An entry is only as true as the day it was written.
Flags move on the server after a release ships. Anthropic's own notes land days later and their documentation later still. Sometimes an entry turns out to be wrong and gets corrected by hand. All of that is recorded against the entry it happened to, and this is the whole of it in the order it happened.
Nothing here replaces an entry. Every line links to the page its release published, still saying what that release said, because a correction is added and dated rather than swapped in.
| When | Entry | What happened |
|---|---|---|
v2.1.290/verify |
Documentation arrivedAnthropic's documentation has since written up /verify, on Week 30 · July 20–24, 2026.
the line in the docs[`/code-review`](/docs/en/code-review-local) 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`/verify`, `/code-review`, and `/deep-resear… |
|
v2.1.299fast_mode |
Documentation arrivedAnthropic's documentation has since written up fast_mode, on Customize your status line.
the line in the docs> "fast_mode": false, |
|
v2.1.302skillOverrides |
Documentation arrivedAnthropic's documentation has since written up skillOverrides, on Extend Claude with skills.
the line in the docs> The [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on. To hide it, set the `DISABLE_DOCTOR_COMMAND` environment variable or a [`skillOverrides`](#override-skill-visibility-from-sett… |
|
v2.1.296skillOverrides |
Documentation arrivedAnthropic's documentation has since written up skillOverrides, on Extend Claude with skills.
the line in the docs> The [`/doctor`](/docs/en/commands#all-commands) setup checkup stays typable when `disableBundledSkills` is on. To hide it, set the `DISABLE_DOCTOR_COMMAND` environment variable or a [`skillOverrides`](#override-skill-visibility-from-sett… |
|
v2.1.293/help |
Documentation arrivedAnthropic's documentation has since written up /help, on Extend Claude with skills.
the line in the docs> For built-in commands like `/help` and `/compact`, and bundled skills like `/debug` and `/code-review`, see the [commands reference](/docs/en/commands). |
|
v2.1.293manifest.json |
Documentation arrivedAnthropic's documentation has since written up manifest.json, on Advanced setup.
the line in the docscurl -fsSLO "$REPO/$VERSION/manifest.json" |
|
v2.1.283DISABLE_GROWTHBOOK |
Documentation arrivedAnthropic's documentation has since written up DISABLE_GROWTHBOOK, on Continue local sessions from any device with Remote Control.
the line in the docsWith only `DISABLE_TELEMETRY` or `DO_NOT_TRACK` set, your sessions don't auto-connect through your organization's admin default or Claude Code's own default. If something else makes Remote Control unavailable for you, such as `DISABLE_GROW… |
|
v2.1.290/rc |
Documentation arrivedAnthropic's documentation has since written up /rc, on Continue local sessions from any device with Remote Control.
the line in the docsIf you're already in a Claude Code session and want to continue it remotely, use the `/remote-control` (or `/rc`) command: |
|
v2.1.281CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE, on Troubleshoot plugins.
the line in the docsexport CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 |
|
v2.1.286CLAUDE_CODE_ENABLE_FUNCTION_HOOKS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_ENABLE_FUNCTION_HOOKS, on Mods overview.
the line in the docs> If you set `CLAUDE_CODE_ENABLE_FUNCTION_HOOKS` during early access, remove it. Claude Code v2.1.287 and later ignores it, so setting it to `0` doesn't keep mods off. |
|
v2.1.280CLAUDE_CODE_ENABLE_FUNCTION_HOOKS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_ENABLE_FUNCTION_HOOKS, on Mods overview.
the line in the docs> If you set `CLAUDE_CODE_ENABLE_FUNCTION_HOOKS` during early access, remove it. Claude Code v2.1.287 and later ignores it, so setting it to `0` doesn't keep mods off. |
|
v2.1.283tool.output |
Documentation arrivedAnthropic's documentation has since written up tool.output, on Monitoring.
the line in the docs**`tool.output` span event on `claude_code.tool`** |
|
v2.1.290GH_HOST |
Documentation arrivedAnthropic's documentation has since written up GH_HOST, on Interactive mode.
the line in the docs> * **A GitHub Enterprise host set as `GH_HOST`**: `GH_ENTERPRISE_TOKEN` or `GITHUB_ENTERPRISE_TOKEN`, or the token saved by `gh auth login --hostname <host>`. Without one, the footer shows the same hints |
|
v2.1.290GH_HOST |
Documentation arrivedAnthropic's documentation has since written up GH_HOST, on Interactive mode.
the line in the docs> * **A GitHub Enterprise host set as `GH_HOST`**: `GH_ENTERPRISE_TOKEN` or `GITHUB_ENTERPRISE_TOKEN`, or the token saved by `gh auth login --hostname <host>`. Without one, the footer shows the same hints |
|
v2.1.296updatedToolOutput |
Documentation arrivedAnthropic's documentation has since written up updatedToolOutput, on Hooks reference.
the line in the docs> `updatedToolOutput` only changes what Claude sees. The tool has already run by the time the hook fires, so any files written, commands executed, or network requests sent have already taken effect. Telemetry such as OpenTelemetry tool spa… |
|
v2.1.299CLAUDE_CODE_DISABLE_FILE_MENTIONS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_FILE_MENTIONS, on Hooks reference.
the line in the docs> * **Turn the insertion off**: set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS=1`](/docs/en/env-vars#variables) in your shell, user settings, or managed settings. Claude then gets the mentioned paths with a note to read them using its file tools.… |
|
v2.1.287PostToolBatch |
Documentation arrivedAnthropic's documentation has since written up PostToolBatch, on Hooks reference.
the line in the docs to that model… |
|
v2.1.302/design-sync |
Documentation arrivedAnthropic's documentation has since written up /design-sync, on Feature availability.
the line in the docs**Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [web search](/docs/en/tools-reference#websearch-tool-behavior), [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/ad… |
|
v2.1.286fastMode |
Documentation arrivedAnthropic's documentation has since written up fastMode, on Speed up responses with fast mode.
the line in the docs> * **Fast mode turned off by managed settings**: if your organization deploys [managed settings](/docs/en/managed-settings) that set [`fastMode: false`](/docs/en/settings-reference#fastmode), turning fast mode on with `/fast` shows the sa… |
|
v2.1.299/security-review |
Documentation arrivedAnthropic's documentation has since written up /security-review, on Error reference.
the line in the docs### /security-review fails without origin/HEAD |
|
v2.1.300--restricted |
Documentation arrivedAnthropic's documentation has since written up --restricted, on Error reference.
the line in the docs### Cloud sessions cannot be created from a `--restricted` session |
|
v2.1.296--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Error reference.
the line in the docs### Conflict between `--bg` and `--print` |
|
v2.1.293/bug |
Documentation arrivedAnthropic's documentation has since written up /bug, on Error reference.
the line in the docs| `/feedback is disabled by your organization's policy`, or the same for `/bug` or `/share` | [Command-line errors](#feedback-is-disabled-by-your-organizations-policy) | |
|
v2.1.302claude --resume |
Documentation arrivedAnthropic's documentation has since written up claude --resume, on Desktop application.
the line in the docs> While a conversation's Claude Code process is still running, don't run [`claude --resume`](/docs/en/cli-reference#cli-flags) for it on the remote machine. Claude Code doesn't stop you, and both processes then write to the same conversati… |
|
v2.1.300claude daemon stop |
Documentation arrivedAnthropic's documentation has since written up claude daemon stop, on Run Claude Code behind a corporate launcher.
the line in the docsA running background service and any open `claude` sessions read the variable once at startup, so they keep launching unwrapped processes until restarted. Run `claude daemon stop --any` to stop the on-demand service. The next command that … |
|
v2.1.300claude daemon |
Documentation arrivedAnthropic's documentation has since written up claude daemon, on Run Claude Code behind a corporate launcher.
the line in the docsA running background service and any open `claude` sessions read the variable once at startup, so they keep launching unwrapped processes until restarted. Run `claude daemon stop --any` to stop the on-demand service. The next command that … |
|
v2.1.293processWrapper |
Documentation arrivedAnthropic's documentation has since written up processWrapper, on Run Claude Code behind a corporate launcher.
the line in the docs> `CLAUDE_CODE_PROCESS_WRAPPER` requires Claude Code v2.1.208 or later. Earlier versions ignore the variable and start every process unwrapped. The equivalent [`processWrapper` setting](/docs/en/settings-reference#processwrapper) requires … |
|
v2.1.302claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on Let Claude coordinate ongoing work with Projects.
the line in the docs* **In a terminal**: run `claude remote-control` in the folder and leave it running. In a git repository, add `--spawn worktree` to give each thread there its own [worktree](/docs/en/worktrees) instead of the folder itself. |
|
v2.1.302claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on Let Claude coordinate ongoing work with Projects.
the line in the docs* **In a terminal**: run `claude remote-control` in the folder and leave it running. In a git repository, add `--spawn worktree` to give each thread there its own [worktree](/docs/en/worktrees) instead of the folder itself. |
|
v2.1.300--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on Use Claude Code in the cloud.
the line in the docs> `--cloud` creates cloud sessions. `--remote-control` is unrelated: it lets you monitor and steer a local CLI session from claude.ai or the Claude app. See [Remote Control](/docs/en/remote-control). |
|
v2.1.296--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on Use Claude Code in the cloud.
the line in the docs> `--cloud` creates cloud sessions. `--remote-control` is unrelated: it lets you monitor and steer a local CLI session from claude.ai or the Claude app. See [Remote Control](/docs/en/remote-control). |
|
v2.1.287--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on Use Claude Code in the cloud.
the line in the docs> `--cloud` creates cloud sessions. `--remote-control` is unrelated: it lets you monitor and steer a local CLI session from claude.ai or the Claude app. See [Remote Control](/docs/en/remote-control). |
|
v2.1.287--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on Use Claude Code in the cloud.
the line in the docs> `--cloud` creates cloud sessions. `--remote-control` is unrelated: it lets you monitor and steer a local CLI session from claude.ai or the Claude app. See [Remote Control](/docs/en/remote-control). |
|
v2.1.283load_test_mode |
Documentation arrivedAnthropic's documentation has since written up load_test_mode, on Claude apps gateway configuration.
the line in the docs> Never turn this on for a gateway that developers use. Every request gets the canned reply and no model is called. The gateway logs a `load_test_mode is on` warning at boot and marks each `inference` [audit event](/docs/en/claude-apps-gat… |
|
v2.1.290private_key_jwt |
Documentation arrivedAnthropic's documentation has since written up private_key_jwt, on Claude apps gateway configuration.
the line in the docsGive the gateway the private key and the certificate in a `client_assertion` block. Leave `client_secret` out, because the gateway refuses to start when one is set together with `private_key_jwt`. This `oidc` block authenticates the gatewa… |
|
v2.1.296managed.policies |
Documentation arrivedAnthropic's documentation has since written up managed.policies, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docsThis config is enough for a working sign-in loop with the default Amazon Bedrock model catalog. Once it's running, add per-group RBAC and managed settings via [`managed.policies`](/docs/en/claude-apps-gateway-config#managed), telemetry fan… |
|
v2.1.295gateway.yaml |
Documentation arrivedAnthropic's documentation has since written up gateway.yaml, on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
the line in the docs**3. Write gateway.yaml** |
|
v2.1.299--fork-session |
Documentation arrivedAnthropic's documentation has since written up --fork-session, on Checkpointing.
the line in the docs> Summarize keeps you in the same session and compresses context, like a targeted `/compact`. To branch off and try a different approach while preserving the original session intact, use [`/branch`](/docs/en/sessions#branch-a-session) or `… |
|
v2.1.285mcp.connect |
Documentation arrivedAnthropic's documentation has since written up mcp.connect, on Channels reference.
the line in the docsawait mcp.connect(new StdioServerTransport()) |
|
v2.1.299/reload-plugins |
Documentation arrivedAnthropic's documentation has since written up /reload-plugins, on Push events into a running session with channels.
the line in the docsWhen the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports `Run /reload-plugins to apply.`, see [Apply plugin changes without … |
|
v2.1.301/rename |
Documentation arrivedAnthropic's documentation has since written up /rename, on Best practices for Claude Code.
the line in the docs> Name sessions with `/rename` and treat them like branches: each workstream gets its own persistent context. |
|
v2.1.295--transport |
Documentation arrivedAnthropic's documentation has since written up --transport, on Best practices for Claude Code.
the line in the docs> Run `claude mcp add` with a server name and URL or command to connect external tools like Notion, Figma, or your database. For example: `claude mcp add --transport http notion https://mcp.notion.com/mcp`. |
|
v2.1.299/init |
Documentation arrivedAnthropic's documentation has since written up /init, on Best practices for Claude Code.
the line in the docs> Run `/init` to generate a starter CLAUDE.md file based on your current project structure, then refine over time. |
|
v2.1.302/design |
Documentation arrivedAnthropic's documentation has since written up /design, on Share session output as artifacts.
the line in the docs> Templates are in beta. They're on by default on Pro, Max, and Team plans. On Enterprise plans, an Owner [turns each template on](https://support.claude.com/en/articles/16994751-artifacts-admin-guide-for-team-and-enterprise-plans) under *… |
|
v2.1.285/setup-bedrock |
Documentation arrivedAnthropic's documentation has since written up /setup-bedrock, on Claude Code on Amazon Bedrock.
the line in the docsRun `claude`. At the login prompt, select **3rd-party platform**, then **Amazon Bedrock**. If you're already signed in and see the chat prompt instead, run `/setup-bedrock` to open the wizard. Until `CLAUDE_CODE_USE_BEDROCK=1` is set, Clau… |
|
v2.1.288localSettings |
Documentation arrivedAnthropic's documentation has since written up localSettings, on Handle approvals and user input.
the line in the docsThe user approves and doesn't want to be asked again for this kind of call. The third callback argument carries `suggestions`, an array of ready-made [`PermissionUpdate`](/docs/en/agent-sdk/typescript#permissionupdate) entries. Echo one ba… |