One read of Claude Code CLIclaude-code-20260814T043110Z
187 pages moved out of 187 read.
Pages moved
187
significant first
Pages read
187
in this capture
Captured
04:31 UTC
Corpus hash
415ba349e48b
full baseline · corpus-hash
What this read moved
176-187 of 187, page 8 of 8This capture is too large to show at once. Changes 176-187 of 187 are below, significant first; the rest are on the following screens.
whats-new/2026-w24 First recorded · 80 lines, first recorded
# Week 24 · June 8–12, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 24 · June 8–12, 2026
> Move a session to a new directory with /cd, let subagents spawn their own subagents, and troubleshoot a broken configuration with safe mode.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-166">v2.1.166 → v2.1.176</a></span>
<span>3 features · June 8–12</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Move a session with /cd</span>
<span className="digest-feature-pill">v2.1.169</span>
</div>
<p className="digest-feature-lede">The new <code>/cd</code> command moves the current session to a different working directory without rebuilding the prompt cache: the new directory's <code>CLAUDE.md</code> is appended as a message instead of replacing the system prompt. The session relocates to the new directory's project storage, so `--resume` and `--continue` find it there. Claude prompts you to trust the directory if you haven't worked in it before.</p>
<p className="digest-feature-try">Move the session into another project without restarting:</p>
```text Claude Code theme={null}
> /cd ../other-project
```
<a className="digest-feature-link" href="/docs/docs/en/commands#all-commands">Commands reference</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Subagents can spawn subagents</span>
<span className="digest-feature-pill">v2.1.172</span>
</div>
<p className="digest-feature-lede">Subagents can now spawn their own subagents. The subagent panel below the prompt shows the full tree: each row carries a count of its descendants and a path back to <code>main</code>. Subagent chains are capped at five levels deep to prevent runaway concurrent trees.</p>
<p className="digest-feature-try">Open the agents view to watch the nested tree as work fans out:</p>
```text Claude Code theme={null}
> /agents
```
<a className="digest-feature-link" href="/docs/docs/en/sub-agents#let-subagents-spawn-their-own-subagents">Spawn nested subagents</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Troubleshoot with safe mode</span>
<span className="digest-feature-pill">v2.1.169</span>
</div>
<p className="digest-feature-lede">Start Claude Code with `--safe-mode`, or set <code>CLAUDE\_CODE\_SAFE\_MODE</code>, to launch with all customizations disabled: <code>CLAUDE.md</code>, skills, plugins, hooks, MCP servers, and custom commands and agents do not load. Authentication, model selection, built-in tools, and permissions still work. If a problem disappears in safe mode, one of those surfaces is the cause.</p>
<p className="digest-feature-try">Launch a clean session to isolate a broken configuration:</p>
```bash terminal theme={null}
claude --safe-mode
```
<a className="digest-feature-link" href="/docs/docs/en/debug-your-config#test-against-a-clean-configuration">Test against a clean configuration</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div><a href="/docs/docs/en/model-config#fallback-model-chains"><code>fallbackModel</code></a> configures up to three fallback models tried in order when the primary is overloaded or unavailable, and `--fallback-model` now applies to interactive sessions too</div>
<div>Session titles are now generated in the language of your conversation; pin a specific one with the <code>language</code> setting</div>
<div>`claude agents --json` adds `--all` to include completed sessions plus new <code>id</code> and <code>state</code> fields, and no longer omits blocked or newly dispatched sessions</div>
<div>Browsing a marketplace's plugins in <code>/plugin</code> now has a search bar</div>
<div>New <code>disableBundledSkills</code> setting and <code>CLAUDE\_CODE\_DISABLE\_BUNDLED\_SKILLS</code> hide bundled skills, workflows, and built-in commands from the model</div>
<div>Deny rules accept a glob in the tool-name position, so <code>"\*"</code> denies all tools, and unknown tool names in deny rules now warn at startup</div>
<div>Agent messaging is hardened: messages relayed via <code>SendMessage</code> from other agents no longer carry user authority, and auto mode blocks them</div>
<div>Amazon Bedrock reads the AWS region from <code>\~/.aws</code> config files when <code>AWS\_REGION</code> is unset, and <code>/status</code> shows where the region came from</div>
<div>New <code>enforceAvailableModels</code> managed setting makes the <code>availableModels</code> allowlist also constrain the Default model</div>
<div>Claude in Chrome browser tools now load in a single batched call instead of one per tool</div>
<div><code>claude update</code> announces the target version before downloading instead of going silent</div>
<div>New <code>footerLinksRegexes</code> setting adds regex-matched link badges to the footer row</div>
</div>
</div>
[Full changelog for v2.1.166–v2.1.176 →](/docs/en/changelog#2-1-166)
whats-new/2026-w25 First recorded · 86 lines, first recorded
# Week 25 · June 15–19, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 25 · June 15–19, 2026
> Publish a live, shareable page from your session with Artifacts, match tool parameters in deny and ask rules, and set any setting from the prompt with /config.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-178">v2.1.178 → v2.1.183</a></span>
<span>3 features · June 15–19</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Artifacts</span>
</div>
<p className="digest-feature-lede">An artifact is a live, interactive page that Claude Code publishes from your session to a private URL on claude.ai, and it updates in place as the session keeps working. Ask for one when terminal text is the wrong medium, such as a PR walkthrough with the diff annotated inline or a dashboard built from session data. Artifacts are in beta on Team and Enterprise plans.</p>
<Frame>
<video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/1ylKDoQynT1UgfEK/images/whats-new/artifacts.mp4?fit=max&auto=format&n=1ylKDoQynT1UgfEK&q=85&s=7f5391559d2bc69989621b36322fcff1" data-path="images/whats-new/artifacts.mp4" />
</Frame>
<p className="digest-feature-try">Ask Claude for a page, then approve the publish prompt:</p>
```text title="Claude Code" wrap theme={null}
Make an artifact that walks through this PR with the diff annotated inline.
```
<a className="digest-feature-link" href="/docs/docs/en/artifacts#create-an-artifact">Create an artifact</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Match by input parameter</span>
<span className="digest-feature-pill">v2.1.178</span>
</div>
<p className="digest-feature-lede">Deny and ask permission rules can now match a tool's input parameters with the <code>Tool(param:value)</code> syntax. For example, <code>Agent(model:opus)</code> matches subagent spawns that request the Opus model tier. The value accepts `*` as a wildcard, so `Agent(isolation:*)` matches any explicit isolation value.</p>
<p className="digest-feature-try">Add a parameter rule to the deny list in <code>settings.json</code>:</p>
```json .claude/settings.json {3} theme={null}
{
"permissions": {
"deny": ["Agent(model:opus)"]
}
}
```
<a className="digest-feature-link" href="/docs/docs/en/permissions#match-by-input-parameter">Match by input parameter</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Set any setting from the prompt</span>
<span className="digest-feature-pill">v2.1.181</span>
</div>
<p className="digest-feature-lede">Pass <code>key=value</code> to <code>/config</code> to change a setting directly without opening the Settings interface. The syntax also works in non-interactive mode with the <code>-p</code> flag and from Remote Control.</p>
<p className="digest-feature-try">Set the <code>thinking</code> setting from the prompt:</p>
```text title="Claude Code" wrap theme={null}
/config thinking=false
```
<a className="digest-feature-link" href="/docs/docs/en/commands#all-commands">Commands reference</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div>Auto mode now blocks destructive git commands (`git reset --hard`, `git clean -fd`, `git stash drop`) when you didn't ask to discard local work, and blocks <code>terraform destroy</code> unless you asked for the specific stack</div>
<div>Set the new <code>attribution.sessionUrl</code> setting to <code>false</code> to omit the claude.ai session link from commits and PRs in web and Remote Control sessions</div>
<div>In the <code>/config</code> interface, Enter and Space both change the selected setting, and Esc now saves and closes instead of reverting</div>
<div>New <code>sandbox.allowAppleEvents</code> opt-in setting lets sandboxed commands send Apple Events on macOS</div>
<div>Point <code>CLAUDE\_CLIENT\_PRESENCE\_FILE</code> at a marker file to suppress mobile push notifications while you're at the machine</div>
<div>Long paragraphs now stream line by line instead of waiting for the first line break</div>
<div>API connection drops mid-thinking now retry automatically instead of showing "Connection closed while thinking"</div>
<div>With <code>CLAUDE\_CODE\_EXPERIMENTAL\_AGENT\_TEAMS=1</code> set, every session has one implicit team, so you spawn teammates directly with the Agent tool's <code>name</code> parameter</div>
<div>Skills in nested <code>.claude/skills</code> directories load when working on files there; on a name clash the nested skill appears as `<dir>:<name>` so both stay available</div>
<div>Fixed prompt caching not reading on a custom <code>ANTHROPIC\_BASE\_URL</code> and on Microsoft Foundry</div>
<div>Fixed Write and Edit producing zero-byte or truncated files on network drives and cloud-synced folders</div>
</div>
</div>
[Full changelog for v2.1.178–v2.1.183 →](/docs/en/changelog#2-1-178)
whats-new/2026-w26 First recorded · 62 lines, first recorded
# Week 26 · June 22–26, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 26 · June 22–26, 2026
> Authenticate MCP servers from your shell with claude mcp login, get a response to shell mode command output with the ! prefix, and resume a conversation from before /clear with /rewind.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-185">v2.1.185 → v2.1.193</a></span>
<span>2 features · June 22–26</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Authenticate MCP servers from the CLI</span>
<span className="digest-feature-pill">v2.1.186</span>
</div>
<p className="digest-feature-lede">New `claude mcp login <name>` and `claude mcp logout <name>` commands authenticate a configured MCP server from your shell instead of the interactive <code>/mcp</code> menu. `claude mcp login` runs the server's OAuth flow directly, and `claude mcp logout` clears the stored credentials.</p>
<p className="digest-feature-try">Run the OAuth flow for a configured server without opening a session:</p>
```bash terminal theme={null}
claude mcp login sentry
```
<a className="digest-feature-link" href="/docs/docs/en/mcp#authenticate-from-the-command-line">Authenticate from the command line</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Shell mode responds to command output</span>
<span className="digest-feature-pill">v2.1.186</span>
</div>
<p className="digest-feature-lede">Commands you run with the <code>!</code> prefix now get a response from Claude once the output lands in the transcript, so you can run <code>! npm test</code> and get an explanation of the failures without a second prompt. The response costs the same as sending a normal prompt. To keep the earlier behavior, where the output is added to context without a response, set <code>respondToBashCommands</code> to <code>false</code> in <code>settings.json</code>.</p>
<p className="digest-feature-try">Run a command and get a response to its output:</p>
```text Claude Code theme={null}
> ! npm test
```
<a className="digest-feature-link" href="/docs/docs/en/interactive-mode#shell-mode-with-prefix">Shell mode with the ! prefix</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div><code>/rewind</code> can now resume a conversation from before <code>/clear</code> was run</div>
<div>New <code>sandbox.credentials</code> setting blocks sandboxed commands from reading credential files and secret environment variables</div>
<div>Org-configured model restrictions now apply to the model picker, `--model`, <code>/model</code>, and <code>ANTHROPIC\_MODEL</code>, with a "restricted by your organization's settings" message when a restricted model is selected</div>
<div>New <code>autoMode.classifyAllShell</code> setting routes all Bash and PowerShell commands through the auto-mode classifier, and denial reasons now show in the transcript, the denial toast, and <code>/permissions</code></div>
<div>New <code>claude\_code.assistant\_response</code> OpenTelemetry log event carries the model's response text; deployments that already log prompt content start receiving it on upgrade, so set <code>OTEL\_LOG\_ASSISTANT\_RESPONSES=0</code> to keep prompts only</div>
<div>Background subagents now surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies only that tool</div>
<div><code>/install-github-app</code> can now install only the GitHub App and skip the Actions workflow and secret steps</div>
<div>Hosts you allow in the sandbox network permission dialog are remembered for the rest of the session instead of re-prompting on every connection</div>
<div>Streaming responses use about 37% less CPU, and long-session memory growth from the terminal output cache is reduced</div>
<div>`/review <pr>` now uses the same review engine as <code>/code-review medium</code></div>
<div>Bash mode <code>!</code> commands get live file path autocomplete</div>
</div>
</div>
[Full changelog for v2.1.185–v2.1.193 →](/docs/en/changelog#2-1-185)
whats-new/2026-w27 First recorded · 99 lines, first recorded
# Week 27 · June 29 – July 3, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 27 · June 29 – July 3, 2026
> Claude Sonnet 5 becomes the default model, Claude in Chrome reaches general availability, subagents run in the background by default, Claude Desktop arrives on Linux in beta, and /radio tunes into Claude FM.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-195">v2.1.195 → v2.1.201</a></span>
<span>5 features · June 29 – July 3</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Claude Sonnet 5</span>
<span className="digest-feature-pill">new model</span>
</div>
<p className="digest-feature-lede">Sonnet 5 is the new default model for Pro, Team Standard, and Enterprise subscription seats: top-tier coding and tool use at Sonnet pricing, with a native 1M-token context window and adaptive thinking on by default. API pricing is promotional at \$2/\$10 per MTok through August 31. Requires v2.1.197 or later.</p>
<p className="digest-feature-try">Switch to Sonnet 5 by name, or pick it from the model picker:</p>
```text Claude Code theme={null}
> /model claude-sonnet-5
```
<a className="digest-feature-link" href="/docs/docs/en/model-config#available-models">Model configuration</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Claude in Chrome is generally available</span>
<span className="digest-feature-pill">v2.1.198</span>
</div>
<p className="digest-feature-lede">The Chrome integration is out of preview for everyone on a direct Anthropic plan. Claude Code drives your browser through the Claude in Chrome extension: it opens tabs, clicks through pages, fills forms, reads console logs, and shares your login state, so it can test the app it builds without you switching contexts.</p>
<a className="digest-feature-link" href="/docs/docs/en/chrome">Use Claude Code with Chrome</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Subagents run in the background by default</span>
<span className="digest-feature-pill">v2.1.198</span>
</div>
<p className="digest-feature-lede">Claude now keeps working while subagents run and picks up their results when they finish, instead of pausing the conversation to wait. Claude still runs a subagent in the foreground when it needs the result before continuing, and background subagents surface every permission prompt in your main session. Pin a subagent's behavior with the <code>background</code> frontmatter field.</p>
<a className="digest-feature-link" href="/docs/docs/en/sub-agents#run-subagents-in-foreground-or-background">Run subagents in foreground or background</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Claude Desktop on Linux</span>
<span className="digest-feature-pill">Desktop</span>
</div>
<p className="digest-feature-lede">The Claude desktop app is now available on Ubuntu 22.04+ and Debian 12+ in beta, on x86\_64 and arm64. You get the same Chat, Cowork, and Claude Code experience as macOS and Windows: parallel sessions, visual diff review, an integrated terminal and editor, and live app preview. Installs from Anthropic's apt repository, so updates arrive through regular package updates.</p>
<a className="digest-feature-link" href="/docs/docs/en/desktop-linux">Claude Desktop on Linux</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">/radio</span>
<span className="digest-feature-pill">CLI</span>
</div>
<p className="digest-feature-lede">Claude FM is on the air. <code>/radio</code> opens the lo-fi radio stream in your browser for something to code to, and prints the stream URL when no browser is available. Not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry.</p>
<Frame>
<video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/x358isu_VzLnyTEN/images/whats-new/radio.mp4?fit=max&auto=format&n=x358isu_VzLnyTEN&q=85&s=36a0c33859cef119c7192dceea8bcbd3" data-path="images/whats-new/radio.mp4" />
</Frame>
<p className="digest-feature-try">Tune in from any session:</p>
```text Claude Code theme={null}
> /radio
```
<a className="digest-feature-link" href="/docs/docs/en/commands#all-commands">All commands</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div><a href="/docs/docs/en/artifacts">Artifacts</a> are now generally available and included on Pro and Max plans, joining Team and Enterprise</div>
<div>Admins can set an <a href="/docs/docs/en/model-config#organization-default-model">organization default model</a> in the org console; it shows as "Org default" in <code>/model</code> when you haven't picked a model yourself</div>
<div>Stacked skill invocations like <code>/skill-a /skill-b do XYZ</code> now load all leading skills (up to 5), not only the first</div>
<div><code>AskUserQuestion</code> dialogs no longer auto-continue by default; opt into an idle timeout via <code>/config</code></div>
<div>The "default" permission mode is now named "Manual" across the CLI, `--help`, VS Code, and JetBrains; `--permission-mode manual` is accepted alongside `default`</div>
<div>New <code>/dataviz</code> skill gives chart and dashboard design guidance, with a runnable color-palette validator</div>
<div>The built-in Explore agent now inherits the main session's model (capped at Opus) instead of running on Haiku</div>
<div>Background agents launched from <code>claude agents</code> now commit, push, and open a draft PR when they finish code work in a worktree, instead of stopping to ask</div>
<div>Hook matchers with hyphenated identifiers like <code>code-reviewer</code> now exact-match instead of substring-matching; use <code>mcp\_\_brave-search\_\_.\*</code> to match all tools from a hyphenated MCP server</div>
<div>Transient server rate-limit errors unrelated to your usage limit are now retried automatically with backoff for subscribers instead of failing the turn</div>
<div>The streaming idle watchdog is now on by default for all providers: it aborts and retries when a response stream produces no events for 5 minutes (<code>CLAUDE\_ENABLE\_STREAM\_WATCHDOG=0</code> to disable)</div>
</div>
</div>
[Full changelog for v2.1.195–v2.1.201 →](/docs/en/changelog#2-1-195)
whats-new/2026-w28 First recorded · 59 lines, first recorded
# Week 28 · July 6–10, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 28 · July 6–10, 2026
> Browse external sites from the Desktop app's built-in browser, run a full setup checkup with /doctor, and pick up auto mode transcript protections and agent view upgrades.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-202">v2.1.202 → v2.1.206</a></span>
<span>2 features · July 6–10</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">In-app browser on Desktop</span>
<span className="digest-feature-pill">Desktop</span>
</div>
<p className="digest-feature-lede">Claude Code on desktop now has a built-in browser. Claude can pull up docs, designs, or any other site, and read, click through, and interact with pages the same way it does with your local dev server previews. The browser is sandboxed and configurable: you choose whether browsing sessions persist, and safety classifiers review actions on external sites.</p>
<Frame>
<video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/x358isu_VzLnyTEN/images/whats-new/desktop-browser.mp4?fit=max&auto=format&n=x358isu_VzLnyTEN&q=85&s=8033e85a1cb0a37870a79e702c18f4e4" data-path="images/whats-new/desktop-browser.mp4" />
</Frame>
<a className="digest-feature-link" href="/docs/docs/en/desktop#browse-external-sites">Browse external sites</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">/doctor is a full setup checkup</span>
<span className="digest-feature-pill">v2.1.205</span>
</div>
<p className="digest-feature-lede"><code>/doctor</code> now diagnoses issues and can fix them, instead of printing a read-only report. It checks installation health, finds unused skills, MCP servers, and plugins versus their context cost, deduplicates local <code>CLAUDE.md</code> files against checked-in ones, proposes trimming <code>CLAUDE.md</code> content Claude could derive from the codebase, and flags slow hooks. It reports findings first and asks for confirmation before changing anything. <code>/checkup</code> is its alias.</p>
<p className="digest-feature-try">Run a checkup from any session:</p>
```text Claude Code theme={null}
> /doctor
```
<a className="digest-feature-link" href="/docs/docs/en/commands#all-commands">All commands</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div>Auto mode now blocks tampering with session transcript files, and asks before running <code>rm -rf</code> on a variable it can't resolve from context</div>
<div><code>/cd</code> now suggests directory paths as you type, matching <code>/add-dir</code></div>
<div><code>/commit-push-pr</code> auto-allows <code>git push</code> to the repo's configured push remote in addition to <code>origin</code></div>
<div>Gateway: <code>/login</code> now supports Anthropic-operated public gateway endpoints</div>
<div><code>EnterWorktree</code> asks for confirmation before entering a git worktree outside the project's <code>.claude/worktrees/</code> directory</div>
<div>Background agents upgrade to a new version in the background right after a Claude Code update, instead of paying a slow stale-session upgrade when you attach</div>
<div>Agent view rows now show a colored state word and a classifier-written headline instead of raw tool call text, and sessions that edit, merge, comment on, or push to an existing PR link it in <code>claude agents</code></div>
<div>Auto-update binary downloads now stream to disk instead of buffering in memory, cutting the updater's peak memory usage by roughly 400 MB</div>
<div>Background task notifications now explicitly state that no human input has occurred, preventing fabricated in-transcript approvals from being acted on</div>
<div>Improved <code>/code-review</code> findings quality on Opus 4.8 across all effort levels</div>
</div>
</div>
[Full changelog for v2.1.202–v2.1.206 →](/docs/en/changelog#2-1-202)
whats-new/2026-w29 First recorded · 66 lines, first recorded
# Week 29 · July 13–17, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 29 · July 13–17, 2026
> Pull live data into published artifacts through MCP connectors, and use Claude Code with a screen reader in the new screen reader mode.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-207">v2.1.207 → v2.1.212</a></span>
<span>2 features · July 13–17</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Artifacts call your MCP connectors</span>
<span className="digest-feature-pill">web</span>
</div>
<p className="digest-feature-lede">A published artifact can now call MCP connectors each time someone views it, so a dashboard shows live data and can take actions on demand rather than a snapshot from the session that built it. Each call runs through the viewing account's own connections, and viewers approve access before the page's first connector call. This week also adds public sharing links, editor roles for shared editing on Team and Enterprise plans, and artifacts created from Claude Tag sessions.</p>
<Frame>
<video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/ItzF3QVI6L0QypjJ/images/whats-new/artifacts-mcp.mp4?fit=max&auto=format&n=ItzF3QVI6L0QypjJ&q=85&s=ff8b81ed52b26c773899dc28cec959e6" data-path="images/whats-new/artifacts-mcp.mp4" />
</Frame>
<p className="digest-feature-try">Name the connector and the data you want in your prompt:</p>
```text title="Claude Code" wrap theme={null}
Build a dashboard artifact of open pull requests that pulls the live list through my GitHub connector when the page loads.
```
<a className="digest-feature-link" href="/docs/docs/en/artifacts#pull-live-data-with-mcp-connectors">Pull live data with MCP connectors</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Screen reader mode</span>
<span className="digest-feature-pill">CLI</span>
</div>
<p className="digest-feature-lede">Screen reader mode replaces the visual terminal interface with plain, linear text: instead of boxes, spinners, and in-place redraws, Claude Code prints labeled lines that a screen reader such as VoiceOver or NVDA reads in order, so you can approve permissions and review output end to end. Turn it on per session with a flag, per shell with the <code>CLAUDE\_AX\_SCREEN\_READER</code> environment variable, or everywhere with the <code>axScreenReader</code> setting.</p>
<p className="digest-feature-try">Start a session in screen reader mode:</p>
```bash terminal theme={null}
claude --ax-screen-reader
```
<a className="digest-feature-link" href="/docs/docs/en/accessibility#turn-on-screen-reader-mode">Turn on screen reader mode</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div><code>/fork</code> now copies your conversation into a new background session with its own row in <code>claude agents</code> while you keep working; the in-session forked subagent it used to launch is now <code>/subtask</code></div>
<div><a href="/docs/docs/en/permission-modes#enable-auto-mode-on-bedrock-agent-platform-or-foundry">Auto mode</a> no longer needs the <code>CLAUDE\_CODE\_ENABLE\_AUTO\_MODE</code> opt-in on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry; administrators can turn it off with <code>disableAutoMode</code></div>
<div>MCP tool calls that run longer than two minutes now move to the background automatically so the session stays usable; tune or disable the threshold with <code>CLAUDE\_CODE\_MCP\_AUTO\_BACKGROUND\_MS</code></div>
<div>New <code>claude auto-mode reset</code> restores the default auto-mode configuration, and `--yes` skips the confirmation prompt</div>
<div>New <a href="/docs/docs/en/corporate-launcher">corporate launcher</a> support: <code>CLAUDE\_CODE\_PROCESS\_WRAPPER</code> or the <code>processWrapper</code> setting runs the processes Claude Code starts from its own binary, such as the background service and agent view sessions, through a required wrapper executable</div>
<div><code>vimInsertModeRemaps</code> setting maps two-key insert-mode sequences such as <code>jj</code> to Escape in vim mode</div>
<div>`--forward-subagent-text` and <code>CLAUDE\_CODE\_FORWARD\_SUBAGENT\_TEXT</code> include subagent text and thinking blocks in <a href="/docs/docs/en/headless">stream-json output</a></div>
<div>Session-wide caps stop runaway loops: WebSearch calls and subagent spawns each default to 200, tunable with <code>CLAUDE\_CODE\_MAX\_WEB\_SEARCHES\_PER\_SESSION</code> and <code>CLAUDE\_CODE\_MAX\_SUBAGENTS\_PER\_SESSION</code></div>
<div>"Always allow" permission rules save at the repository root, so approvals granted in a git worktree persist across sessions and worktrees</div>
<div>Amazon Bedrock, Google Cloud's Agent Platform, and Claude Platform on AWS now default to Claude Opus 4.8</div>
<div>The collapsed tool summary line shows a live elapsed-time counter, so long-running tool calls visibly tick instead of looking stuck</div>
</div>
</div>
[Full changelog for v2.1.207–v2.1.212 →](/docs/en/changelog#2-1-207)
whats-new/2026-w30 First recorded · 87 lines, first recorded
# Week 30 · July 20–24, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 30 · July 20–24, 2026
> Opus 5 becomes the default Opus model, Claude Code Desktop adds an iOS Simulator pane, and the Claude Security plugin scans your code for vulnerabilities.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-214">v2.1.214 → v2.1.219</a></span>
<span>3 features · July 20–24</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Claude Opus 5</span>
<span className="digest-feature-pill">new model</span>
</div>
<p className="digest-feature-lede">Claude Opus 5 is the new default Opus model in Claude Code. It's the default on Max, Team Premium, Enterprise pay-as-you-go, and the Anthropic API, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform. On the Anthropic API and on Max, Team, and Enterprise plans, Opus 5 runs with a <a href="/docs/docs/en/model-config#extended-context">1M-token context window</a>; on Amazon Bedrock and Google Cloud's Agent Platform, select the 1M model variant. Fast mode moves to Opus 5 at \$10/\$50 per MTok. Requires v2.1.219 or later.</p>
<Frame>
<video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/opus-5.mp4?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=8536b1cb3180e539008f39930403e47b" data-path="images/whats-new/opus-5.mp4" />
</Frame>
<p className="digest-feature-try">Switch to Opus 5 by name, or pick it from the model picker:</p>
```text Claude Code theme={null}
> /model claude-opus-5
```
<a className="digest-feature-link" href="/docs/docs/en/model-config#available-models">Model configuration</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">iOS Simulator in Claude Code Desktop</span>
<span className="digest-feature-pill">Desktop</span>
</div>
<p className="digest-feature-lede">Claude Code Desktop on macOS gets an iOS Simulator pane, in public beta on Pro, Max, and Team plans. When Claude builds, launches, or checks your app in a simulator, the pane opens next to the conversation and streams the device screen live, so you can watch Claude tap through the app to verify its changes or drive the device yourself. Requires Xcode with the iOS platform installed, and Claude Desktop v1.24012.0 or later.</p>
<Frame>
<img className="w-full" src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/ios-simulator.jpg?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=6c88418ed14ed0fb12cc1af75b17f2ee" alt="Claude Code Desktop with the iOS Simulator pane showing an iPhone app next to the conversation" width="2048" height="1152" data-path="images/whats-new/ios-simulator.jpg" />
</Frame>
<p className="digest-feature-try">Ask Claude to run or test your app, and the pane opens when the app launches:</p>
```text Claude Code theme={null}
> Build the app and run it in the simulator to check the onboarding flow.
```
<a className="digest-feature-link" href="/docs/docs/en/desktop-ios-simulator#run-your-app-in-the-simulator">Test iOS apps in the simulator</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Claude Security plugin</span>
<span className="digest-feature-pill">plugin</span>
</div>
<p className="digest-feature-lede">The Claude Security plugin runs a multi-agent vulnerability scan of your codebase inside a Claude Code session: agents map your architecture, build a threat model, hunt for vulnerabilities, and independently review every finding before writing the report to a <code>CLAUDE-SECURITY-\<timestamp>/</code> directory. Scan a whole repository or only a branch's diff, a pull request, or a single commit, then turn the findings you choose into reviewed patches that you apply yourself.</p>
<p className="digest-feature-try">Install the plugin from the official Anthropic marketplace, run <code>/reload-plugins</code>, then start a scan with <code>/claude-security</code>:</p>
```text Claude Code theme={null}
> /plugin install claude-security@claude-plugins-official
```
<a className="digest-feature-link" href="/docs/docs/en/claude-security#scan-and-fix-your-codebase">Scan and fix your codebase</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div><a href="/docs/docs/en/code-review#review-a-diff-locally"><code>/code-review</code></a> now runs as a background subagent with its own context window, so review work stays out of your conversation and the findings arrive when it completes</div>
<div><code>/verify</code>, <code>/code-review</code>, and <code>/deep-research</code> run only when you invoke them; Claude no longer launches them on its own</div>
<div><a href="/docs/docs/en/interactive-mode#emoji-shortcodes">Emoji shortcodes</a> autocomplete in the prompt input: type <code>:heart:</code> to insert an emoji, or two or more characters after <code>:</code> for suggestions; turn it off with <code>emojiCompletionEnabled</code></div>
<div>Skills with <code>context: fork</code> <a href="/docs/docs/en/skills#run-skills-in-a-subagent">run in the background</a> by default, and <code>background: false</code> in the skill's frontmatter waits for the result in the same turn</div>
<div>A session runs up to 20 subagents concurrently by default; change the <a href="/docs/docs/en/sub-agents#concurrent-subagent-limit">limit</a> with <code>CLAUDE\_CODE\_MAX\_CONCURRENT\_SUBAGENTS</code></div>
<div>`--max-budget-usd` now enforces the cap on subagents: once spend reaches it, Claude can't start more and running background subagents stop</div>
<div>New <a href="/docs/docs/en/sandboxing#disable-filesystem-isolation"><code>sandbox.filesystem.disabled</code></a> setting skips filesystem isolation while keeping network egress control</div>
<div>In auto mode, the checks for dangerous <code>rm</code> commands, background jobs, and suspicious Windows paths no longer open permission dialogs; the auto-mode classifier adjudicates them instead</div>
<div>Bash permission checks fail closed on more shell forms, including file-descriptor redirects, Zsh variable subscripts in <code>\[\[ ]]</code> comparisons, <code>help</code> and <code>man</code> invocations that could run unsafe options, and commands over 10,000 characters</div>
<div><a href="/docs/docs/en/fast-mode">Fast mode</a> no longer supports Opus 4.7: <code>/fast</code> now applies to Opus 5 and Opus 4.8</div>
<div>Long-running tool calls emit a periodic progress heartbeat instead of going silent</div>
</div>
</div>
[Full changelog for v2.1.214–v2.1.219 →](/docs/en/changelog#2-1-214)
whats-new/2026-w32 First recorded · 99 lines, first recorded
# Week 32 · August 3–7, 2026
The first capture of this source. The page was already there, and this is what it said.
# Week 32 · August 3–7, 2026
> Claude Code sessions message each other, self-hosted environments run cloud sessions on your infrastructure, and auto mode becomes the default permission mode.
<div className="digest-meta">
<span>Releases <a href="/docs/docs/en/changelog#2-1-220">v2.1.220 → v2.1.224</a></span>
<span>3 features · August 3–7</span>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Cross-session messaging</span>
<span className="digest-feature-pill">v2.1.224</span>
</div>
<p className="digest-feature-lede">Your Claude Code sessions can now message each other. Claude discovers your other sessions with the <code>ListAgents</code> tool and sends with <code>SendMessage</code>, either when you ask it to or on its own, such as after a change in one session affects what another is working on. A message is text Claude writes for the other session, never your conversation history or files. Available on macOS and Linux. Requires v2.1.224 or later.</p>
<Frame>
<video autoPlay muted loop playsInline className="w-full" src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/cross-session-messaging.mp4?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=8f33c3390f78660a4a26dc980f46159f" data-path="images/whats-new/cross-session-messaging.mp4" />
</Frame>
<p className="digest-feature-try">With two sessions open on the same machine, ask one of them to pass something along:</p>
```text title="Claude Code" wrap theme={null}
Tell the session working on the payments API that users.name is now users.display_name
```
<p className="digest-feature-try">The other session shows a <code>Message from</code> row once Claude has read the message; press <code>Ctrl+O</code> to expand it. To see which sessions Claude can reach, run <code>/list-agents</code>.</p>
<a className="digest-feature-link" href="/docs/docs/en/cross-session-messaging#message-another-session">Message another session</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Self-hosted environments</span>
<span className="digest-feature-pill">v2.1.224</span>
</div>
<p className="digest-feature-lede">Self-hosted environments run Claude Code cloud sessions on your organization's own infrastructure, in public beta on Team and Enterprise plans. Run <code>claude self-hosted-runner</code> on your machines or containers to turn them into runners. When someone picks your environment while starting a session from claude.ai, the mobile or desktop apps, or `claude --cloud`, that session runs inside your network, with access to your internal services. An Owner or admin turns on <strong>Allow self-hosted environments</strong> in <a href="https://claude.ai/admin-settings/cloud-environments">admin settings</a> first.</p>
<Frame>
<img className="w-full" src="https://mintcdn.com/claude-code/N3yEaTYPXMXFrF6k/images/whats-new/self-hosted-environments.jpg?fit=max&auto=format&n=N3yEaTYPXMXFrF6k&q=85&s=ae9152cb1670c8af517d1aee57689b14" alt="The self-hosted environments admin page listing environments such as linux-dev and macos-prod with their status and active session counts" width="2048" height="1152" data-path="images/whats-new/self-hosted-environments.jpg" />
</Frame>
<p className="digest-feature-try">Signed in as an Owner or admin, run the guided setup, which walks you through creating the environment and starts a runner:</p>
```bash terminal theme={null}
claude self-hosted-runner setup
```
<p className="digest-feature-try">The environment shows <strong>Healthy</strong> in admin settings once the runner registers.</p>
<a className="digest-feature-link" href="/docs/docs/en/self-hosted-environments-quickstart#set-up-an-environment-and-runner">Self-hosted environments quickstart</a>
</div>
<div className="digest-feature">
<div className="digest-feature-header">
<span className="digest-feature-title">Auto mode becomes the default</span>
<span className="digest-feature-pill">CLI</span>
</div>
<p className="digest-feature-lede">Starting August 14, auto mode is the default permission mode for new sessions on Pro, Max, and Team plans. If you set a default mode yourself, it stays in place unless you accept the one-time switch prompt, and a default your organization manages doesn't change. You can still switch modes at any time. Already in effect on those plans: the classifier calls auto mode makes no longer count toward your usage limits.</p>
<p className="digest-feature-try">To start every session in auto mode before the switch, set it as your default in your user settings:</p>
```json ~/.claude/settings.json {3} theme={null}
{
"permissions": {
"defaultMode": "auto"
}
}
```
<p className="digest-feature-try">New sessions then show <code>auto mode on</code> in the status bar.</p>
<a className="digest-feature-link" href="/docs/docs/en/permission-modes#eliminate-prompts-with-auto-mode">Auto mode requirements and controls</a>
</div>
<div className="digest-wins">
<p className="digest-wins-title">Other wins</p>
<div className="digest-wins-grid">
<div>The VS Code extension gets <a href="/docs/docs/en/vs-code#extension-settings">Focus view</a>, which hides tool activity behind one expandable row per turn; toggle it from the command menu or with <code>Ctrl+Alt+F</code> (<code>Ctrl+Option+F</code> on Mac)</div>
<div>Sandbox credential files accept <a href="/docs/docs/en/sandboxing#mask-credential-files"><code>mode: "mask"</code></a> on Linux and WSL2, so sandboxed commands read a sentinel copy while the sandbox proxy substitutes the real value on egress; credential masking also gains <code>extract</code>, JWT-aware <code>decode</code>, and AWS SigV4 re-signing options</div>
<div>Marketplaces can distribute a plugin as a <a href="/docs/docs/en/plugin-marketplaces#zip-archives">zip archive</a> with the new <code>archive</code> source, downloaded over HTTPS with an optional SHA-256 pin, so installs work without git or npm</div>
<div><code>/review</code> is now an alias of <a href="/docs/docs/en/code-review#review-a-diff-locally"><code>/code-review</code></a>, and <code>/code-review</code> with no effort level reuses the level you typed last</div>
<div>A session you copy with <a href="/docs/docs/en/agent-view#copy-the-session-with-%2Ffork"><code>/fork</code></a> now makes its code changes in a worktree of its own instead of the original session's checkout</div>
<div>Plugins you install from <a href="/docs/docs/en/discover-plugins#install-plugins"><code>/plugin</code></a> activate in the current session when it's safe to do so; the install summary reports <code>Plugin is now active.</code> or tells you to run <code>/reload-plugins</code></div>
<div><a href="/docs/docs/en/agent-view#how-file-edits-are-isolated">Background sessions</a> that changed code in a worktree now commit and push before finishing, open a draft pull request only when the task calls for one, and follow the git instructions in your <code>CLAUDE.md</code></div>
<div>The 200-subagent-per-session cap is removed, so long-running sessions no longer refuse new subagents; the <a href="/docs/docs/en/sub-agents#concurrent-subagent-limit">concurrency</a> and depth limits still apply</div>
<div>A repository's checked-in settings can no longer turn on <a href="/docs/docs/en/remote-control#enable-remote-control-for-all-sessions">Remote Control auto-connect</a>; set <code>remoteControlAtStartup</code> in your user or managed settings instead, and project and local settings can only turn it off</div>
<div><a href="/docs/docs/en/worktrees#how-claude-code-enforces-isolation">Worktree isolation</a> now blocks not only file edits but also Bash commands and git redirects that reach the main checkout, in every session type and in the session's subagents</div>
<div>A Bash command can no longer hide part of itself from permission checks, and tab or invisible-Unicode padding no longer hides part of a command from the approval dialog</div>
<div>PreToolUse auto-allow hooks no longer bypass tool restrictions in Claude Code's internal side tasks such as summaries and compaction</div>
<div>The <a href="/docs/docs/en/ultraplan">Ultraplan</a> research preview is removed, including the <code>/ultraplan</code> command and the <code>ultraplan</code> keyword; use plan mode or Claude Code on the web instead</div>
</div>
</div>
[Full changelog for v2.1.220–v2.1.224 →](/docs/en/changelog#2-1-220)
whats-new/index First recorded · 157 lines, first recorded
# What's new
The first capture of this source. The page was already there, and this is what it said.
# What's new
> A weekly digest of notable Claude Code features, with code snippets, demos, and context on why they matter.
The weekly dev digest highlights the features most likely to change how you work. Each entry includes runnable code, a short demo, and a link to the full docs. For every bug fix and minor improvement, see the [changelog](/docs/en/changelog).
<Update label="Week 32" description="August 3–7, 2026" tags={["v2.1.220–v2.1.224"]}>
**Cross-session messaging**: on macOS and Linux, your Claude Code sessions can now message each other, so Claude passes a finding or a decision from one session to another instead of you re-explaining it.
Also this week: **self-hosted environments** run Claude Code cloud sessions on infrastructure your organization operates, in public beta on Team and Enterprise plans; **auto mode** becomes the default permission mode for new sessions on Pro, Max, and Team plans starting August 14; and the **VS Code extension** gets Focus view.
[Read the Week 32 digest →](/docs/en/whats-new/2026-w32)
</Update>
<Update label="Week 30" description="July 20–24, 2026" tags={["v2.1.214–v2.1.219"]}>
**Claude Opus 5**: the new default Opus model in Claude Code, with a 1M-token context window and fast mode at \$10/\$50 per MTok.
Also this week: **Claude Code Desktop** opens an iOS Simulator pane in public beta so Claude can run your app and tap through it while you watch; the **Claude Security plugin** runs a multi-agent vulnerability scan of your codebase and turns the findings you pick into patches you apply yourself; and **`/code-review`** runs as a background subagent.
[Read the Week 30 digest →](/docs/en/whats-new/2026-w30)
</Update>
<Update label="Week 29" description="July 13–17, 2026" tags={["v2.1.207–v2.1.212"]}>
**Artifacts call your MCP connectors**: a published artifact can pull live data and take actions through each viewer's own MCP connectors when they open the page, and this week also adds public sharing links, editor roles on Team and Enterprise, and artifacts created from Claude Tag sessions.
Also this week: **screen reader mode** replaces the visual terminal interface with plain, linear text for screen readers such as VoiceOver and NVDA; **`/fork`** copies your conversation into a new background session while you keep working; and **auto mode** no longer needs an opt-in variable on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry.
[Read the Week 29 digest →](/docs/en/whats-new/2026-w29)
</Update>
<Update label="Week 28" description="July 6–10, 2026" tags={["v2.1.202–v2.1.206"]}>
**In-app browser on Desktop**: Claude Code on desktop gets a built-in browser, so Claude can pull up docs, designs, or any other site and interact with pages the same way it does with your local dev server previews.
Also this week: **`/doctor`** is a full setup checkup that diagnoses issues and can fix them, with `/checkup` as its alias; **auto mode** blocks transcript tampering and asks before `rm -rf` on unresolved variables; and **agent view rows** show a colored state word and a classifier-written headline.
[Read the Week 28 digest →](/docs/en/whats-new/2026-w28)
</Update>
<Update label="Week 27" description="June 29 – July 3, 2026" tags={["v2.1.195–v2.1.201"]}>
**Claude Sonnet 5**: the new default model for Pro, Team Standard, and Enterprise subscription seats, with top-tier coding and tool use at Sonnet pricing, a native 1M-token context window, and adaptive thinking on by default.
Also this week: **Claude in Chrome** is generally available on all direct Anthropic plans; **subagents run in the background by default** so Claude keeps working while they run; **Claude Desktop on Linux** lands in beta on Ubuntu and Debian; and **`/radio`** tunes into Claude FM lo-fi radio.
[Read the Week 27 digest →](/docs/en/whats-new/2026-w27)
</Update>
<Update label="Week 26" description="June 22–26, 2026" tags={["v2.1.185–v2.1.193"]}>
**`claude mcp login`**: authenticate a configured MCP server from your shell instead of the interactive `/mcp` menu, and clear its stored credentials later with `claude mcp logout`.
Also this week: **shell mode responds to command output** (`! npm test` gets an explanation without a second prompt); **`/rewind`** can resume a conversation from before `/clear` was run; and **background subagents** now surface permission prompts in the main session instead of auto-denying.
[Read the Week 26 digest →](/docs/en/whats-new/2026-w26)
</Update>
<Update label="Week 25" description="June 15–19, 2026" tags={["v2.1.178–v2.1.183"]}>
**Artifacts**: turn a session's output into a live, shareable page on claude.ai that updates in place as the session works, now in beta on Team and Enterprise plans.
Also this week: **deny and ask rules match tool parameters** with `Tool(param:value)`, for example `Agent(model:opus)`; **`/config key=value`** sets any setting from the prompt, in `-p` mode, and from Remote Control; and **auto mode blocks destructive git commands** when you didn't ask to discard local work.
[Read the Week 25 digest →](/docs/en/whats-new/2026-w25)
</Update>
<Update label="Week 24" description="June 8–12, 2026" tags={["v2.1.166–v2.1.176"]}>
**`/cd`**: move the current session to a new working directory mid-conversation without rebuilding the prompt cache.
Also this week: **sub-agents can spawn their own sub-agents** (background chains are capped at five levels deep); **`--safe-mode`** starts Claude Code with all customizations disabled for troubleshooting; and **`fallbackModel`** configures up to three fallback models tried in order.
[Read the Week 24 digest →](/docs/en/whats-new/2026-w24)
</Update>
<Update label="Week 23" description="June 1–5, 2026" tags={["v2.1.158–v2.1.165"]}>
**Auto mode on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry**: auto mode is now available on third-party providers for Opus 4.7 and Opus 4.8, replacing permission prompts with background safety checks.
Also this week: **safer automatic edits** prompt before writing files that can run code in `acceptEdits` mode; **`/plugin list`** prints your installed plugins inline; and **version requirements** let managed deployments require an approved Claude Code version range.
[Read the Week 23 digest →](/docs/en/whats-new/2026-w23)
</Update>
<Update label="Week 22" description="May 25–29, 2026" tags={["v2.1.150–v2.1.157"]}>
**Claude Opus 4.8**: the new default model for Max, Team Premium, Enterprise pay-as-you-go, and Anthropic API accounts, with high effort by default and `/effort xhigh` for the hardest tasks.
Also this week: **dynamic workflows** orchestrate dozens to hundreds of subagents from a script Claude writes; the **security-guidance plugin** reviews Claude's changes for vulnerabilities as it works; and **fast mode** runs on Opus 4.8 at \$10/\$50 per MTok.
[Read the Week 22 digest →](/docs/en/whats-new/2026-w22)
</Update>
<Update label="Week 21" description="May 18–22, 2026" tags={["v2.1.143–v2.1.149"]}>
**Auto mode on the Pro plan**: auto mode now runs on Pro accounts and supports Sonnet 4.6 alongside Opus, replacing permission prompts with background safety checks.
Also this week: **`/usage`** breaks down what drives your plan limits by skill, subagent, plugin, and MCP server; the new **`/code-review`** command reports correctness bugs; and **background sessions** appear in `/resume` and stay alive when pinned.
[Read the Week 21 digest →](/docs/en/whats-new/2026-w21)
</Update>
<Update label="Week 20" description="May 11–15, 2026" tags={["v2.1.139–v2.1.142"]}>
**Agent view**: `claude agents` opens one screen for every Claude Code session, showing what's running, what's blocked on you, and what's done.
Also this week: **`/goal`** keeps Claude working across turns until a completion condition holds; **fast mode** now runs on Opus 4.7 by default; and the **Rewind menu** can compress earlier context with "Summarize up to here".
[Read the Week 20 digest →](/docs/en/whats-new/2026-w20)
</Update>
<Update label="Week 19" description="May 4–8, 2026" tags={["v2.1.128–v2.1.136"]}>
**Plugins load from `.zip` archives and URLs**: `--plugin-dir` now accepts `.zip` files, and `--plugin-url` fetches a plugin archive for the current session.
Also this week: **`worktree.baseRef`** chooses whether new worktrees branch from the remote default or local `HEAD`; **auto mode hard deny rules** block actions unconditionally regardless of allow exceptions; and **hooks see the active effort level** via `effort.level` and `$CLAUDE_EFFORT`.
[Read the Week 19 digest →](/docs/en/whats-new/2026-w19)
</Update>
<Update label="Week 18" description="April 27 – May 1, 2026" tags={["v2.1.120–v2.1.126"]}>
**Windows without Git Bash**: Git for Windows is no longer required, and Claude Code uses PowerShell as the shell tool when Bash is absent.
Also this week: **`claude ultrareview`** brings cloud code review to CI and scripts; **`claude project purge`** cleans up local state for a project; and pasting a **PR URL into `/resume`** finds the session that created it.
[Read the Week 18 digest →](/docs/en/whats-new/2026-w18)
</Update>
<Update label="Week 17" description="April 20–24, 2026" tags={["v2.1.114–v2.1.119"]}>
**`/ultrareview`** opens as a public research preview: a fleet of bug-hunting agents runs in the cloud and findings land back in your CLI or Desktop automatically.
Also this week: **session recap** shows you what happened while a terminal was unfocused; **custom themes** let you build and ship color palettes from `/theme` or a plugin; and **Claude Code on the web** gets a redesign with a new sessions sidebar and drag-and-drop layout.
[Read the Week 17 digest →](/docs/en/whats-new/2026-w17)
</Update>
<Update label="Week 16" description="April 13–17, 2026" tags={["v2.1.105–v2.1.113"]}>
**Claude Opus 4.7** lands as the new default on Max and Team Premium, with a new `xhigh` effort level that's the recommended setting for most coding work and an interactive `/effort` slider to dial it in.
Also this week: **Routines** on Claude Code on the web fire templated cloud agents from a schedule, GitHub event, or API call; **mobile push notifications** ping your phone when a long task finishes or Claude needs you; `/usage` shows what's driving your limits; and the CLI moves to native binaries.
[Read the Week 16 digest →](/docs/en/whats-new/2026-w16)
</Update>
<Update label="Week 15" description="April 6–10, 2026" tags={["v2.1.92–v2.1.101"]}>
**Ultraplan** enters early preview: draft a plan in the cloud from your CLI, review and comment on it in a web editor, then run it remotely or pull it back local. The first run now auto-creates a cloud environment for you.
Also this week: the **Monitor** tool streams background events into the conversation so Claude can tail logs and react live, `/loop` self-paces when you omit the interval, `/team-onboarding` packages your setup into a replayable guide, and `/autofix-pr` turns on PR auto-fix from your terminal.
[Read the Week 15 digest →](/docs/en/whats-new/2026-w15)
</Update>
<Update label="Week 14" description="March 30 – April 3, 2026" tags={["v2.1.86–v2.1.91"]}>
**Computer use** comes to the CLI in research preview: Claude can open native apps, click through UI, and verify changes from your terminal. Best for closing the loop on things only a GUI can verify.
Also this week: `/powerup` interactive lessons, flicker-free alt-screen rendering, a per-tool MCP result-size override up to 500K, and plugin executables on the Bash tool's `PATH`.
[Read the Week 14 digest →](/docs/en/whats-new/2026-w14)
</Update>
<Update label="Week 13" description="March 23–27, 2026" tags={["v2.1.83–v2.1.85"]}>
**Auto mode** lands in research preview: a classifier handles your permission prompts so safe actions run without interruption and risky ones get blocked. The middle ground between approving everything and `--dangerously-skip-permissions`.
Also this week: computer use in the Desktop app, PR auto-fix on Web, transcript search with `/`, a native PowerShell tool for Windows, and conditional `if` hooks.
[Read the Week 13 digest →](/docs/en/whats-new/2026-w13)
</Update>
workflows First recorded · 407 lines, first recorded
# Orchestrate subagents at scale with dynamic workflows ## When to use a workflow ## Run a bundled workflow ### Bundled workflows ### Watch the run ## Have Claude write a workflow ### Ask for a workflow in your prompt #### Dismiss or turn off the keyword #### Where the keyword works ### Let Claude decide with ultracode ### Approve the plan before it runs ### Save the workflow for reuse ### Distribute a workflow in a plugin ### Pass input to a saved workflow ## Example workflow prompts ### Audit many files for the same issue ### Keep fixing until a check passes ### Migrate many files in parallel ### Review every changed file and write one summary ### Research a topic across many sources ### Find issues until the list stops growing ### What the saved script looks like ## How a workflow runs ### Prompt caching in a fan-out ### Behavior and limits ## Manage runs ### Resume after a pause ### Cost ### Set a size guideline ### Turn workflows off ## Related resources
The first capture of this source. The page was already there, and this is what it said.
# Orchestrate subagents at scale with dynamic workflows
> Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.
<Note>
Dynamic workflows require Claude Code v2.1.154 or later and are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`.
</Note>
A dynamic workflow is a JavaScript script that orchestrates [subagents](/docs/en/sub-agents) at scale. Claude writes the script for the task you describe, and a runtime executes it in the background while your session stays responsive.
Reach for a workflow when a task needs more agents than one conversation can coordinate, or when you want the orchestration codified as a script you can read and rerun. Examples include a codebase-wide bug sweep, a 500-file migration, a research question that needs sources cross-checked against each other, and a hard plan worth drafting from several independent angles before you commit to one.
## When to use a workflow
[Subagents](/docs/en/sub-agents), [skills](/docs/en/skills), [agent teams](/docs/en/agent-teams), and workflows can all run a multi-step task. The difference is who holds the plan:
| | Subagents | Skills | Agent teams | Workflows |
| :------------------------------ | :----------------------------- | :--------------------------- | :------------------------------------- | :----------------------------------- |
| What it is | A worker Claude spawns | Instructions Claude follows | A lead agent supervising peer sessions | A script the runtime executes |
| Who decides what runs next | Claude, turn by turn | Claude, following the prompt | The lead agent, turn by turn | The script |
| Where intermediate results live | Claude's context window | Claude's context window | A shared task list | Script variables |
| What's repeatable | The worker definition | The instructions | The team definition | The orchestration itself |
| Scale | A few delegated tasks per turn | Same as subagents | A handful of long-running peers | Dozens to hundreds of agents per run |
| Interruption | Restarts the turn | Restarts the turn | Teammates keep running | Resumable in the same session |
A workflow moves the plan into code. With subagents, skills, and agent teams, Claude is the orchestrator: it decides turn by turn what to spawn or assign next, and every result lands in a context window. A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.
Moving the plan into code also lets a workflow apply a repeatable quality pattern, not just run more agents: it can have independent agents adversarially review each other's findings before they're reported, or draft a plan from several angles and weigh them against each other, so you get a more trustworthy result than a single pass.
## Run a bundled workflow
The quickest way to see a workflow in action is to run `/deep-research`, the [built-in workflow](#bundled-workflows) Claude Code includes for investigating a question across many sources. You'll see agents work through a set of phases in the background while your session stays free, and get one report at the end instead of a turn-by-turn transcript.
<Steps>
<Step title="Run the workflow">
Run `/deep-research` with a question you want investigated. It fans out web searches across several angles, fetches and cross-checks the sources it finds, and synthesizes a cited report.
```text wrap theme={null}
/deep-research What changed in the Node.js permission model between v20 and v22?
```
</Step>
<Step title="Allow workflows">
Claude Code asks whether to allow the workflow. Select **Yes** to continue. The exact prompt depends on your permission mode. See [Approve the plan before it runs](#approve-the-plan-before-it-runs) for the per-mode options.
</Step>
<Step title="Watch progress">
The run starts in the background. Run `/workflows`, use the arrow keys to select the run, and press Enter to open its progress view:
```text wrap theme={null}
/workflows
```
The view shows each phase with its agent count, token total, and elapsed time. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-run) for the full set of controls.
You can also watch from the task panel below the input box: a one-line progress summary appears there while the run is going. Press the down arrow to focus it, then Enter to expand.
</Step>
<Step title="Read the report">
When the run finishes, the report lands in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
</Step>
</Steps>
To run a workflow for your own task, [have Claude write one](#have-claude-write-a-workflow), and once a run does what you wanted you can [save it](#save-the-workflow-for-reuse) as a command of your own.
### Bundled workflows
Claude Code includes `/deep-research` as a built-in workflow:
| Command | What it does |
| :-------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `/deep-research <question>` | Fans out web searches on a question across several angles, fetches and cross-checks the sources it finds, votes on each claim, and returns a cited report with claims that didn't survive cross-checking filtered out. Requires the [WebSearch tool](/docs/en/tools-reference#websearch-tool-behavior) to be available |
`/deep-research` runs only when you invoke it.
[Workflows you save](#save-the-workflow-for-reuse) yourself become commands the same way and appear in `/` autocomplete alongside the bundled ones.
### Watch the run
Workflows run in the background, so the session stays responsive while agents work. Run `/workflows` at any time to list running and completed workflows, then select one to open its progress view.
```text wrap theme={null}
/workflows
```
The progress view shows each phase with its agent counts, token totals, and elapsed time. The footer lists the key for each action:
| Key | Action |
| :------------- | :-------------------------------------------------------------------------------------------------------------------------- |
| `↑` / `↓` | Select a phase or agent |
| `Enter` or `→` | Drill into the selected phase, then into an agent to read its prompt, recent tool calls, and result |
| `Esc` or `←` | Back out one level. In v2.1.203 through v2.1.205, `←` didn't step back out of a phase or agent; use `Esc` on those versions |
| `j` / `k` | Scroll within the agent detail when it overflows |
| `f` | Filter the agent list in the selected phase by status. Press again to cycle |
| `p` | Pause or resume the run |
| `x` | Stop the selected agent, or stop the whole workflow when focus is on the run |
| `r` | Restart the selected running agent |
| `s` | [Save](#save-the-workflow-for-reuse) the run's script as a command |
## Have Claude write a workflow
You can have Claude write a workflow for your task in two ways:
* [Ask for a workflow](#ask-for-a-workflow-in-your-prompt) in your prompt, either in your own words or by including the keyword `ultracode`, and Claude writes one for the task.
* [Let Claude decide with ultracode](#let-claude-decide-with-ultracode): set `/effort ultracode` and Claude plans a workflow for every substantive task in the session.
You can also run a workflow command that already exists: a [bundled workflow](#bundled-workflows) like `/deep-research`, or one you've [saved](#save-the-workflow-for-reuse).
### Ask for a workflow in your prompt
To run a single task as a workflow without changing the session's effort level, include the keyword `ultracode` in your prompt. Asking in your own words, for example "use a workflow" or "run a workflow", also works: Claude treats a direct request as the same opt-in. Before v2.1.160 the literal trigger keyword was `workflow`; natural-language requests work in both versions.
```text wrap theme={null}
ultracode: audit every API endpoint under src/routes/ for missing auth checks
```
Claude Code highlights the keyword in your input and Claude writes a workflow script for the task instead of working through it turn by turn. The keyword only chooses how Claude structures the work: a workflow started this way runs inside the session's existing [permission mode](/docs/en/permission-modes), and its agents' tool calls receive the same permission checks and [sandboxing](/docs/en/sandboxing) as any other tool call in the session.
If the run does what you wanted, you can [save it as a command](#save-the-workflow-for-reuse) afterward. If you already have an orchestrator built another way, such as a folder of subagent prompts or a skill that fans work out, you can point Claude at it and ask for a workflow that does the same thing.
#### Dismiss or turn off the keyword
If you didn't mean to start a workflow, press `Option+W` on macOS or `Alt+W` on Windows and Linux to dismiss the highlight for this prompt, or press backspace while the cursor is right after the highlighted keyword. To stop the keyword from triggering at all, turn off Ultracode keyword trigger in `/config`.
#### Where the keyword works
The keyword is an opt-in only in a prompt you type yourself: at the interactive prompt, in an IDE extension panel, in a [Remote Control](/docs/en/remote-control) client, or in an Agent SDK application that stamps your keyboard input's [`origin`](/docs/en/agent-sdk/typescript#sdkmessageorigin) as `{ kind: "human" }`. It doesn't start a workflow when it reaches the session another way:
* a prompt passed with `-p`
* a prompt an Agent SDK application sends without stamping it as human input
* a scheduled task prompt
* a webhook payload or pull request comment relayed into the conversation
<Note>
Before v2.1.210, the keyword started a workflow from any of these routes too, including a webhook payload or pull request comment relayed into the conversation.
</Note>
### Let Claude decide with ultracode
Ultracode is a Claude Code setting that combines `xhigh` [reasoning effort](/docs/en/model-config#adjust-effort-level) with automatic workflow orchestration. With it on, Claude plans a workflow for each substantive task instead of waiting for you to ask.
```text wrap theme={null}
/effort ultracode
```
To start a session with ultracode already on, launch with `claude --effort ultracode`. Requires Claude Code v2.1.203 or later.
With ultracode on, Claude decides when a task warrants a workflow. A single request can turn into several workflows in a row: one to understand the code, one to make the change, and one to verify it. This applies to every task in the session, so each request uses more tokens and takes longer than at lower effort levels.
Ultracode lasts for the current session and resets when you start a new one. Drop back with `/effort high` when you return to routine work. It's available on models that support `xhigh` [effort](/docs/en/model-config#adjust-effort-level); on other models the `/effort` menu doesn't offer it.
### Approve the plan before it runs
In the CLI, the per-run prompt shows the planned phases and these options:
* **Yes, run it**: start the run
* **Yes, and don't ask again for `<name>` in `<path>`**: start, and skip this prompt for this workflow in this project from now on
* **View raw script**: read the script before deciding
* **No**: cancel
`Ctrl+G` opens the script in your editor. `Tab` lets you adjust the prompt before the run starts.
Whether you see this prompt depends on your [permission mode](/docs/en/permission-modes):
| Permission mode | When you're prompted |
| :----------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Default, accept edits | Every run, unless you've selected **Yes, and don't ask again** for that workflow in this project |
| Auto | First launch only. Any **Yes** records consent in your user settings, and later launches start without prompting. Skipped entirely when ultracode is on |
| Bypass permissions, `claude -p`, Agent SDK | Never. The run starts immediately |
In the Desktop app, an approval card shows the workflow name, the phase list, and a token-usage caution, with **Once**, **Always**, and **Deny** actions. The progress view appears in the Background tasks side pane.
Your permission mode controls only the launch prompt above. The subagents the workflow spawns always run in `acceptEdits` mode and inherit your [tool allowlist](/docs/en/settings#permission-settings), regardless of your session's mode. File edits are auto-approved.
Shell commands, web fetches, and MCP tools that aren't in your allowlist can still prompt you mid-run. To avoid this on a long run, add the commands the agents need to your allowlist before starting.
In `claude -p` and the Agent SDK there is no one to prompt, so tool calls follow your configured permission rules without interactive confirmation.
### Save the workflow for reuse
When Claude writes a workflow for a task you'll repeat, you can save that run's script as a command. A process like a review you run on every branch then runs the same orchestration each time.
Run `/workflows`, select the run you want to keep, and press `s`. In the save dialog, Tab toggles between the two save locations:
* `.claude/workflows/` in your project: shared with everyone who clones the repo
* `~/.claude/workflows/` in your home directory: available in every project, visible only to you. If you set [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars), this location is the `workflows/` directory under that path.
The save dialog shows the resolved path for the personal location.
Press Enter to save. The workflow runs as `/<name>` in future sessions from either location.
Claude Code checks the save location for symlinks before writing, and shows an error instead of writing through one. What it checks depends on where you save:
* Project location: Claude Code refuses if `.claude`, `.claude/workflows`, or the target file is a symlink.
* Personal location: Claude Code refuses only if the target file itself is a symlink, so a `~/.claude` directory managed by a dotfiles tool still works.
Before v2.1.216, Claude Code followed the link, which could place the file outside the location you chose.
In a monorepo with several `.claude/` directories, you can keep workflows alongside the package they apply to. As of v2.1.178, saving to the project location writes to the closest `.claude/workflows/` directory that already exists between your working directory and the repository root, or to the repository root if none exists yet. Project workflows also load from every `.claude/workflows/` along that path, and when more than one defines the same name Claude Code runs the one closest to the working directory.
If a project workflow and a personal workflow share a name, the project one runs.
### Distribute a workflow in a plugin
To share a workflow across teams or repositories, include it in a [plugin](/docs/en/plugins). Place the script in a `workflows/` directory at the plugin root, or point to a different location with the [`workflows` manifest field](/docs/en/plugins-reference#component-path-fields).
Plugin workflows are namespaced by the plugin name. A plugin called `acme-tools` containing a script whose `meta.name` is `release-audit` runs as `/acme-tools:release-audit`.
### Pass input to a saved workflow
A saved workflow can accept input through the `args` parameter. The script reads it as a global named `args`. Use this to supply a research question, a list of target paths, or a configuration object at invocation time instead of editing the script for each run.
The following prompt runs a saved workflow with a list of issue numbers:
```text wrap theme={null}
Run /triage-issues on issues 1024, 1025, and 1030
```
Claude passes the list as structured data, so the script can call array and object methods on `args` directly without parsing it first. If `args` is omitted, the global is `undefined` inside the script.
## Example workflow prompts
A workflow fits best when the task is larger than one agent can hold in context, or when the same step needs to run across many items. The prompts below show common shapes. Each one asks Claude to write and run a workflow for that task; you don't write the script yourself.
### Audit many files for the same issue
Fan out one agent per file, then collect and verify the findings.
```text wrap theme={null}
use a workflow to audit every route handler under src/routes/ for missing authentication checks, and adversarially verify each finding before reporting it
```
### Keep fixing until a check passes
Run a checker, fix what failed, and repeat until it passes or stops making progress.
```text wrap theme={null}
use a workflow to run npx tsc --noEmit and keep fixing the reported errors until the type check passes or two rounds in a row make no progress
```
### Migrate many files in parallel
Discover the files to migrate, transform each one in an isolated copy so edits don't conflict, and verify each result.
```text wrap theme={null}
use a workflow to migrate every component under src/components/ from styled-components to Tailwind, working on each file in its own isolated copy
```
### Review every changed file and write one summary
Run a reviewer per file, then hand all the findings to one agent that ranks and deduplicates them.
```text wrap theme={null}
use a workflow to review every file changed in this PR for correctness issues, then merge the per-file findings into one ranked summary
```
### Research a topic across many sources
Fan out readers across changelogs, issues, and docs, then synthesize. The bundled `/deep-research` workflow does this; you can also describe a narrower version.
```text wrap theme={null}
use a workflow to research how our three competitors handle rate limiting: read their public docs and recent changelog entries in parallel, then compare the approaches
```
### Find issues until the list stops growing
Keep searching in rounds and stop when new rounds turn up nothing new.
```text wrap theme={null}
use a workflow to find flaky tests in this repo: run the suite repeatedly, record which tests fail intermittently, and stop once two rounds in a row find nothing new
```
### What the saved script looks like
When you [save a workflow](#save-the-workflow-for-reuse), the file in `.claude/workflows/` holds a `meta` block followed by a script body that orchestrates subagents. You usually don't need to edit it, but here is the shape of a small one so you can recognize what Claude generated:
```javascript theme={null}
export const meta = {
name: 'audit-routes',
description: 'Audit every route handler for missing auth checks',
}
const found = await agent('List every .ts file under src/routes/.', {
schema: { type: 'object', required: ['files'], properties: { files: { type: 'array', items: { type: 'string' } } } },
})
const audits = await pipeline(found.files, file =>
agent(`Audit ${file} for missing authentication checks.`, { label: file }),
)
return audits.filter(Boolean)
```
The body is plain JavaScript with top-level `await`. `agent()` spawns one subagent and `pipeline()` runs one per item in a list.
An `agent()` call resolves to `null` if you stop it mid-run or it hits an unrecoverable API error. `pipeline()` keeps that `null` in the results array, which is why the example ends with `.filter(Boolean)` to drop those entries.
If you want to edit a script by hand, ask Claude to walk you through the change, or see the Workflow tool entry in the [Agent SDK reference](/docs/en/agent-sdk/typescript) for the full set of options.
Cut at 300 lines. The page has the rest.
worktrees First recorded · 311 lines, first recorded
# Run parallel sessions with worktrees ## Start Claude in a worktree ### Set up the worktree environment ### Ask Claude to create a worktree ## Clean up worktrees ## Resume a worktree session ## How Claude Code enforces isolation ## Isolate subagents with worktrees ### Clean up subagent and background-session worktrees ## Customize worktree creation ### Choose the base branch ### Branch from a pull request ### Copy gitignored files into worktrees ### Reuse a worktree name ### Replace worktree creation with a hook ## What worktrees share with the main checkout ## Manage worktrees manually ## Non-git version control ## Troubleshooting ### Claude Code can't enter the worktree at startup ### Worktree creation fails on a symlinked path ### Claude Code refuses to use a worktree ### The session resumes outside its worktree ## See also
The first capture of this source. The page was already there, and this is what it said.
# Run parallel sessions with worktrees
> Isolate parallel Claude Code sessions in separate git worktrees so changes don't collide. Covers the `--worktree` flag, subagent isolation, `.worktreeinclude`, cleanup, and non-git VCS hooks.
A [git worktree](https://git-scm.com/docs/git-worktree) is a separate working directory with its own files and branch, sharing the same repository history and remote as your main checkout. Running each Claude Code session in its own worktree means edits in one session never touch files in another, so one session can build a feature while a second fixes a bug.
<Note>
Worktrees require a git repository; for other version control systems, [configure hooks to replace the git logic](#non-git-version-control). In the [desktop app](/docs/en/desktop#work-in-parallel-with-sessions), every new session gets its own worktree automatically.
</Note>
Worktrees are one of several ways to run Claude in parallel. They isolate file edits, while [subagents](/docs/en/sub-agents) and [agent teams](/docs/en/agent-teams) coordinate the work itself. See [Run agents in parallel](/docs/en/agents) to compare the approaches, or skip ahead to [Isolate subagents with worktrees](#isolate-subagents-with-worktrees) to use worktrees and subagents together.
Most sessions need only the first two sections: [start Claude in a worktree](#start-claude-in-a-worktree), then [clean up when you exit](#clean-up-worktrees). Return to the rest of the page when you need to [resume a session](#resume-a-worktree-session), [change how worktrees are created](#customize-worktree-creation), or [debug a failure](#troubleshooting).
## Start Claude in a worktree
Pass `--worktree` or `-w` with a name to create an isolated worktree and start Claude in it. By default, the worktree is created under `.claude/worktrees/<name>/` at your repository root, on a new branch named `worktree-<name>`:
```bash theme={null}
claude --worktree feature-auth
```
Run the command again with a different name in another terminal to start a second isolated session. If you omit the name, Claude generates one such as `bright-running-fox`.
Interactive runs require [workspace trust](/docs/en/security): if you haven't run Claude in the directory before, run `claude` once there to accept the trust dialog, or `--worktree` exits with an error prompting you to. Non-interactive runs with `-p` skip the trust check, so `claude -p --worktree` proceeds without it.
<Tip>
Add `.claude/worktrees/` to your `.gitignore` so worktree contents don't appear as untracked files in your main checkout.
</Tip>
### Set up the worktree environment
A worktree is a fresh checkout, so initialize your development environment there: ask Claude to install dependencies, or run your project's setup yourself in the worktree directory under `.claude/worktrees/`. To carry gitignored files such as `.env` into every new worktree automatically, add a [`.worktreeinclude` file](#copy-gitignored-files-into-worktrees).
### Ask Claude to create a worktree
You can also ask Claude to "work in a worktree" during a session, and it creates one with the [`EnterWorktree`](/docs/en/tools-reference) tool. Once in a worktree, Claude can switch directly to another one under `.claude/worktrees/` by calling `EnterWorktree` with the target path; the previous worktree stays on disk untouched.
When Claude enters a path outside the repository's `.claude/worktrees/` directory, Claude Code asks for your approval first, because the move takes the session's working directory, write access, and project configuration such as `CLAUDE.md` and settings to that location. An `EnterWorktree` [permission rule](/docs/en/permissions) or choosing "don't ask again" doesn't suppress this prompt; only `bypassPermissions` mode skips it. Before v2.1.206, Claude could enter any existing worktree path without asking.
## Clean up worktrees
When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, and new commits.
* **The worktree is clean**: for an unnamed session, Claude removes the worktree and its branch automatically. A [named](/docs/en/sessions#name-your-sessions) session prompts you first so you can keep the worktree for later
* **The worktree has work in it**: Claude prompts you to keep or remove the worktree. Keeping preserves the directory and branch so you can return later. Removing deletes the worktree directory and its branch, along with all the work in them
Non-interactive runs with `-p` have no exit prompt, so Claude doesn't clean up their worktrees. Remove them with `git worktree remove`.
On Windows, removing a worktree doesn't delete files outside it. If a folder inside the worktree is really a link to somewhere else, such as an NTFS junction or a directory symlink, Claude Code deletes only the link and keeps the folder it points to. Before v2.1.205, removing a worktree with a link nested in a subdirectory could delete the folder it pointed to.
## Resume a worktree session
When you resume a session that was inside a worktree, Claude Code returns the session to that worktree. This holds for interactive resumes, for `--continue` and `--resume` in [non-interactive mode](/docs/en/headless) with `-p`, and for the Agent SDK. Back inside the worktree, Claude can still exit it with the [`ExitWorktree`](/docs/en/tools-reference) tool.
Before returning the session to its worktree, Claude Code verifies that the worktree is still a checkout separate from the main one, and declines to re-enter a worktree that fails the check. For a git worktree, the check reads its git metadata. A worktree without git metadata, such as one a [`WorktreeCreate` hook](#non-git-version-control) created, can pass the check; the cases Claude Code still refuses are listed with their recoveries under [Claude Code refuses to use a worktree](#claude-code-refuses-to-use-a-worktree). For the messages and how to recover from each, see [The session resumes outside its worktree](#the-session-resumes-outside-its-worktree).
Where you launch from, and how you resume, change what Claude Code re-enters:
* **Launch directory**: resume from the main checkout or another directory of the repository. Claude Code re-enters a worktree it created with git under `.claude/worktrees/` even when you launch from inside it. When you launch from inside any other worktree, Claude Code re-enters it only if it can vouch for it from there: a worktree that is its own repository, one without git metadata, or a launch from a subdirectory of a worktree you created with `git worktree add` declines, so launch those from the main checkout.
* **`--fork-session`**: the forked session starts in the directory you launched Claude from, and Claude Code leaves the original session's worktree untouched.
* **Deleted worktree**: if the worktree directory no longer exists, Claude Code resumes the session in the directory you launched Claude from. It tells you the worktree is gone and clears the session's worktree binding.
<Note>
Before v2.1.212, a non-interactive resume stayed in the starting directory and `ExitWorktree` reported that there was no active worktree session to exit.
</Note>
When Claude enters or exits a worktree that Claude Code created with git, the transcript follows: Claude Code records the session under the session's new working directory, the same way [`/cd`](/docs/en/commands) does, so `/desktop` and `--resume` find it there. Exiting moves it back the same way. A worktree created by a [`WorktreeCreate` hook](#non-git-version-control) keeps its transcript at the launch directory. Requires Claude Code v2.1.198 or later.
## How Claude Code enforces isolation
While a session is isolated in a worktree, Claude Code blocks the tool calls the checks below define. The same rules apply whether you started the session with `--worktree`, Claude entered a worktree with `EnterWorktree`, or you resumed a worktree session.
The same enforcement covers every subagent Claude spawns from the isolated session. It applies whether the session is interactive or runs in the [background](/docs/en/agent-view#how-file-edits-are-isolated). [Subagents that run in their own worktree](#isolate-subagents-with-worktrees) carry the same checks. Their version history is under [Write subagent files](/docs/en/sub-agents#write-subagent-files).
Claude Code applies four checks:
* **File edits**: Claude Code blocks an `Edit`, `Write`, or `NotebookEdit` that targets a path in the main checkout.
* **Command working directory**: Claude Code blocks a Bash, PowerShell, or Monitor command whose working directory resolves to the main checkout, or whose working directory it can't verify stays outside it.
* **Git redirects**: Claude Code blocks a Bash or Monitor command that redirects git into the main checkout. The redirect can come through `git -C`, `--git-dir`, a `GIT_DIR` or `GIT_WORK_TREE` variable, or a `cd` into the main checkout before running git.
* **Command shape**: Claude Code blocks a Bash or Monitor command it can't verify stays inside the worktree. The block applies even when the command runs no git at all. Claude Code refuses shell constructs it can't statically trace, such as brace expansion and heredocs with unquoted delimiters. It tells Claude to break the command into plain, separate commands. You can't turn this check off.
The checks apply to the repository you launched Claude Code from. They also cover the main checkout a linked worktree is linked from. For PowerShell commands, Claude Code applies only the working-directory check.
Claude sees each refusal as a tool error that names the worktree and says how to proceed.
## Isolate subagents with worktrees
Subagents can run in their own worktrees so parallel edits don't conflict. Ask Claude to "use worktrees for your agents", or make the isolation permanent for a [custom subagent](/docs/en/sub-agents#supported-frontmatter-fields) by adding `isolation: worktree` to its frontmatter.
This subagent in `.claude/agents/` always runs in its own worktree:
```markdown theme={null}
---
name: refactorer
description: Applies mechanical refactors across many files
isolation: worktree
---
Apply the requested refactor across every affected file, then run the tests
and report the results.
```
Each subagent gets a temporary worktree that Claude Code removes automatically when the subagent finishes without changes; a worktree with changes stays on disk until the [periodic sweep below](#clean-up-subagent-and-background-session-worktrees) can remove it without losing work.
Subagent worktrees use the same [base branch](#choose-the-base-branch) as `--worktree`, so they branch from your repository's default branch unless `worktree.baseRef` is set to `"head"`.
### Clean up subagent and background-session worktrees
A periodic sweep removes worktrees that Claude created for subagents and [background sessions](/docs/en/agent-view#how-file-edits-are-isolated) once they are older than your [`cleanupPeriodDays`](/docs/en/settings#available-settings) setting, following the [retention sweep rules](/docs/en/claude-directory#cleaned-up-automatically). The sweep skips a worktree that still holds work: changed or untracked files, or unpushed commits. It never removes worktrees you create with `--worktree`.
While an agent is running, Claude runs `git worktree lock` on its worktree so that concurrent cleanup cannot remove it. The lock is released when the agent finishes.
The sweep also releases a lock Claude Code set for a session whose process has exited, so a killed background session doesn't leave its worktree permanently locked. The sweep never releases a lock you set yourself with `git worktree lock`. Before v2.1.210, a lock left by a killed session stayed in place until you ran `git worktree unlock`.
To clean up a worktree that the sweep keeps, run `git worktree remove`, adding `--force` if the worktree has uncommitted changes or untracked files.
## Customize worktree creation
Claude Code's defaults for creating worktrees cover most sessions: it creates them under `.claude/worktrees/`, branches them from your repository's default branch, and checks out only tracked files. The options in this section change those defaults.
### Choose the base branch
New worktrees branch from the repository's default branch, so most sessions don't need this setting. Set `worktree.baseRef` in [settings](/docs/en/settings#worktree-settings) to branch from your current work instead. The setting accepts two values:
* `"fresh"` (default): branch from the repository's default branch on the remote, usually `main`, so the worktree starts from a clean tree matching the remote.
* `"head"`: branch from your current local `HEAD`, so the worktree carries your unpushed commits and feature-branch state. Use this when isolating subagents that need to operate on in-progress work. Inside a worktree, `"head"` resolves to that worktree's `HEAD`, not the main checkout's.
You can't set `worktree.baseRef` to a branch name. To start a worktree from a specific existing branch, [create it with git directly](#manage-worktrees-manually).
For a `"fresh"` base, Claude Code keeps `origin/HEAD` current: when the repository hasn't been fetched in the last 24 hours, it fetches the default branch, capped at five seconds, and uses the locally cached ref if the fetch fails. If no remote is configured, or `origin/HEAD` isn't cached locally and can't be fetched, the worktree falls back to your current local `HEAD`. Before v2.1.208, a fresh worktree used whatever `origin/HEAD` was already cached locally.
This example makes every new worktree branch from your current work:
```json theme={null}
{
"worktree": {
"baseRef": "head"
}
}
```
### Branch from a pull request
To branch from a specific pull request, pass `--worktree` the PR number prefixed with `#`, or a full GitHub pull request URL. Claude Code fetches `pull/<number>/head` from `origin` and creates the worktree at `.claude/worktrees/pr-<number>`. Quote the argument so your shell doesn't treat `#` as the start of a comment:
```bash theme={null}
claude --worktree "#1234"
```
### Copy gitignored files into worktrees
A worktree is a fresh checkout, so untracked files like `.env` or `.env.local` from your main repository are not present. To copy them automatically when Claude creates a worktree, add a `.worktreeinclude` file to your project root.
The file uses `.gitignore` syntax. Only files that match a pattern and are also gitignored are copied, so tracked files are never duplicated.
This `.worktreeinclude` copies two env files and a secrets config into each new worktree:
```text .worktreeinclude theme={null}
.env
.env.local
config/secrets.json
```
This applies to every worktree Claude Code creates with git: `--worktree` worktrees, [subagent worktrees](#isolate-subagents-with-worktrees), and parallel sessions in the [desktop app](/docs/en/desktop#work-in-parallel-with-sessions). With a [`WorktreeCreate` hook](#non-git-version-control), copy the files inside the hook script.
### Reuse a worktree name
Passing `--worktree` a name whose directory already exists opens that existing worktree instead of creating a new one.
With the default `"fresh"` [base](#choose-the-base-branch), a reopened worktree resets to the repository's default branch instead of continuing at its old tip when all of the following hold:
* It has no uncommitted changes or untracked files.
* It is still on the branch Claude Code created for it.
* It has no commits of its own, or its pull request was merged and its remote branch deleted.
Claude Code detects the merged case from git state alone: the remote branch the worktree pushed to no longer exists, and every commit in the worktree is already on the default branch.
Anything else reopens at the old tip: a worktree that fails any of the conditions, one whose state can't be verified, and any reuse when `worktree.baseRef` is `"head"` or the name is a pull request number. Before v2.1.208, a reused name always reopened the old worktree at its old tip.
### Replace worktree creation with a hook
Configure a [`WorktreeCreate` hook](/docs/en/hooks#worktreecreate) to replace the default `git worktree` logic entirely, including placing worktrees somewhere other than `.claude/worktrees/`. For a complete example, see [Non-git version control](#non-git-version-control).
## What worktrees share with the main checkout
A worktree gets its own files and branch, but it shares the repository's `.git` directory, project-scope plugins, and saved permission approvals with the main checkout:
* **The repository's `.git` directory**: git commands in a worktree write to the main repository's shared `.git` directory, and [sandboxing](/docs/en/sandboxing#filesystem-isolation) allows those writes, so commands such as `git commit` work from inside a worktree with the sandbox enabled.
* **Plugins**: plugins installed at [project scope](/docs/en/plugins-reference#plugin-installation-scopes) from the main checkout also load in worktrees of the same repository, so you don't need to reinstall them per worktree. Requires Claude Code v2.1.200 or later.
* **Permission approvals**: choosing "Yes, don't ask again" for a Bash command in a worktree session saves the rule to the main checkout's `.claude/settings.local.json`, so it applies in the main checkout and in every other worktree of the repository, and it survives the worktree's removal. Before v2.1.211, an approval granted in a worktree was saved inside that worktree, didn't apply elsewhere, and was lost when the worktree was removed. See [where approvals are saved](/docs/en/permissions#permission-system).
All three apply whether you create the worktree with `--worktree`, with `git worktree add`, or through the [desktop app](/docs/en/desktop#work-in-parallel-with-sessions).
## Manage worktrees manually
Create worktrees with Git directly when you need to check out a specific existing branch or place the worktree outside the repository.
Create a worktree on a new branch:
```bash theme={null}
git worktree add ../project-feature-a -b feature-a
```
Create a worktree from an existing branch, replacing `fix-issue-456` with a branch that already exists in your repository:
```bash theme={null}
git worktree add ../project-bugfix fix-issue-456
```
Start Claude in the worktree:
```bash theme={null}
cd ../project-feature-a
claude
```
List your worktrees:
```bash theme={null}
git worktree list
```
Remove one when you're done with it:
```bash theme={null}
git worktree remove ../project-feature-a
```
See the [Git worktree documentation](https://git-scm.com/docs/git-worktree) for the full command reference.
## Non-git version control
Worktree isolation uses git by default. For SVN, Perforce, Mercurial, or other systems, configure [`WorktreeCreate` and `WorktreeRemove` hooks](/docs/en/hooks#worktreecreate) to provide custom creation and cleanup logic. Because the hook replaces the default git behavior, [`.worktreeinclude`](#copy-gitignored-files-into-worktrees) is not processed when you use `--worktree`. Copy any local configuration files inside your hook script instead.
This `WorktreeCreate` hook reads the worktree name from the JSON on stdin with `jq`, checks out a fresh SVN working copy, and prints the directory path so Claude Code can use it as the session's working directory. Add the configuration to your [`settings.json`](/docs/en/settings#settings-files):
```json theme={null}
{
"hooks": {
"WorktreeCreate": [
{
"hooks": [
{
"type": "command",
"command": "bash -c 'NAME=$(jq -r .name); DIR=\"$HOME/.claude/worktrees/$NAME\"; svn checkout https://svn.example.com/repo/trunk \"$DIR\" >&2 && echo \"$DIR\"'"
}
]
}
]
}
}
```
Pair it with a `WorktreeRemove` hook to clean up when the session ends. See the [hooks reference](/docs/en/hooks#worktreecreate) for the input schema and a removal example.
## Troubleshooting
Claude Code reports the errors below when it creates a worktree, enters one at startup, or returns a resumed session to one.
### Claude Code can't enter the worktree at startup
When Claude Code can't enter the worktree directory at startup, it prints an error naming the path and exits with code 1. This can happen when a [`WorktreeCreate` hook](/docs/en/hooks#worktreecreate) prints something other than the directory it created, or when the directory was deleted after it was set up.
### Worktree creation fails on a symlinked path
Claude Code refuses to create a worktree when `.claude`, `.claude/worktrees`, or the worktree directory itself is a symlink, and the error names the symlinked path. Remove the symlink and retry. Before v2.1.212, if the repository already contained a committed symlink at one of those paths, worktree creation followed it and could create files outside the repository.
### Claude Code refuses to use a worktree
An error starting `Refusing to use <path> as an isolation worktree` means Claude Code checked the directory's git identity before adopting it as a session's or subagent's isolated checkout, and declined it. The check runs whether Claude Code is creating the worktree, entering an existing one, or reusing one from an earlier run.
In most cases the rest of the message says the directory's git metadata resolves into the main checkout: for example, its `.git` file points at the main repository's own `.git` directory, or git resolves its working tree to the main checkout through a `core.worktree` redirect. From such a directory, an ordinary git command such as `git reset --hard` would act on the main checkout instead of the worktree. Claude Code also refuses when the directory has a `.git` entry it can't read, rather than assuming the worktree is safe.
Claude Code leaves the refused directory in place, since it may hold work. Match the message to its recovery, whether it follows `Refusing to use <path>` or appears in a [resume message](#the-session-resumes-outside-its-worktree); some endings occur only in resume messages:
* **Says `launch from the parent checkout` or `Run the resume from the project checkout`**: you launched Claude Code from inside the worktree. Launch from the main checkout instead; the worktree needs no recreation.
* **Says `it cannot be resumed or re-entered`**: nothing in this session vouches for the worktree from where you launched. Recreate it; the directory and its work remain on disk for manual recovery, and when the worktree has a parent checkout, resuming from there also works.
* **Says `it contains the protected checkout`**: the refused directory is a parent of your main checkout, such as your home directory. Don't delete it. Change the worktree path, such as the path your `WorktreeCreate` hook returns or the `EnterWorktree` target, so the worktree doesn't contain the checkout.
* **Says `the protected checkout <path> has a .git entry that could not be examined` or `has git metadata that could not be resolved`**: the problem is the main checkout's git metadata, not the worktree's. Don't delete the worktree, and ignore the message's trailing advice to recreate it, which doesn't apply to these two endings. Repair the main checkout, for example a permissions problem or a git `dubious ownership` refusal on its `.git`, and retry.
* **Says `its recorded path has a network spelling`**: Claude Code never resumes into a worktree at a network path. Recreate the worktree at a local path.
* **Any other ending**: the message names the problem and its fix, such as removing a `core.worktree` redirect or recreating the worktree; follow it. Before deleting a directory whose message says its git identity could not be verified, address the named cause first, for example a symbolic link in the worktree's path or git itself failing to run, since the directory may be healthy. When you do recreate, salvage any changes you need from the old directory first; it stays on disk.
### The session resumes outside its worktree
When an interactive resume can't return the session to its worktree, Claude Code says so with one of the messages below.
| Message starts with | What happened and what to do |
| :------------------------------------------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `Your worktree <path> no longer exists` | The worktree directory was removed. The session continues in the current directory without isolation, and Claude Code clears the worktree binding. No action needed. |
| `Could not verify your worktree <path> this time` | Claude Code couldn't verify the worktree, usually for a transient reason; the binding is kept, and the session continues in the current directory without isolation. Resume again to retry; if it keeps happening, enter the worktree in a new session and match the refusal message under [Claude Code refuses to use a worktree](#claude-code-refuses-to-use-a-worktree), which can name the main checkout's metadata rather than the worktree's. |
| `Did not re-enter your worktree <path>` | Claude Code refused the worktree binding as unsafe; it clears the binding and the session continues without isolation. The message includes the specific refusal: match it under [Claude Code refuses to use a worktree](#claude-code-refuses-to-use-a-worktree), since the fix is recreation for some refusals and a path change for others. |
| `Could not re-enter your worktree <path>` | Claude Code couldn't vouch for the worktree from where you launched, most commonly because you launched from inside it; the binding is kept. The rest of the message names the fix; match it under [Claude Code refuses to use a worktree](#claude-code-refuses-to-use-a-worktree). |
In [non-interactive mode](/docs/en/headless) with `-p`, and on resumes the [Agent SDK](/docs/en/agent-sdk/sessions) runs, Claude Code stops the resume with a stderr error for every refusal except a gone worktree, instead of continuing without isolation, and the messages take different shapes from the ones in the table above:
* `Error: cannot resume into worktree <path>: ...This session was not started.` for a refusal the table shows as `Did not re-enter`
* `Error: could not verify worktree <path> for this resume, so the resume was aborted...` for `Could not verify`
* `Error: ...The worktree binding is kept.` for `Could not re-enter`
* `Notice: the worktree <path> for this session no longer exists...` for a gone worktree; Claude Code prints it and continues the session, as an interactive resume does
Cut at 300 lines. The page has the rest.
zero-data-retention First recorded · 78 lines, first recorded
# Zero data retention ## ZDR scope ### Route Claude Code traffic to your ZDR organization ### What ZDR covers ### What ZDR does not cover ## Features disabled under ZDR ### Model availability under ZDR ## Data retention for policy violations ## Request ZDR
The first capture of this source. The page was already there, and this is what it said.
# Zero data retention > Learn about Zero Data Retention (ZDR) for Claude Code, available to qualified accounts on Claude for Enterprise, including scope, disabled features, and how to request enablement. Zero Data Retention (ZDR) for Claude Code is available to qualified accounts on Claude for Enterprise. When ZDR is enabled, prompts and model responses generated during Claude Code sessions are processed in real time and not stored by Anthropic after the response is returned, except where needed to comply with law or combat misuse. <Note> ZDR is not included in the standard Claude for Enterprise plan and cannot be enabled from your admin settings. It is available to qualified accounts and requires separate enablement by Anthropic. If your organization requires ZDR, [contact sales](https://www.anthropic.com/contact-sales?utm_source=claude_code\&utm_medium=docs\&utm_content=zero_data_retention_request) or your Anthropic account team to confirm eligibility. </Note> ZDR on Claude for Enterprise gives enterprise customers the ability to use Claude Code with zero data retention and access administrative capabilities: * Cost controls per user * [Analytics](/docs/en/analytics) dashboard * [Server-managed settings](/docs/en/server-managed-settings) * Audit logs ZDR for Claude Code on Claude for Enterprise applies only to Anthropic's direct platform. For Claude deployments on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, refer to those platforms' data retention policies. ## ZDR scope ZDR covers Claude Code inference on Claude for Enterprise. <Warning> ZDR is enabled on a per-organization basis. Each new organization requires ZDR to be enabled separately by your Anthropic account team. ZDR does not automatically apply to new organizations created under the same account. Contact your account team to enable ZDR for any new organizations. </Warning> ### Route Claude Code traffic to your ZDR organization ZDR applies to requests that authenticate into a ZDR-enabled organization. If a developer signs in to Claude Code with a personal account or with an API key from a different organization, those sessions are not covered. To require that developers' claude.ai logins belong to your ZDR organization, deploy the `forceLoginMethod` and `forceLoginOrgUUID` managed settings; see [Restrict login to your organization](/docs/en/authentication#restrict-login-to-your-organization), which also explains how these keys treat Claude Console logins. ### What ZDR covers ZDR covers model inference calls made through Claude Code on Claude for Enterprise. When you use Claude Code in your terminal, the prompts you send and the responses Claude generates are not retained by Anthropic. This applies to every model available to ZDR organizations. Some models require data retention and are not available under ZDR; see [Model availability under ZDR](#model-availability-under-zdr). ### What ZDR does not cover ZDR does not extend to the following, even for organizations with ZDR enabled. These features follow [standard data retention policies](/docs/en/data-usage#data-retention): | Feature | Details | | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Chat on claude.ai | Chat conversations through the Claude for Enterprise web interface are not covered by ZDR. | | Cowork | Cowork sessions are not covered by ZDR. | | Claude Code Analytics | Does not store prompts or model responses, but collects productivity metadata such as account emails and usage statistics. Contribution metrics are not available for ZDR organizations; the [analytics dashboard](/docs/en/analytics) shows usage metrics only. | | User and seat management | Administrative data such as account emails and seat assignments is retained under standard policies. | | Third-party integrations | Data processed by third-party tools, MCP servers, or other external integrations is not covered by ZDR. Review those services' data handling practices independently. | ## Features disabled under ZDR When ZDR is enabled for a Claude Code organization on Claude for Enterprise, certain features that require storing prompts or completions are automatically disabled at the backend level: | Feature | Reason | | ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | | [Claude Code on the Web](/docs/en/claude-code-on-the-web) | Requires server-side storage of conversation history. | | [Cloud sessions](/docs/en/desktop#cloud-sessions) from the Desktop app | Requires persistent session data that includes prompts and completions. | | [Artifacts](/docs/en/artifacts) | Requires storing published page content on Anthropic-operated infrastructure. | | Feedback submission (`/feedback`, `/bug`, `/share`) | Submitting feedback sends conversation data to Anthropic. | | [Remote Control](/docs/en/remote-control) | Stores the session transcript on Anthropic servers to sync the conversation across devices. | These features are blocked in the backend regardless of client-side display. If you see a disabled feature in the Claude Code terminal during startup, attempting to use it returns an error indicating the organization's policies do not allow that action. Future features may also be disabled if they require storing prompts or completions. ### Model availability under ZDR Claude Fable 5 is not available for organizations with zero data retention enabled. This model class [requires data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements), so requests from ZDR organizations cannot be served by it. The model is either absent from the `/model` picker for ZDR organizations or shown as disabled with a notice that disabling ZDR is required, and the server rejects requests for it regardless of client configuration. Other models remain available under ZDR. Fable 5 is not the default model, and the `best` alias, which resolves to Fable 5 where it is available, resolves to Opus for organizations where it is not, including ZDR organizations. ## Data retention for policy violations Even with ZDR enabled, Anthropic may retain data where required by law or to address Usage Policy violations. If a session is flagged for a policy violation, Anthropic may retain the associated inputs and outputs for up to 2 years, consistent with Anthropic's standard ZDR policy. ## Request ZDR To request ZDR for Claude Code on Claude for Enterprise, [contact sales](https://www.anthropic.com/contact-sales?utm_source=claude_code\&utm_medium=docs\&utm_content=zero_data_retention_request) or your Anthropic account team. Your account team will submit the request internally, and Anthropic will review and enable ZDR on your organization after confirming eligibility. All enablement actions are audit-logged. If you are currently using ZDR for Claude Code via pay-as-you-go API keys, you can transition to Claude for Enterprise to gain access to administrative features while maintaining ZDR for Claude Code. Contact your account team to coordinate the migration.