> ## Documentation Index
> Fetch the complete documentation index at: https://codegeninc-codegen-bot-add-trufflehog-security-docs-1758040.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Code

Users can configure Codegen to run Claude Code as the main agent loop. For some organizations and tasks, this can lead to improved agent performance.

<Card title="Use Claude Code on Codegen" icon="brain-circuit" href="https://codegen.com/settings/model">
  Enable Claude Code mode in your model configuration settings to enhance agent
  capabilities.
</Card>

<Note>OpenAI Codex and Gemini CLI support are coming soon.</Note>

## What is Claude Code?

Claude Code is Anthropic's specialized coding environment that provides:

* **Enhanced Code Understanding**: Better comprehension of complex codebases and architectural patterns
* **Advanced Tool Integration**: Seamless integration with development tools through MCP (Model Context Protocol)
* **Improved Code Generation**: More accurate and contextually appropriate code suggestions
* **Better Error Handling**: Enhanced debugging and error resolution capabilities
* **Validation Hooks**: Built-in validation to ensure proper tool usage and workflow completion

## Enabling Claude Code

Claude Code can be enabled at the organization level through your model configuration settings:

1. Navigate to [**codegen.com/settings/model**](https://codegen.com/settings/model)
2. Locate the "Claude Code Mode" section
3. Toggle the setting to "Enabled"
4. Select your preferred Claude Code model (typically Claude 4 Sonnet)

## How It Works

When Claude Code is enabled, Codegen automatically:

1. **Sandbox Execution**: Runs Claude Code in a secure **[sandbox environment](/sandboxes/overview)** for safe code execution and testing
2. **MCP Integration**: Provides access to all your **[integrations](/integrations/integrations)** through MCP (Model Context Protocol) for seamless tool coordination
3. **Enhanced Logging**: Captures detailed logs using Claude Code hooks, which are displayed in the agent UI on codegen.com for full transparency and debugging
4. **Full Feature Compatibility**: Manages interactions with Slack, Linear, and other project management tools, while maintaining the complete PR lifecycle including **[automatic check fixing](/capabilities/checks-autofixer)** and code reviews

## Key Features

### MCP Integration

Claude Code agents automatically use MCP (Model Context Protocol) for tool integration, providing:

* Standardized tool interfaces
* Better error handling and validation
* Consistent tool behavior across different environments
* Enhanced debugging capabilities

### Validation Hooks

Claude Code supports validation hooks that ensure agents complete required actions:

* **Message Validation**: Ensures agents send appropriate messages before completing tasks
* **PR Creation Validation**: Verifies that pull requests are created when required
* **Custom Validations**: Organization-specific validation rules can be configured

### Enhanced Capabilities

* **Better Code Analysis**: Improved understanding of code structure and dependencies
* **Contextual Awareness**: Better retention of conversation context across long interactions
* **Tool Coordination**: More effective coordination between different development tools
* **Error Recovery**: Enhanced ability to recover from and resolve errors

## Supported Channels

Claude Code is available across all Codegen integration channels:

* **Slack**: Enhanced responses and code assistance in Slack channels
* **GitHub**: Improved PR reviews, issue resolution, and code suggestions
* **API**: Full Claude Code capabilities available through the Codegen API
* **Linear**: Better integration with Linear workflows and issue management

## Model Selection

When Claude Code is enabled, you can choose from available Claude models:

* **Claude 4 Sonnet** (Recommended): Best balance of performance and cost
* **Claude 4 Opus**: Maximum capability for complex tasks
* **Claude 4 Haiku**: Faster responses for simpler tasks

<Tip>
  Claude 4 Sonnet is recommended for most use cases as it provides excellent
  performance while maintaining cost efficiency. Our prompts and workflows are
  optimized for this model.
</Tip>

## User Preferences

Individual users can override the organization-wide Claude Code setting through their personal preferences, allowing for:

* **Per-user enablement**: Users can opt into Claude Code even if not enabled organization-wide
* **Per-user disabling**: Users can opt out of Claude Code if they prefer the standard agent
* **Flexible adoption**: Teams can gradually adopt Claude Code at their own pace

## Best Practices

### When to Use Claude Code

Claude Code is particularly effective for:

* **Complex Refactoring**: Large-scale code changes and architectural improvements
* **Debugging**: Investigating and resolving complex bugs
* **Code Reviews**: Comprehensive analysis of pull requests
* **Documentation**: Generating and updating technical documentation
* **Integration Work**: Connecting different systems and APIs

### Configuration Tips

* **Start with Organization-wide**: Enable Claude Code at the organization level for consistent experience
* **Monitor Performance**: Track agent performance and user feedback during initial rollout
* **Customize Validations**: Configure validation hooks based on your team's workflow requirements
* **Model Selection**: Use Claude 4 Sonnet unless you have specific needs for other models

## Troubleshooting

### Common Issues

**Claude Code not activating:**

* Verify the setting is enabled in organization model configuration
* Check that feature flags are properly configured for your organization
* Ensure users have the appropriate permissions

**Tool integration problems:**

* MCP integration is automatic with Claude Code - no additional configuration needed
* Check sandbox logs for any MCP server startup issues
* Verify that required tools are available in your organization's configuration

**Performance concerns:**

* Claude Code may have slightly different response times compared to standard agents
* Monitor usage patterns and adjust model selection if needed
* Consider user preferences for performance-sensitive workflows

### Getting Help

If you encounter issues with Claude Code:

1. Check the agent run logs for detailed error information
2. Verify your organization's model configuration settings
3. Contact support with specific error messages and agent run IDs

<Note>
  Claude Code is a premium feature that may require specific plan levels or
  feature flag enablement. Contact your Codegen representative if you don't see
  the Claude Code options in your settings.
</Note>

## Migration from Standard Agents

Switching to Claude Code is seamless:

* **No workflow changes**: Existing integrations and workflows continue to work
* **Same tool access**: All existing Codegen tools remain available
* **Backward compatibility**: Can switch back to standard agents at any time
* **Gradual rollout**: Enable for specific users or channels as needed

The transition to Claude Code enhances your existing Codegen experience without requiring changes to how you interact with the platform.