oh-my-customcode 0.1.3 → 0.1.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.1.3",
+  "version": "0.1.4",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

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

@@ -251,6 +251,49 @@ CORRECT:
 ╚══════════════════════════════════════════════════════════════════╝
 ```
 
+## 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/manager/creator/refs/rules/MUST-orchestrator-coordination.md

@@ -251,6 +251,49 @@ CORRECT:
 ╚══════════════════════════════════════════════════════════════════╝
 ```
 
+## 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/agents/manager/creator/refs/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/agents/manager/creator/refs/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/agents/manager/creator/refs/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