Codemode in Claude Code

Anthropic shipped Code Mode in Claude Code v2.1.323, an experimental, off-by-default feature that has Claude write JavaScript to make tool calls instead of issuing Bash, Read, or Edit calls one at a time. The mode lets one script run commands in parallel, chain results into later calls, and return only the needed output, but it is limited to interactive terminal sessions on the native build with Opus 5.5, Sonnet 5.5, Haiku 5.5, or Fable 5.2, and it disables Remote Control, Claude in Chrome, computer use, and background sessions. Anthropic warns Code Mode may change or be removed in any release, and long-running code stops after ten minutes unless it runs in the background.

tools https://code.claude.com/docs/en/tools-reference . Without Code Mode, Claude asks for tool calls such as Bash, Read, or Edit directly and reads each result before it decides what to do next. With Code Mode, Claude writes a piece of JavaScript that makes the tool calls, and Claude Code runs that code in your session. Code Mode is experimental and off by default. It may change or be removed in any release. To share feedback, run /feedback . In a Code Mode session, you still describe your task in a prompt, and Claude writes JavaScript to carry it out. One piece of code can run commands in parallel, use one result in the next call, and return the part of the output that Claude needs to read. For example, if you ask Claude to raise a retry limit, Claude might write this code to find the file, edit it, and run the tests. The last line returns the file’s path and the test output to Claude: Ctrl+O to open the transcript viewer https://code.claude.com/docs/en/interactive-mode transcript-viewer . Each piece of code appears there as a collapsed Code row, with a hint for how to expand it. Try Code Mode on tasks that take many related tool calls, such as: - A change that repeats across many files - A search whose results need filtering before Claude reads them - Several independent commands that can run at the same time Before you turn on Code Mode, check that you can accept these limits: - Resuming : you can resume a Code Mode session only in the terminal, with Code Mode on - Auto mode : auto mode’s classifier reviews the code, not each tool call permission-checks - Long-running code : unless code can run in the background long-running-code , you wait for it to finish, and it stops after ten minutes - Hooks : you can see tool calls refused tool-call-refused-by-a-hook when a PreToolUse hook can’t run or times out, and code output blocked code-output-withheld-by-a-hook by a UserPromptSubmit hook - Unavailable features : you can’t use Remote Control https://code.claude.com/docs/en/remote-control , Claude in Chrome https://code.claude.com/docs/en/chrome , or computer use https://code.claude.com/docs/en/computer-use - Moving the session : you can’t move the session to the Desktop app or turn it into a background session https://code.claude.com/docs/en/agent-view , and /fork can’t start a background copy - Version : Claude Code v2.1.323 or later, on either release channel https://code.claude.com/docs/en/setup configure-release-channel . An older version starts without Code Mode, with or without the reason it isn't open to your account yet - Account : a Claude subscription or Console account. You can’t use Code Mode through a gateway, Amazon Bedrock, Claude Platform on AWS, Google Cloud’s Agent Platform, or Microsoft Foundry - Organization : your organization doesn’t use the HIPAA configuration https://code.claude.com/docs/en/hipaa-setup or zero data retention https://code.claude.com/docs/en/zero-data-retention - Model : Claude Opus 5.5, Sonnet 5.5, Haiku 5.5, or Fable 5.2 - Surface : an interactive claude session in a terminal. Code Mode doesn’t work with -p , the Agent SDK, the VS Code panel, the Desktop app, or cloud sessions - Installation : the native build https://code.claude.com/docs/en/setup of Claude Code - Windows : Git for Windows https://git-scm.com/downloads/win is installed DISABLE TELEMETRY . For the fix for each, see Code Mode doesn’t start code-mode-doesnt-start . Turn on Code Mode, give Claude a task, and look at the code that Claude wrote. 1 Check your version Run claude --version . If the version is older than v2.1.323, run claude update . If you’re on the stable channel and the update doesn’t reach v2.1.323, wait for stable to catch up or switch to https://code.claude.com/docs/en/setup configure-release-channel . latest 2 Start Claude Code with Code Mode on Set the environment variable to https://code.claude.com/docs/en/env-vars variables CLAUDE CODE EXPERIMENTAL CODE MODE 1 . To try Code Mode, set it in your shell. To turn on Code Mode for every new session, set it in your user settings. - macOS, Linux, WSL - Windows PowerShell - settings.json 3 Confirm that you want Code Mode Claude Code asks you to confirm before your first Code Mode session. Select If you see a different line or none, see Yes, turn on Code Mode . Claude Code restarts and shows this line near the top of the session: Code Mode doesn’t start code-mode-doesnt-start . 4 Give Claude a task with many tool calls In a project you know, send a prompt such as this one: 5 Read the code Claude wrote Press Ctrl+O and expand a Code row to see the JavaScript behind the tool calls. Press Ctrl+O again to return to the conversation. Remove CLAUDE CODE EXPERIMENTAL CODE MODE from your shell and from ~/.claude/settings.json , then start a new session. You can also keep the variable and change its value to 0 in either place. With a 0 in one place, Code Mode stays off even if you set 1 in the other. Add CLAUDE CODE EXPERIMENTAL CODE MODE with the value 0 to your managed settings https://code.claude.com/docs/en/managed-settings so that nobody in your organization can use Code Mode: 0 is in place. You can’t turn on Code Mode for your users from managed settings. Your permission mode decides how Claude’s code is checked and whether you can talk to Claude while the code runs. Each tool call that Claude’s code makes goes through your deny and ask permission rules https://code.claude.com/docs/en/permissions and your . You don’t need to change a rule or matcher for a tool such as https://code.claude.com/docs/en/hooks pretooluse PreToolUse hooks Bash . Beyond rules and hooks, a classifier reviews the code in auto mode, and you answer prompts in the modes that ask: - Auto mode https://code.claude.com/docs/en/permission-modes eliminate-prompts-with-auto-mode : the classifier reviews each piece of code before it runs, not each tool call. It doesn’t see values computed at run time, such as a path taken from search output, so keep rules or hooks for calls you must control. You can still be prompted when new code starts while earlier code runs permission-prompt-with-a-countdown - Other permission modes https://code.claude.com/docs/en/permission-modes : the code starts without a review, and you’re prompted for each tool call that would prompt you in that mode PreToolUse hook that matches REPL , the tool that runs Claude’s code, and read the JavaScript from tool input.code . While code runs a long build or test, Claude either waits for it or lets it continue in the background: - Waiting : Claude answers after the code finishes, and the code stops after ten minutes, including time you spend at permission prompts - Background : you can keep talking to Claude, and the code can run for up to two hours bypassPermissions mode. If Claude still waits, check your current mode and how you started the session: - You switched to another mode : press Shift+Tab until you’re back in the mode you started in - You started in another mode, or picked the session from the claude --resume list : if auto mode is available https://code.claude.com/docs/en/permission-modes eliminate-prompts-with-auto-mode to you, exit, then run claude --continue --permission-mode auto with Code Mode on - You passed tool names to --tools : start again in auto mode without that flag Code Mode experimental isn't available near the top of the session means that Claude Code started without Code Mode. The reason follows on the same line, and /status shows it too. Find the reason in this table, make the change, and start a new session. For a reason that isn’t listed, check the requirements requirements . If you see no line about Code Mode, run claude --version . If your version is older than v2.1.323, update. Then check that CLAUDE CODE EXPERIMENTAL CODE MODE is 1 in your shell or user settings, and remove any 0 from those and from any --settings file. When Claude starts more code in auto mode while earlier code is still running, the earlier code loses its classifier review. Claude Code then asks you about the earlier code’s remaining calls that would need a review. With no IDE connected, the prompt shows a countdown: If Claude reports a refused tool call, ask it for the error text. These errors mean that a PreToolUse hook didn’t give a decision, which refuses the call even when is unset: https://code.claude.com/docs/en/hooks block-the-action-when-a-hook-fails onFailure - the hook failed : on a call from Claude’s code, your hook couldn’t start, was killed, exited with 126, 127, or a code above 128, or returned an HTTP error or invalid output. Fix the hook - the hook did not finish : your hook timed out on a call from Claude’s code, or on any other tool call once Claude has run code in the session. Raise the hook’s timeout https://code.claude.com/docs/en/hooks common-fields command or http hook fails or times out, set "onFailure": "continue" on it. If a command hook exits with an ordinary code such as 1, the call goes ahead unless you set "onFailure": "block" . If Claude reports a hook’s block reason where you expected output from Claude’s code, check your hooks. When https://code.claude.com/docs/en/hooks userpromptsubmit UserPromptSubmit code can run in the background long-running-code , command , http , and mcp tool hooks on that event also run on code output. To let the output through, change the hook so that it doesn’t block when source in its input is poll event . - Permission modes https://code.claude.com/docs/en/permission-modes : compare auto mode with the modes that prompt you - Hooks reference https://code.claude.com/docs/en/hooks : write PreToolUse and UserPromptSubmit hooks - Managed settings https://code.claude.com/docs/en/managed-settings : apply one configuration across an organization