Code Execution

Use the Claude API code execution tool so the model runs Bash and Python in an Anthropic-hosted sandbox during a response — for calculation, data analysis, file generation, and checking its own work. Covers tool versions, file upload, retrieving generated files, container reuse, limits, and data-retention constraints. Use this skill when building features where Claude must actually run code (not just write it), when choosing a code execution tool version, or when debugging missing output files or expired containers. Activate when: Claude code execution, code_execution tool, Python sandbox, run code tool, data analysis agent, code interpreter, container_upload, container reuse, OUTPUT_DIR.

latestaiagents Updated 6 repo stars

File contents

latestaiagents/agent-skills commit 53f170358d

Frequently asked questions

npx get-skill add latestaiagents/code-execution-2