agents
npx machina-cli add skill claude-world/director-mode-lite/agents --openclawAvailable Agents
List all agents available in Director Mode Lite.
Core Agents
code-reviewer
Purpose: Code quality, security, best practices review. Triggers: "review", "check code", before commits
debugger
Purpose: Systematic debugging for errors. Triggers: Errors, test failures, "bug", "debug"
doc-writer
Purpose: Documentation creation and maintenance. Triggers: New features, "document", "README"
Expert Agents
claude-md-expert
CLAUDE.md design patterns and best practices.
mcp-expert
MCP configuration and troubleshooting.
agents-expert
Custom agent creation and configuration.
skills-expert
Custom skill/command creation.
hooks-expert
Automation hooks and triggers.
How Agents Work
- Auto-activate based on context
- Follow specific methodologies
- Provide structured output
- Can be explicitly invoked
Using Agents
"Use code-reviewer to check src/auth/"
"I need the debugger - tests are failing"
"Have doc-writer update the API docs"
Creating Custom Agents
---
name: my-agent
description: What this agent does
tools: Read, Grep, Glob, Bash
---
# Agent Name
## When to Activate
## Process
## Output Format
Save to .claude/agents/my-agent.md
Source
git clone https://github.com/claude-world/director-mode-lite/blob/main/skills/agents/SKILL.mdView on GitHub Overview
This skill enumerates every available agent in Director Mode Lite, including core agents (code-reviewer, debugger, doc-writer) and expert agents (claude-md-expert, mcp-expert, agents-expert, skills-expert, hooks-expert). It helps you understand each agent's purpose and triggers, enabling effective automation planning and customization.
How This Skill Works
Reads the Available Agents sections from the skill content, grouping core vs expert agents and listing their purpose and triggers. It also notes the activation behavior: auto-activate by context and explicit invocation, and how to use the Using Agents examples to run them.
When to Use It
- Planning an automation workflow and want to see available core and expert agents and their triggers
- Diagnosing issues and deciding between code-reviewer or debugger when code quality or tests fail
- Keeping documentation up-to-date by delegating to doc-writer for new features or changes
- Exploring advanced workflows by investigating expert agents (e.g., claude-md-expert, hooks-expert)
- Creating and saving a new custom agent using the provided template
Quick Start
- Step 1: Review the Available Agents to see core and expert options
- Step 2: Invoke a specific agent, for example: 'Use code-reviewer to check src/auth/' or 'I need the debugger - tests are failing'
- Step 3: If you need custom behavior, copy the Creating Custom Agents template and save to .claude/agents/your-agent.md
Best Practices
- Review each agent's core purpose and triggers before building a workflow
- Prefer core agents for standard tasks (code-reviewer, debugger, doc-writer) to start quickly
- Use expert agents to handle specialized or complex automation needs
- Test custom agents using the Creating Custom Agents template and save to .claude/agents
- Document your agent workflows and invocation patterns for team reuse
Example Use Cases
- Use code-reviewer to check src/auth/ for code quality and security issues
- I need the debugger when tests are failing and need root-cause analysis
- Have doc-writer update the API docs after a feature release
- Create and configure a new agents-expert for custom automation
- Follow the Creating Custom Agents template and save as .claude/agents/my-agent.md
