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 |
|---|---|---|
v2.1.257--setting-sources |
Documentation arrivedAnthropic's documentation has since written up --setting-sources, on Extend Claude with skills.
the line in the docs* A session where your organization's managed settings [lock skills to plugin sources](/docs/en/settings-reference#strictpluginonlycustomization-skills), or one you start with a [`--setting-sources`](/docs/en/cli-reference#cli-flags) list … |
|
v2.1.257--setting-sources |
Documentation arrivedAnthropic's documentation has since written up --setting-sources, on Extend Claude with skills.
the line in the docs* A session where your organization's managed settings [lock skills to plugin sources](/docs/en/settings-reference#strictpluginonlycustomization-skills), or one you start with a [`--setting-sources`](/docs/en/cli-reference#cli-flags) list … |
|
v2.1.273apiKeyHelper |
Documentation arrivedAnthropic's documentation has since written up apiKeyHelper, on Extend Claude with skills.
the line in the docs* A session that doesn't use a sign-in stored by `/login`, such as one that authenticates with an API key, or one where `ANTHROPIC_AUTH_TOKEN`, `CLAUDE_CODE_OAUTH_TOKEN`, or an `apiKeyHelper` script supplies the credential |
|
v2.1.246CLAUDE_CODE_OAUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_OAUTH_TOKEN, on Extend Claude with skills.
the line in the docs* A session that doesn't use a sign-in stored by `/login`, such as one that authenticates with an API key, or one where `ANTHROPIC_AUTH_TOKEN`, `CLAUDE_CODE_OAUTH_TOKEN`, or an `apiKeyHelper` script supplies the credential |
|
v2.1.273unset |
Documentation arrivedAnthropic's documentation has since written up unset, on All settings.
the line in the docsTurn off the download of the [skills enabled for your claude.ai account](/docs/en/skills#how-synced-skills-behave). Claude Code downloads them into `~/.claude/skills/synced/` in [terminal sessions where you sign in with your claude.ai acco… |
|
v2.1.273local |
Documentation arrivedAnthropic's documentation has since written up local, on All settings.
the line in the docs| [`syncClaudeAiPlugins`](#syncclaudeaiplugins) | Stop loading the [plugins enabled on your claude.ai account](/docs/en/plugins-reference#synced-plugins) and stop downloading new ones | Plugins and skills | User, local, or managed | |
|
v2.1.273local |
Documentation arrivedAnthropic's documentation has since written up local, on All settings.
the line in the docs| [`syncClaudeAiPlugins`](#syncclaudeaiplugins) | Stop loading the [plugins enabled on your claude.ai account](/docs/en/plugins-reference#synced-plugins) and stop downloading new ones | Plugins and skills | User, local, or managed | |
|
v2.1.246syncClaudeAiPlugins |
Documentation arrivedAnthropic's documentation has since written up syncClaudeAiPlugins, on Plugins reference.
the line in the docs* **Stop syncing on a machine**: set [`syncClaudeAiPlugins`](/docs/en/settings-reference#syncclaudeaiplugins) to `false` in your user settings. Claude Code stops downloading, and the next time it starts it moves the plugins it already sync… |
|
v2.1.273/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Plugins reference.
the line in the docsA sign-in from an earlier version of Claude Code picks up plugin access the next time Claude Code renews that sign-in in the background, within a few hours, or right away if you run `/login` again. Plugin sync starts the next time you star… |
|
v2.1.273/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Plugins reference.
the line in the docsA sign-in from an earlier version of Claude Code picks up plugin access the next time Claude Code renews that sign-in in the background, within a few hours, or right away if you run `/login` again. Plugin sync starts the next time you star… |
|
v2.1.273local |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming local after this was published.
the line in the docs* [`useAutoModeDuringPlan`](/docs/en/settings-reference#useautomodeduringplan), [`syncClaudeAiSkills`](/docs/en/settings-reference#syncclaudeaiskills), and [`syncClaudeAiPlugins`](/docs/en/settings-reference#syncclaudeaiplugins), where a `… |
|
v2.1.273local |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming local after this was published.
the line in the docs* [`useAutoModeDuringPlan`](/docs/en/settings-reference#useautomodeduringplan), [`syncClaudeAiSkills`](/docs/en/settings-reference#syncclaudeaiskills), and [`syncClaudeAiPlugins`](/docs/en/settings-reference#syncclaudeaiplugins), where a `… |
|
v2.1.251CLAUDE_CODE_SYNC_SKILLS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SYNC_SKILLS, on Environment variables.
the line in the docs| `CLAUDE_CODE_SYNC_SKILLS` | Set to `1` in non-interactive mode with the `-p` flag to make Claude Code download the skills enabled for your claude.ai account in that run and wait for the list of them, up to `CLAUDE_CODE_SYNC_SKILLS_WAIT_T… |
|
v2.1.246syncClaudeAiPlugins |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming syncClaudeAiPlugins after this was published.
the line in the docs| [Disable claude.ai sync](/docs/en/settings-reference#syncclaudeaiskills) | Stop Claude Code from loading the [skills](/docs/en/skills#how-synced-skills-behave) and [plugins](/docs/en/plugins-reference#synced-plugins) your developers enab… |
|
v2.1.271breakdown |
Documentation arrivedAnthropic's documentation has since written up breakdown, on Beta.
the line in the docsPer-iteration token usage breakdown. |
|
v2.1.271multiplier |
Documentation arrivedAnthropic's documentation has since written up multiplier, on pricing.
the line in the docs*<sup>1 Cache hits and refreshes on Claude Fable 5.1 and Claude Mythos 5.1 are priced at 0.025x the base input price. All other models use the standard 0.1x multiplier.</sup>* |
|
v2.1.267_meta |
Documentation arrivedAnthropic's documentation has since written up _meta, on SEP-2640: Skills Extension.
the line in the docs* [Skill `_meta` Keys](https://github.com/modelcontextprotocol/ext-skills/blob/main/docs/archive/skill-meta-keys.md): `_meta` key conventions for skill resources |
|
v2.1.271dependencies |
Documentation arrivedAnthropic's documentation has since written up dependencies, on Create and distribute a plugin marketplace.
the line in the docsClaude Code copies each installed plugin into the local versioned plugin cache at `~/.claude/plugins/cache`, unless the plugin loads in place. A [`command` source in link mode](#copy-mode-and-link-mode) loads in place, and so does a [relat… |
|
v2.1.265plugin.json |
Documentation arrivedAnthropic's documentation has since written up plugin.json, on Create and distribute a plugin marketplace.
the line in the docs| `displayName` | string | Human-readable name shown in UI surfaces. When neither the entry nor the plugin's `plugin.json` sets one, users see the plugin's `name`. May contain spaces and any casing. Not used for namespacing or lookup. | |
|
v2.1.246${CLAUDE_PLUGIN_ROOT} |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming ${CLAUDE_PLUGIN_ROOT} after this was published.
the line in the docs* `${CLAUDE_PLUGIN_ROOT}`: the plugin's installation directory, for scripts bundled with a [plugin](/docs/en/plugins). See [plugin environment variables](/docs/en/plugins-reference#environment-variables) for how the path behaves across upd… |
|
v2.1.257CLAUDE_CODE_SUBPROCESS_ENV_SCRUB |
Documentation arrivedA small documentation edit on Environment variables touched a line naming CLAUDE_CODE_SUBPROCESS_ENV_SCRUB after this was published.
the line in the docs| `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` | Set to `1` to strip credentials from subprocess environments (Bash tool, hooks, MCP stdio servers): Anthropic and cloud provider credentials, any other variable that Claude Code recognizes as a creden… |
|
v2.1.260dictation |
Documentation arrivedAnthropic's documentation has since written up dictation, on How Claude Science works with your data.
the line in the docs* **Organization settings** for connectors, skills, the sandbox network allowlist, SSH hosts, Modal, model endpoints, and memory (see [Admin controls](/docs/claude-science/admin-controls)). There is no organization setting for web search, … |
|
v2.1.260dictation |
Documentation arrivedAnthropic's documentation has since written up dictation, on How Claude Science works with your data.
the line in the docs* **Organization settings** for connectors, skills, the sandbox network allowlist, SSH hosts, Modal, model endpoints, and memory (see [Admin controls](/docs/claude-science/admin-controls)). There is no organization setting for web search, … |
|
v2.1.268deniedDomains |
Documentation arrivedAnthropic's documentation has since written up deniedDomains, on Configure the sandboxed Bash tool.
the line in the docsA per-command list widens only what the sandbox denies by default. [`deniedDomains`](/docs/en/settings-reference#sandbox-network-denieddomains) entries still block. When [`strictAllowlist`](/docs/en/settings-reference#sandbox-network-stric… |
|
v2.1.246permissions.additionalDirectories |
Documentation arrivedAnthropic's documentation has since written up permissions.additionalDirectories, on Configure the sandboxed Bash tool.
the line in the docsAsk Claude to run a command, such as a build or a test suite. By default, commands inside the sandbox can write to the working directory, the session temp directory, and any [directories you've added](/docs/en/permissions#additional-direct… |
|
v2.1.236classifierContext |
Documentation arrivedAnthropic's documentation has since written up classifierContext, on Choose a permission mode.
the line in the docsYou can annotate a call's result with a [PostToolUse hook's `classifierContext` field](/docs/en/hooks#annotate-a-result-for-the-auto-mode-classifier), which the classifier reads as application-provided context. The field requires Claude Co… |
|
v2.1.236classifierContext |
Documentation arrivedAnthropic's documentation has since written up classifierContext, on Choose a permission mode.
the line in the docsYou can annotate a call's result with a [PostToolUse hook's `classifierContext` field](/docs/en/hooks#annotate-a-result-for-the-auto-mode-classifier), which the classifier reads as application-provided context. The field requires Claude Co… |
|
v2.1.234interpreter |
Documentation arrivedAnthropic's documentation has since written up interpreter, on Configure auto mode.
the line in the docsBy default, narrow Bash and PowerShell allow rules such as `Bash(npm test)` stay in effect in auto mode. Claude Code resolves them before the classifier runs, unless the command carries [per-command allowed domains](/docs/en/sandboxing#per… |
|
v2.1.251CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC, on Find bugs with ultrareview.
the line in the docsClaude Code doesn't post from your machine. It sends the findings to a [cloud session](/docs/en/claude-code-on-the-web), which posts the comment through the GitHub account you've connected to Claude. Posting requires the same claude.ai sig… |
|
v2.1.269/code-review ultra |
Documentation arrivedAnthropic's documentation has since written up /code-review ultra, on Find bugs with ultrareview.
the line in the docsUltrareview is a deep code review that runs as a [cloud session](/docs/en/claude-code-on-the-web) on Anthropic's infrastructure. When you run `/code-review ultra`, Claude Code launches a fleet of reviewer agents in a cloud sandbox to find … |
|
v2.1.267/list-agents |
Documentation arrivedAnthropic's documentation has since written up /list-agents, on Tools reference.
the line in the docs| `ListAgents` | Lists the agents Claude can message with `SendMessage`: subagents in the session, [agent team](/docs/en/agent-teams) teammates, your other local Claude Code sessions, and, while this session is connected to [Remote Control… |
|
v2.1.248/list-agents |
Documentation arrivedAnthropic's documentation has since written up /list-agents, on Tools reference.
the line in the docs| `ListAgents` | Lists the agents Claude can message with `SendMessage`: subagents in the session, [agent team](/docs/en/agent-teams) teammates, your other local Claude Code sessions, and, while this session is connected to [Remote Control… |
|
v2.1.239/list-agents |
Documentation arrivedAnthropic's documentation has since written up /list-agents, on Tools reference.
the line in the docs| `ListAgents` | Lists the agents Claude can message with `SendMessage`: subagents in the session, [agent team](/docs/en/agent-teams) teammates, your other local Claude Code sessions, and, while this session is connected to [Remote Control… |
|
v2.1.239/list-agents |
Documentation arrivedAnthropic's documentation has since written up /list-agents, on Tools reference.
the line in the docs| `ListAgents` | Lists the agents Claude can message with `SendMessage`: subagents in the session, [agent team](/docs/en/agent-teams) teammates, your other local Claude Code sessions, and, while this session is connected to [Remote Control… |
|
v2.1.268@mention |
Documentation arrivedAnthropic's documentation has since written up @mention, on Claude Code in Slack.
the line in the docsIn Code + Chat routing mode, when you mention @Claude in a Slack channel or thread, Claude automatically detects whether your message is a coding task. Coding tasks go to a Claude Code cloud session. Anything else gets a regular chat reply… |
|
v2.1.239--mcp-config |
Documentation arrivedA small documentation edit on All settings touched a line naming --mcp-config after this was published.
the line in the docsIn cloud sessions, Claude Code also ignores server-delivered mid-session MCP updates, the path behind cloud session configuration and SDK `setMcpServers()` calls that reach those sessions. In-process `type: "sdk"` entries stay exempt there… |
|
v2.1.239--mcp-config |
Documentation arrivedA small documentation edit on All settings touched a line naming --mcp-config after this was published.
the line in the docsIn cloud sessions, Claude Code also ignores server-delivered mid-session MCP updates, the path behind cloud session configuration and SDK `setMcpServers()` calls that reach those sessions. In-process `type: "sdk"` entries stay exempt there… |
|
v2.1.239--mcp-config |
Documentation arrivedA small documentation edit on All settings touched a line naming --mcp-config after this was published.
the line in the docsIn cloud sessions, Claude Code also ignores server-delivered mid-session MCP updates, the path behind cloud session configuration and SDK `setMcpServers()` calls that reach those sessions. In-process `type: "sdk"` entries stay exempt there… |
|
v2.1.239--mcp-config |
Documentation arrivedA small documentation edit on All settings touched a line naming --mcp-config after this was published.
the line in the docsIn cloud sessions, Claude Code also ignores server-delivered mid-session MCP updates, the path behind cloud session configuration and SDK `setMcpServers()` calls that reach those sessions. In-process `type: "sdk"` entries stay exempt there… |
|
v2.1.239--mcp-config |
Documentation arrivedA small documentation edit on All settings touched a line naming --mcp-config after this was published.
the line in the docsIn cloud sessions, Claude Code also ignores server-delivered mid-session MCP updates, the path behind cloud session configuration and SDK `setMcpServers()` calls that reach those sessions. In-process `type: "sdk"` entries stay exempt there… |
|
v2.1.234setup-token |
Documentation arrivedA small documentation edit on Test self-hosted environments end to end touched a line naming setup-token after this was published.
the line in the docsThere is no long-lived CI token for this today. The scope that grants cloud-session control, `user:sessions:claude_code`, is capped server-side at 30 days, so `claude setup-token`, which mints a one-year inference-only token, doesn't cover… |
|
v2.1.234claude setup-token |
Documentation arrivedA small documentation edit on Test self-hosted environments end to end touched a line naming claude setup-token after this was published.
the line in the docsThere is no long-lived CI token for this today. The scope that grants cloud-session control, `user:sessions:claude_code`, is capped server-side at 30 days, so `claude setup-token`, which mints a one-year inference-only token, doesn't cover… |
|
v2.1.239/chrome |
Documentation arrivedAnthropic's documentation has since written up /chrome, on Overview.
the line in the docs| Debug live web applications | [Chrome](/docs/en/chrome) | |
|
v2.1.257.mcp.json |
Documentation arrivedA small documentation edit on Connect to MCP servers touched a line naming .mcp.json after this was published.
the line in the docs* **Cloud sessions**: commit a `.mcp.json` to your repository. See [Edit .mcp.json directly](#edit-mcp-json-directly). |
|
v2.1.248.mcp.json |
Documentation arrivedA small documentation edit on Connect to MCP servers touched a line naming .mcp.json after this was published.
the line in the docs* **Cloud sessions**: commit a `.mcp.json` to your repository. See [Edit .mcp.json directly](#edit-mcp-json-directly). |
|
v2.1.257disableRemoteControl |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming disableRemoteControl after this was published.
the line in the docsOn Team and Enterprise plans, an Owner enables or disables [Remote Control](/docs/en/remote-control) and [cloud sessions](/docs/en/claude-code-on-the-web) organization-wide in [Claude Code admin settings](https://claude.ai/admin-settings/c… |
|
v2.1.257disableRemoteControl |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming disableRemoteControl after this was published.
the line in the docsOn Team and Enterprise plans, an Owner enables or disables [Remote Control](/docs/en/remote-control) and [cloud sessions](/docs/en/claude-code-on-the-web) organization-wide in [Claude Code admin settings](https://claude.ai/admin-settings/c… |
|
v2.1.251disableRemoteControl |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming disableRemoteControl after this was published.
the line in the docsOn Team and Enterprise plans, an Owner enables or disables [Remote Control](/docs/en/remote-control) and [cloud sessions](/docs/en/claude-code-on-the-web) organization-wide in [Claude Code admin settings](https://claude.ai/admin-settings/c… |
|
v2.1.271quickstart |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming quickstart after this was published.
the line in the docsHooks are user-defined shell commands, HTTP endpoints, MCP tool calls, LLM prompts, or subagents that execute automatically at specific points in Claude Code's lifecycle. Claude Code fires the same hook events wherever it runs: sessions in… |
|
v2.1.271quickstart |
Documentation arrivedA small documentation edit on Hooks reference touched a line naming quickstart after this was published.
the line in the docsHooks are user-defined shell commands, HTTP endpoints, MCP tool calls, LLM prompts, or subagents that execute automatically at specific points in Claude Code's lifecycle. Claude Code fires the same hook events wherever it runs: sessions in… |