tool_call>WebFetch(url1)</tool_call>
+   <tool_call>WebFetch(url2)</tool_call>
+   <tool_call>Bash(cmd)</tool_call>
+```
+
 ## Purpose
 
 Display which agent is using which tool for transparency and debugging. This extends R007 (Agent Identification) to cover tool operations.
 
 ## Tool Usage Format
 
-When invoking a tool, prefix with agent identification:
+When invoking a tool, prefix with agent and model identification:
 
 ```
-[agent-name] → Tool: <tool-name>
+[agent-name][model] → Tool: <tool-name>
 ```
 
 ### Examples
 
 ```
-[golang-expert] → Tool: Read
-[golang-expert] → Reading: src/main.go
+[golang-expert][sonnet] → Tool: Read
+[golang-expert][sonnet] → Reading: src/main.go
 
-[supplier] → Tool: Glob
-[supplier] → Searching: agents/**/index.yaml
+[supplier][haiku] → Tool: Glob
+[supplier][haiku] → Searching: agents/**/index.yaml
 
-[creator] → Tool: Write
-[creator] → Writing: agents/sw-engineer/new-agent/AGENT.md
+[creator][sonnet] → Tool: Write
+[creator][sonnet] → Writing: agents/sw-engineer/new-agent/AGENT.md
 ```
 
 ## Extended Format (Verbose)
@@ -47,6 +107,7 @@ For detailed tracking:
 
 ```
 ┌─ Agent: golang-expert (sw-engineer)
+├─ Model: sonnet
 ├─ Skill: go-best-practices
 ├─ Tool: Read
 └─ Target: src/main.go
@@ -76,9 +137,9 @@ For detailed tracking:
 For inline operations:
 
 ```
-[supplier → Glob] agents/**/index.yaml
-[creator → Write] agents/sw-engineer/new-agent/AGENT.md
-[updater → WebFetch] https://github.com/...
+[supplier][haiku] → Glob: agents/**/index.yaml
+[creator][sonnet] → Write: agents/sw-engineer/new-agent/AGENT.md
+[updater][sonnet] → WebFetch: https://github.com/...
 ```
 
 ## Integration with R007
@@ -87,11 +148,12 @@ R008 extends R007 for tool operations:
 
 ```
 ┌─ Agent: creator (manager)
+├─ Model: sonnet
 └─ Task: Creating new agent
 
-[creator → Write] agents/sw-engineer/new-agent/AGENT.md
-[creator → Write] agents/sw-engineer/new-agent/index.yaml
-[creator → Edit] agents/index.yaml
+[creator][sonnet] → Write: agents/sw-engineer/new-agent/AGENT.md
+[creator][sonnet] → Write: agents/sw-engineer/new-agent/index.yaml
+[creator][sonnet] → Edit: agents/index.yaml
 
 [Done] Agent created successfully
 ```

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

@@ -28,6 +28,7 @@ Display real-time status information during agent operations for improved visibi
 | Component | Description | Example |
 |-----------|-------------|---------|
 | Agent | Active agent name | `golang-expert` |
+| Model | Model used (for parallel) | `sonnet` |
 | Progress | Task progress (current/total) | `2/5` |
 | Parallel | Parallel instance count | `3` |
 
@@ -39,10 +40,16 @@ Display real-time status information during agent operations for improved visibi
 ─── [Agent] creator | [Progress] 1/3 ───
 ```
 
-### With Parallel Execution
+### With Parallel Execution (Model Display REQUIRED)
 
 ```
 ─── [Agent] secretary | [Progress] 0/4 | [Parallel] 4 ───
+
+Instances:
+  [1] readme-update:sonnet
+  [2] code-review:haiku
+  [3] architecture:opus
+  [4] validation:haiku
 ```
 
 ### Completion

package/templates/agents/index.yaml

@@ -235,3 +235,9 @@ agents:
       source:
         type: internal
 
+  tutor:
+    - name: go-tutor
+      path: ./tutor/go-tutor/
+      description: Go + DS/Algorithms tutor for learn-go curriculum
+      source:
+        type: internal