Anthropic Ships Experimental Code Mode for Claude Code

By ▲ Marktechpost AI (@Marktechpost)Original title: ▲ Anthropic just shipped Code Mode in Claude Code, so Claude can now write JavaScript that chains it...
74AI Score

Anthropic has shipped an experimental Code Mode in Claude Code that lets Claude write a single JavaScript program chaining its own tool calls, running commands in parallel and returning only the needed output. The feature is off by default and opt-in via an environment variable, with background code running up to two hours while code Claude waits on stops after ten minutes.

Full Report

▲ Marktechpost AI · 2026-11-18 06

▲ Anthropic just shipped Code Mode in Claude Code, so Claude can now write JavaScript that chains its own tool calls in 1 step.

The key idea is simple. Without Code Mode, Claude asks for each Bash, Read or Edit call and reads every result. With Code Mode, Claude writes 1 program that runs commands in parallel, feeds one result into the next call, and returns only the output it needs.

The numbers: code that runs in the background can keep going for up to 2 hours while you keep talking to Claude. Anthropic's related code execution with MCP pattern cut 1 workflow from 150,000 to 2,000 tokens. It is a trade-off though: Anthropic publishes no token figure for Code Mode itself, code Claude waits on stops after 10 minutes, and auto mode reviews the code, not each tool call.

It is experimental and off by default. Opt in with CLAUDE_CODE_EXPERIMENTAL_CODE_MODE=1 on Claude Code v2.1.323 or later. It works with Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.2, in the terminal, on the Anthropic API only......

Full analysis:

推文配图