code-execution-helper

Code Execution Helper

This skill provides guidance for using code execution capabilities efficiently in Claude Code workflow agents. Code execution enables agents to perform parallel batch processing, conditional filtering, and data aggregation while dramatically reducing token consumption.

About Code Execution

Code execution allows agents to run TypeScript code in a sandboxed Deno runtime, enabling operations that would otherwise require loading massive amounts of data into context. By processing data in the execution environment and returning only filtered or aggregated results, agents can achieve 30-95% token reduction for high-value use cases.

Key Benefits

1. Parallel batch processing - Scan 10+ files simultaneously instead of sequentially
2. Conditional filtering - Return only relevant data (e.g., CRITICAL vulnerabilities only)
3. Data aggregation - Summarize patterns across multiple sources
4. Token efficiency - Process large datasets without context window limits
5. Quota awareness - Check API limits before execution to prevent failures

When to Use Code Execution

Use code execution when tasks meet these criteria:

• Multiple operations: More than 5 files, API calls, or validation checks
• Large datasets: Results exceed 10,000 tokens if loaded into context
• Conditional logic: Need to filter, aggregate, or transform data before returning
• Parallel processing: Operations can run simultaneously for faster execution
• Token efficiency: Reducing context usage is important for the workflow

When NOT to Use Code Execution

Avoid code execution for:

• Single operations: One file scan, one API call, simple queries
• Small datasets: Results under 2,000 tokens
• Direct responses: User needs raw data without filtering
• Simple queries: Questions answerable with existing tools
• Debugging code execution itself: Use direct tools to avoid recursion

Decision Criteria

To determine whether to use code execution, apply these thresholds: