creating-an-agent

# Creating an Agent

**REQUIRED BACKGROUND:** Read ed3d-extending-claude:writing-claude-directives for foundational guidance on token efficiency, compliance techniques, and directive structure. This skill focuses on agent-specific patterns.

## What is an Agent?

An **agent** is a specialized Claude instance with:
- Defined tools (Read, Edit, Bash, etc.)
- Specific responsibilities (code review, security audit, research)
- A focused system prompt

Agents are spawned via the Task tool or defined in plugin `agents/` directories.

## When to Create an Agent

**Create when:**
- Task requires specialized expertise
- Workflow benefits from tool restrictions
- You want consistent behavior across invocations
- Task is complex enough to warrant context isolation

**Don't create for:**
- Simple, one-off tasks
- Tasks the main Claude handles well
- Purely conversational interactions

## Agent File Structure

```
agents/
  my-agent.md
```

**Template:**
```markdown
---
name: agent-name
description: Use when [specific triggers] - [what agent does]
tools: Read, Grep, Glob, Bash
model: sonnet
---

# Agent Name

[Agent system prompt - who they are, what they do]

## Responsibilities
- Task 1
- Task 2

## Workflow
1. Step 1
2. Step 2
```

## Description: The Critical Field

The `description` field determines when Claude auto-delegates to your agent. It's searched when matching tasks to available agents.

### Writing Effective Descriptions

**Format:** "Use when [specific triggers/symptoms] - [what the agent does]"

**Write in third person.** Injected into system prompt.

```yaml
# Bad: vague, no triggers
description: Helps with code

# Bad: first person
description: I review code for security issues

# Good: specific triggers + action
description: Use when reviewing code for security vulnerabilities, analyzing authentication flows, or checking for common security anti-patterns like SQL injection, XSS, or insecure dependencies
```

**Include:**
- Specific symptoms that trigger use
-