Shaike1 Claude Code icon

Shaike1 Claude Code

Use Claude Code SDK to execute AI-powered coding tasks with customizable tool support
Join our community

Actions2

Overview

This node integrates with the Claude Code AI SDK to perform AI-powered coding tasks through conversational interactions. It allows users to send prompts or instructions to Claude Code, which can generate code snippets, analyze projects, or assist with programming-related queries. The node supports starting new conversations or continuing previous ones, enabling iterative development and refinement.

Common scenarios include:

  • Generating code functions or scripts based on natural language prompts.
  • Automating code review or refactoring suggestions.
  • Running AI-assisted project analysis or debugging within a specified project directory.
  • Using built-in tools like file editing, web search, or command execution to enhance AI capabilities.

Practical example:

  • A user inputs a prompt like "Create a Python function to parse CSV files" and receives a structured response containing the generated code, usage metrics, and conversation messages.
  • Another use case is allowing Claude Code to fetch web content or manage todo lists during the coding session by enabling specific built-in tools.

Properties

Name Meaning
Prompt The instruction or query sent to Claude Code. Supports expressions to dynamically use data from previous nodes. Example: "Create a Python function to parse CSV files"
Model Selects the Claude model variant:
- Sonnet: Fast and efficient for most tasks
- Opus: More capable for complex tasks
Max Turns Maximum number of back-and-forth conversation turns allowed in the session. Controls how long the interaction can continue.
Timeout Maximum time (in seconds) to wait for Claude Code to complete the task before aborting. Default is 300 seconds.
Project Path Directory path where Claude Code should run, allowing it to access files and execute commands relative to this location. If empty, uses the current working directory.
Output Format Determines the format of the output data:
- Structured: Returns an object with messages, summary, result, and metrics.
- Messages: Returns raw array of all exchanged messages.
- Text: Returns only the final result text.
Allowed Tools Built-in tools Claude Code is permitted to use during execution. Options include:
Execute bash commands, Edit files, Exit planning mode, Find files by pattern, Search file contents, List directory contents, Multi-edit, Notebook editing/reading, Read/write files, Launch agents for complex searches, Manage todo lists, Fetch web content, Search the web. Default includes WebFetch, TodoWrite, WebSearch, exit_plan_mode, Task.
Additional Options Collection of optional settings:
- System Prompt: Extra context or instructions for Claude Code.
- Require Permissions: Whether tool use requires explicit permission.
- Debug Mode: Enables debug logging for detailed execution info.

Output

The node outputs JSON data structured according to the selected Output Format:

  • Structured:
    An object containing:

    • messages: Array of all messages exchanged during the conversation (user, assistant, system).
    • summary: Counts of user messages, assistant messages, tool uses, presence of result, and available tools.
    • result: The final result text or error message if any.
    • metrics: Performance data including duration in milliseconds, number of turns, total cost in USD, and usage details.
    • success: Boolean indicating if the operation succeeded.

  • Messages:
    Raw array of all messages exchanged, along with a count of messages.

  • Text:
    Only the final result text string, plus metadata such as success status, duration, and cost.

No binary data output is produced by this node.

Dependencies

  • Requires the Claude Code SDK (@anthropic-ai/claude-code) to interact with the Claude AI models.
  • Needs an API key credential configured in n8n to authenticate requests to the Claude Code service.
  • Optionally depends on the availability of a project directory if Project Path is set, allowing file system access.
  • Uses Node.js AbortController for timeout handling.

Troubleshooting

  • Empty Prompt Error:
    If the prompt is empty or whitespace, the node throws an error stating that the prompt is required. Ensure the prompt field is filled with meaningful input.

  • Timeout Errors:
    If the operation exceeds the specified timeout, an abort error occurs. Increase the timeout value in the node settings if longer processing is expected.

  • Permission Denied for Tools:
    If Require Permissions is enabled, Claude Code may request permission before using certain tools. Denying permissions might cause incomplete results.

  • API or Network Issues:
    Failures connecting to the Claude Code service will throw execution errors. Verify API credentials and network connectivity.

  • Debugging:
    Enable Debug Mode in Additional Options to get detailed console logs about the execution flow, prompts, received messages, and tool usage, which helps diagnose issues.

Links and References

Discussion