agent-development

Agent Development for Claude Code Plugins

Overview

Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.

Key concepts:

• Agents are FOR autonomous work, commands are FOR user-initiated actions
• Markdown file format with YAML frontmatter
• Triggering via description field with examples
• System prompt defines agent behavior
• Model and color customization
• MCP servers can be scoped to subagents (inline) or shared from parent (string reference)

Agent File Structure

Complete Format

---
name: agent-identifier
description: Use this agent when [triggering conditions]. Examples:

<example>
Context: [Situation description]
user: "[User request]"
assistant: "[How assistant should respond and use this agent]"
<commentary>
[Why this agent should be triggered]
</commentary>
</example>

<example>
[Additional example...]
</example>

model: inherit
color: blue
tools: ["Read", "Write", "Grep"]
mcpServers:
  - playwright:
      type: stdio
      command: npx
      args: ["-y", "@playwright/mcp@latest"]
  - github
---

You are [agent role description]...

**Your Core Responsibilities:**
1. [Responsibility 1]
2. [Responsibility 2]

**Analysis Process:**
[Step-by-step workflow]

**Output Format:**
[What to return]

Frontmatter Fields

name (required)

Agent identifier used for namespacing and invocation.

Format: lowercase, numbers, hyphens only Length: 3-50 characters Pattern: Must start and end with alphanumeric

Good examples:

• code-reviewer
• test-generator
• api-docs-writer
• security-analyzer

Bad examples:

• helper (too generic)
• -agent- (starts/ends with hyphen)
• my_agent (underscores not allowed)
• ag (too short, < 3 chars)

description (required)

Defines when Claude should trigger this agent. This is the most critical field.

Must include:

1. Triggering conditions ("Use this agent when...")
2. Multiple <example> blocks showing usage
3. Context, user request, and assistant response in each example
4. <commentary> explaining why agent triggers

Format:

Use this agent when [conditions]. Examples:

<example>
Context: [Scenario description]
user: "[What user says]"
assistant: "[How Claude should respond]"
<commentary>
[Why this agent is appropriate]
</commentary>
</example>

[More examples...]

Best practices:

• Include 2-4 concrete examples
• Show proactive and reactive triggering
• Cover different phrasings of same intent
• Explain reasoning in commentary
• Be specific about when NOT to use the agent

model (required)

Which model the agent should use.

Options:

• inherit - Use same model as parent (recommended)
• sonnet - Claude Sonnet (balanced)
• opus - Claude Opus (most capable, expensive)
• haiku - Claude Haiku (fast, cheap)

Recommendation: Use inherit unless agent needs specific model capabilities.

color (required)

Visual identifier for agent in UI.

Options: blue, cyan, green, yellow, magenta, red

Guidelines:

• Choose distinct colors for different agents in same plugin
• Use consistent colors for similar agent types
• Blue/cyan: Analysis, review
• Green: Success-oriented tasks
• Yellow: Caution, validation
• Red: Critical, security
• Magenta: Creative, generation

tools (optional)

Restrict agent to specific tools.

Format: Array of tool names

tools: ["Read", "Write", "Grep", "Bash"]

Default: If omitted, agent has access to all tools

Best practice: Limit tools to minimum needed (principle of least privilege)

Common tool sets:

• Read-only analysis: ["Read", "Grep", "Glob"]
• Code generation: ["Read", "Write", "Grep"]
• Testing: ["Read", "Bash", "Grep"]
• Full access: Omit field or use ["*"]

mcpServers (optional)

Give an agent access to MCP (Model Context Protocol) servers. There are two distinct forms with very different behavior:

Form 1: Inline definition (scoped to the subagent)

mcpServers:
  - playwright:
      type: stdio
      command: npx
      args: ["-y", "@playwright/mcp@latest"]

• Server is connected when the subagent starts and disconnected when it finishes
• Does not need to exist in the parent session's MCP config
• The main conversation never sees these tools
• Disabling it via /mcp in the main session has no effect
• Every invocation spins up a fresh connection

Use inline definitions to keep heavy MCP tools (Playwright, database, etc.) out of the main agent's context window entirely.

Form 2: String reference (reuses the parent session's connection)

mcpServers:
  - github

• Shares the parent session's existing connection — no new server is started
• The referenced server must already be configured and active in the parent session
• If the server is disabled via /mcp in the main session, the subagent loses access

Behavior comparison

	Inline definition	String reference
Connection lifecycle	Subagent start → finish	Shared with parent session
Requires parent config?	No	Yes
Effect of /mcp disable	No effect	Breaks subagent's access
Main agent sees the tools?	No	Yes (unless also restricted)

Combining both forms

You can mix inline and string references in the same agent:

mcpServers:
  - playwright:
      type: stdio
      command: npx
      args: ["-y", "@playwright/mcp@latest"]
  - github

Interaction with tools field

If you omit the tools field entirely, the subagent inherits all tools from the parent thread, including any MCP tools from the parent session. If you want tight control over which tools the subagent can use, specify both tools and mcpServers explicitly.

System Prompt Design

The markdown body becomes the agent's system prompt. Write in second person, addressing the agent directly.

Structure

Standard template:

You are [role] specializing in [domain].

**Your Core Responsibilities:**
1. [Primary responsibility]
2. [Secondary responsibility]
3. [Additional responsibilities...]

**Analysis Process:**
1. [Step one]
2. [Step two]
3. [Step three]
[...]

**Quality Standards:**
- [Standard 1]
- [Standard 2]

**Output Format:**
Provide results in this format:
- [What to include]
- [How to structure]

**Edge Cases:**
Handle these situations:
- [Edge case 1]: [How to handle]
- [Edge case 2]: [How to handle]

Best Practices

✅ DO:

• Write in second person ("You are...", "You will...")
• Be specific about responsibilities
• Provide step-by-step process
• Define output format
• Include quality standards
• Address edge cases
• Keep under 10,000 characters

❌ DON'T:

• Write in first person ("I am...", "I will...")
• Be vague or generic
• Omit process steps
• Leave output format undefined
• Skip quality guidance
• Ignore error cases

Creating Agents

Method 1: AI-Assisted Generation

Use this prompt pattern (extracted from Claude Code):

Create an agent configuration based on this request: "[YOUR DESCRIPTION]"

Requirements:
1. Extract core intent and responsibilities
2. Design expert persona for the domain
3. Create comprehensive system prompt with:
   - Clear behavioral boundaries
   - Specific methodologies
   - Edge case handling
   - Output format
4. Create identifier (lowercase, hyphens, 3-50 chars)
5. Write description with triggering conditions
6. Include 2-3 <example> blocks showing when to use

Return JSON with:
{
  "identifier": "agent-name",
  "whenToUse": "Use this agent when... Examples: <example>...</example>",
  "systemPrompt": "You are..."
}

Then convert to agent file format with frontmatter.

See examples/agent-creation-prompt.md for complete template.

Method 2: Manual Creation

1. Choose agent identifier (3-50 chars, lowercase, hyphens)
2. Write description with examples
3. Select model (usually inherit)
4. Choose color for visual identification
5. Define tools (if restricting access)
6. Write system prompt with structure above
7. Save as agents/agent-name.md

Validation Rules

Identifier Validation

✅ Valid: code-reviewer, test-gen, api-analyzer-v2
❌ Invalid: ag (too short), -start (starts with hyphen), my_agent (underscore)

Rules:

• 3-50 characters
• Lowercase letters, numbers, hyphens only
• Must start and end with alphanumeric
• No underscores, spaces, or special characters

Description Validation

Length: 10-5,000 characters Must include: Triggering conditions and examples Best: 200-1,000 characters with 2-4 examples

System Prompt Validation

Length: 20-10,000 characters Best: 500-3,000 characters Structure: Clear responsibilities, process, output format

Agent Organization

Plugin Agents Directory

plugin-name/
└── agents/
    ├── analyzer.md
    ├── reviewer.md
    └── generator.md

All .md files in agents/ are auto-discovered.

Namespacing

Agents are namespaced automatically:

• Single plugin: agent-name
• With subdirectories: plugin:subdir:agent-name

Testing Agents

Test Triggering

Create test scenarios to verify agent triggers correctly:

1. Write agent with specific triggering examples
2. Use similar phrasing to examples in test
3. Check Claude loads the agent
4. Verify agent provides expected functionality

Test System Prompt

Ensure system prompt is complete:

1. Give agent typical task
2. Check it follows process steps
3. Verify output format is correct
4. Test edge cases mentioned in prompt
5. Confirm quality standards are met

Quick Reference

Minimal Agent

---
name: simple-agent
description: Use this agent when... Examples: <example>...</example>
model: inherit
color: blue
---

You are an agent that [does X].

Process:
1. [Step 1]
2. [Step 2]

Output: [What to provide]

Frontmatter Fields Summary

Field	Required	Format	Example
name	Yes	lowercase-hyphens	code-reviewer
description	Yes	Text + examples	Use when... ...
model	Yes	inherit/sonnet/opus/haiku	inherit
color	Yes	Color name	blue
tools	No	Array of tool names	["Read", "Grep"]
mcpServers	No	Array of inline defs or string refs	See mcpServers section

Best Practices

DO:

• ✅ Include 2-4 concrete examples in description
• ✅ Write specific triggering conditions
• ✅ Use inherit for model unless specific need
• ✅ Choose appropriate tools (least privilege)
• ✅ Write clear, structured system prompts
• ✅ Test agent triggering thoroughly

DON'T:

• ❌ Use generic descriptions without examples
• ❌ Omit triggering conditions
• ❌ Give all agents same color
• ❌ Grant unnecessary tool access
• ❌ Write vague system prompts
• ❌ Skip testing

Additional Resources

Reference Files

For detailed guidance, consult:

• references/system-prompt-design.md - Complete system prompt patterns
• references/triggering-examples.md - Example formats and best practices
• references/agent-creation-system-prompt.md - The exact prompt from Claude Code

Example Files

Working examples in examples/:

• agent-creation-prompt.md - AI-assisted agent generation template
• complete-agent-examples.md - Full agent examples for different use cases

Utility Scripts

Development tools in scripts/:

• validate-agent.sh - Validate agent file structure
• test-agent-trigger.sh - Test if agent triggers correctly

Implementation Workflow

To create an agent for a plugin:

1. Define agent purpose and triggering conditions
2. Choose creation method (AI-assisted or manual)
3. Create agents/agent-name.md file
4. Write frontmatter with all required fields
5. Write system prompt following best practices
6. Include 2-4 triggering examples in description
7. Validate with scripts/validate-agent.sh
8. Test triggering with real scenarios
9. Document agent in plugin README

Focus on clear triggering conditions and comprehensive system prompts for autonomous operation.