sub-agent-creator

# Sub-Agent Creator

Automates creation of Claude Code sub-agents with proper configuration and proactive behavior.

## When to Use

**Trigger Phrases**:
- "create a sub-agent for [purpose]"
- "generate a new sub-agent"
- "set up a sub-agent to handle [task]"
- "make a proactive agent that [behavior]"

**Use Cases**:
- Domain-specific agents (code reviewer, debugger)
- Proactive agents that auto-trigger on patterns
- Security-sensitive agents with limited tools
- Team-shared project-level agents

## Workflow (6-Step Agent Creation Architect)

Follow this structured process for consistent, high-quality agents:

### Step 1: Extract Core Intent
Identify what the agent should accomplish:
- **Single responsibility**: What ONE thing does this agent do?
- **Trigger conditions**: When should Claude invoke this agent?
- **Success criteria**: How do we know the agent succeeded?

```markdown
Example:
- Intent: Review code for security vulnerabilities
- Trigger: Security-related requests, audit requests
- Success: Findings reported with confidence scores
```

### Step 2: Design Expert Persona
Define the expertise the agent embodies:
- **Domain expertise**: What knowledge domain? (security, testing, DevOps)
- **Perspective**: Cautious? Thorough? Fast? Pragmatic?
- **Communication style**: Terse? Educational? Actionable?

```markdown
Example:
- Persona: Senior security engineer with penetration testing background
- Perspective: Cautious, assumes hostile input
- Style: Concise findings with exploit paths
```

### Step 3: Architect Instructions
Structure capabilities and constraints:
- **PROHIBITED** operations first (what it CANNOT do)
- **ALLOWED** operations second (what it CAN do)
- **Output format** specification
- **Edge case handling**

```markdown
Structure order:
1. Prohibitions (safety rails)
2. Capabilities (what it does)
3. Output format (structured response)
4. Examples (when to use / when NOT)
```

### Step 4: Optimize for Token Efficiency
Reduce prompt size without l