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 |
|---|---|---|
v2.1.268/plugin |
Documentation arrivedA small documentation edit on Plugins in the SDK touched a line naming /plugin after this was published.
the line in the docs* **Relative paths**: resolved relative to the `cwd` option (for example, `"./plugins/my-plugin"`) |
|
v2.1.260/advisor |
Documentation arrivedAnthropic's documentation has since written up /advisor, on Escalate hard decisions with the advisor tool.
the line in the docs* For an advisor the table lists as rejected, Claude Code doesn't attach it to the main model's requests. The `/advisor` command output and a notification show this. Subagents whose own model satisfies the pairing may still use the advisor. |
|
v2.1.234/advisor |
Documentation arrivedAnthropic's documentation has since written up /advisor, on Escalate hard decisions with the advisor tool.
the line in the docs* For an advisor the table lists as rejected, Claude Code doesn't attach it to the main model's requests. The `/advisor` command output and a notification show this. Subagents whose own model satisfies the pairing may still use the advisor. |
|
v2.1.269/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Extend Claude with skills.
the line in the docsIn [non-interactive sessions](/docs/en/headless), the names `help` and `feedback` aren't reserved for their terminal-only built-in commands, so a plugin skill with one of those names keeps its bare command there. Every other terminal-only … |
|
v2.1.268/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Extend Claude with skills.
the line in the docsIn [non-interactive sessions](/docs/en/headless), the names `help` and `feedback` aren't reserved for their terminal-only built-in commands, so a plugin skill with one of those names keeps its bare command there. Every other terminal-only … |
|
v2.1.265/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Extend Claude with skills.
the line in the docsIn [non-interactive sessions](/docs/en/headless), the names `help` and `feedback` aren't reserved for their terminal-only built-in commands, so a plugin skill with one of those names keeps its bare command there. Every other terminal-only … |
|
v2.1.269/commit |
Documentation arrivedAnthropic's documentation has since written up /commit, on Extend Claude with skills.
the line in the docsWhen it compares names, Claude Code ignores case, spacing, and invisible characters, and treats compatibility forms such as fullwidth letters and dash variants as their plain equivalents. For example, a local `commit` skill keeps `/commit`… |
|
v2.1.269/commit |
Documentation arrivedAnthropic's documentation has since written up /commit, on Extend Claude with skills.
the line in the docsWhen it compares names, Claude Code ignores case, spacing, and invisible characters, and treats compatibility forms such as fullwidth letters and dash variants as their plain equivalents. For example, a local `commit` skill keeps `/commit`… |
|
v2.1.269anthropic-skills: |
Documentation arrivedAnthropic's documentation has since written up anthropic-skills:, on Extend Claude with skills.
the line in the docs| Any of the above and a skill [synced from your claude.ai account](#how-synced-skills-behave) | The other skill or command. The synced skill still runs as `/anthropic-skills:<name>`. See [When a synced skill name matches another command](… |
|
v2.1.269anthropic-skills: |
Documentation arrivedAnthropic's documentation has since written up anthropic-skills:, on Extend Claude with skills.
the line in the docs| Any of the above and a skill [synced from your claude.ai account](#how-synced-skills-behave) | The other skill or command. The synced skill still runs as `/anthropic-skills:<name>`. See [When a synced skill name matches another command](… |
|
v2.1.268/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Extend Claude with skills.
the line in the docs| A plugin skill and a skill at any of the locations above | Both load, because plugin skills are namespaced as `/plugin-name:skill-name` | |
|
v2.1.242/code-review |
Documentation arrivedAnthropic's documentation has since written up /code-review, on Extend Claude with skills.
the line in the docs| Any of those locations and a [bundled skill](#bundled-skills) | Your skill replaces the bundled command, but not its aliases. A project `code-review` skill replaces `/code-review`, and the bundled alias `/review` never runs your skill | |
|
v2.1.268/remote |
Documentation arrivedA small documentation edit on Claude Code on mobile touched a line naming /remote after this was published.
the line in the docsRemote Control connects the Claude app to a Claude Code session running on your machine, so code execution and filesystem access stay local while you drive the session from your phone. Start the session on your computer with `claude remote… |
|
v2.1.267claude remote-control |
Documentation arrivedA small documentation edit on Claude Code on mobile touched a line naming claude remote-control after this was published.
the line in the docsRemote Control connects the Claude app to a Claude Code session running on your machine, so code execution and filesystem access stay local while you drive the session from your phone. Start the session on your computer with `claude remote… |
|
v2.1.265claude remote-control |
Documentation arrivedA small documentation edit on Claude Code on mobile touched a line naming claude remote-control after this was published.
the line in the docsRemote Control connects the Claude app to a Claude Code session running on your machine, so code execution and filesystem access stay local while you drive the session from your phone. Start the session on your computer with `claude remote… |
|
v2.1.234/remote-control |
Documentation arrivedA small documentation edit on Claude Code on mobile touched a line naming /remote-control after this was published.
the line in the docsRemote Control connects the Claude app to a Claude Code session running on your machine, so code execution and filesystem access stay local while you drive the session from your phone. Start the session on your computer with `claude remote… |
|
v2.1.267env |
Documentation arrivedAnthropic's documentation has since written up env, on Use Claude Code with Chrome.
the line in the docsIn [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), a permission prompt appears before Claude records a GIF, opens a new tab, or runs a shortcut. If [bypass permissions mode is available](/docs/en/permission-m… |
|
v2.1.248browser_batch |
Documentation arrivedAnthropic's documentation has since written up browser_batch, on Use Claude Code with Chrome.
the line in the docsA `tabs_context_mcp` call also prompts when it sets `createIfEmpty`, and so does a `browser_batch` call that includes any of these actions. |
|
v2.1.267Text |
Documentation arrivedAnthropic's documentation has since written up Text, on Agent SDK reference - Python.
the line in the docsTextBlock |
|
v2.1.257outputStyle |
Documentation arrivedA small documentation edit on Modifying system prompts touched a line naming outputStyle after this was published.
the line in the docsIn the Python SDK, set `outputStyle` through the `settings` option, which takes a JSON string such as `'{"outputStyle": "Explanatory"}'` or a path to a settings file that sets it. |
|
v2.1.257outputStyle |
Documentation arrivedA small documentation edit on Modifying system prompts touched a line naming outputStyle after this was published.
the line in the docsIn the Python SDK, set `outputStyle` through the `settings` option, which takes a JSON string such as `'{"outputStyle": "Explanatory"}'` or a path to a settings file that sets it. |
|
v2.1.268/web-setup |
Documentation arrivedA small documentation edit on Get started with Claude Code on the web touched a line naming /web-setup after this was published.
the line in the docsIf you already use the GitHub CLI (`gh`), you can set up Claude Code on the web from your terminal. This requires the [Claude Code CLI](/docs/en/quickstart). On Team and Enterprise plans, `/web-setup` is available only after an Owner turns… |
|
v2.1.268/web-setup |
Documentation arrivedA small documentation edit on Get started with Claude Code on the web touched a line naming /web-setup after this was published.
the line in the docsIf you already use the GitHub CLI (`gh`), you can set up Claude Code on the web from your terminal. This requires the [Claude Code CLI](/docs/en/quickstart). On Team and Enterprise plans, `/web-setup` is available only after an Owner turns… |
|
v2.1.268/web-setup |
Documentation arrivedA small documentation edit on Get started with Claude Code on the web touched a line naming /web-setup after this was published.
the line in the docsIf you already use the GitHub CLI (`gh`), you can set up Claude Code on the web from your terminal. This requires the [Claude Code CLI](/docs/en/quickstart). On Team and Enterprise plans, `/web-setup` is available only after an Owner turns… |
|
v2.1.268/web-setup |
Documentation arrivedA small documentation edit on Get started with Claude Code on the web touched a line naming /web-setup after this was published.
the line in the docsIf you already use the GitHub CLI (`gh`), you can set up Claude Code on the web from your terminal. This requires the [Claude Code CLI](/docs/en/quickstart). On Team and Enterprise plans, `/web-setup` is available only after an Owner turns… |
|
v2.1.265directory |
Documentation arrivedAnthropic's documentation has since written up directory, on Use Claude Code on the web.
the line in the docs| Clean git state | Your working directory must have no uncommitted changes. Teleport prompts you to stash changes if needed. | |
|
v2.1.269tee |
Documentation arrivedAnthropic's documentation has since written up tee, on Use Claude Code on the web.
the line in the docsOpen the session on claude.ai or the Claude mobile app to check progress or interact directly. From there you can steer Claude, provide feedback, or answer questions as in any other conversation. |
|
v2.1.269tee |
Documentation arrivedAnthropic's documentation has since written up tee, on Use Claude Code on the web.
the line in the docsOpen the session on claude.ai or the Claude mobile app to check progress or interact directly. From there you can steer Claude, provide feedback, or answer questions as in any other conversation. |
|
v2.1.269tee |
Documentation arrivedAnthropic's documentation has since written up tee, on Use Claude Code on the web.
the line in the docsOpen the session on claude.ai or the Claude mobile app to check progress or interact directly. From there you can steer Claude, provide feedback, or answer questions as in any other conversation. |
|
v2.1.269tee |
Documentation arrivedAnthropic's documentation has since written up tee, on Use Claude Code on the web.
the line in the docsOpen the session on claude.ai or the Claude mobile app to check progress or interact directly. From there you can steer Claude, provide feedback, or answer questions as in any other conversation. |
|
v2.1.269config |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming config after this was published.
the line in the docs| `effort` | `'low' \| 'medium' \| 'high' \| 'xhigh' \| 'max'` | `undefined` | Controls how much effort Claude puts into its response. Works with adaptive thinking to guide thinking depth. See [adjust the effort level](/docs/en/model-confi… |
|
v2.1.265muted |
Documentation arrivedAnthropic's documentation has since written up muted, on Troubleshoot Claude Tag setup.
the line in the docsMost of the silence problems in this section span a whole workspace or channel and come down to configuration. If Claude stays silent in one thread but answers everywhere else, a setting isn't the cause. Either Claude's session for that th… |
|
v2.1.265muted |
Documentation arrivedAnthropic's documentation has since written up muted, on Troubleshoot Claude Tag setup.
the line in the docsMost of the silence problems in this section span a whole workspace or channel and come down to configuration. If Claude stays silent in one thread but answers everywhere else, a setting isn't the cause. Either Claude's session for that th… |
|
v2.1.269config |
Documentation arrivedAnthropic's documentation has since written up config, on Troubleshoot Claude Tag setup.
the line in the docsMost of the silence problems in this section span a whole workspace or channel and come down to configuration. If Claude stays silent in one thread but answers everywhere else, a setting isn't the cause. Either Claude's session for that th… |
|
v2.1.267session |
Documentation arrivedAnthropic's documentation has since written up session, on Troubleshoot Claude Tag setup.
the line in the docsMost of the silence problems in this section span a whole workspace or channel and come down to configuration. If Claude stays silent in one thread but answers everywhere else, a setting isn't the cause. Either Claude's session for that th… |
|
v2.1.267session |
Documentation arrivedA small documentation edit on Claude Code changelog touched a line naming session after this was published.
the line in the docs* Fixed read-only git commands in Bash unexpectedly asking for permission after a session had been running for a while (regression in 2.1.269) |
|
v2.1.268admin |
Documentation arrivedA small documentation edit on Connect a service that isn't in the list touched a line naming admin after this was published.
the line in the docsClaude can call the endpoint with `curl`, an AWS SDK, or the AWS CLI. The sandbox holds no real AWS credentials, so a CLI or SDK signs the request with placeholder values; Agent Proxy strips that signature and re-signs with the stored cred… |
|
v2.1.267env |
Documentation arrivedA small documentation edit on Connect a service that isn't in the list touched a line naming env after this was published.
the line in the docsClaude can call the endpoint with `curl`, an AWS SDK, or the AWS CLI. The sandbox holds no real AWS credentials, so a CLI or SDK signs the request with placeholder values; Agent Proxy strips that signature and re-signs with the stored cred… |
|
v2.1.248wslInheritsWindowsSettings |
Documentation arrivedA small documentation edit on All settings touched a line naming wslInheritsWindowsSettings after this was published.
the line in the docsChoose whether Claude Code applies only the highest-priority [managed source](/docs/en/managed-settings#how-claude-code-combines-managed-sources) your organization delivers, or combines every admin source it delivers. By default Claude Cod… |
|
v2.1.246managed-settings.json |
Documentation arrivedA small documentation edit on All settings touched a line naming managed-settings.json after this was published.
the line in the docsChoose whether Claude Code applies only the highest-priority [managed source](/docs/en/managed-settings#how-claude-code-combines-managed-sources) your organization delivers, or combines every admin source it delivers. By default Claude Cod… |
|
v2.1.268ultracode |
Documentation arrivedA small documentation edit on All settings touched a line naming ultracode after this was published.
the line in the docs* **Per-session overrides**: `/effort ultracode` turns ultracode on for one session without this key. The `--effort ultracode` flag also turns it on for one session and requires Claude Code v2.1.203 or later |
|
v2.1.268head |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming head after this was published.
the line in the docsWhether [`ANTHROPIC_CUSTOM_HEADERS`](/docs/en/env-vars#variables) needs approval also depends on the delivered value. Headers that only tag requests, such as `Accept-Language`, apply without the dialog. A line that names a credential, an o… |
|
v2.1.260ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming ANTHROPIC_CUSTOM_HEADERS after this was published.
the line in the docsWhether [`ANTHROPIC_CUSTOM_HEADERS`](/docs/en/env-vars#variables) needs approval also depends on the delivered value. Headers that only tag requests, such as `Accept-Language`, apply without the dialog. A line that names a credential, an o… |
|
v2.1.260ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming ANTHROPIC_CUSTOM_HEADERS after this was published.
the line in the docsWhether [`ANTHROPIC_CUSTOM_HEADERS`](/docs/en/env-vars#variables) needs approval also depends on the delivered value. Headers that only tag requests, such as `Accept-Language`, apply without the dialog. A line that names a credential, an o… |
|
v2.1.251ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedA small documentation edit on Configure server-managed settings touched a line naming ANTHROPIC_CUSTOM_HEADERS after this was published.
the line in the docsWhether [`ANTHROPIC_CUSTOM_HEADERS`](/docs/en/env-vars#variables) needs approval also depends on the delivered value. Headers that only tag requests, such as `Accept-Language`, apply without the dialog. A line that names a credential, an o… |
|
v2.1.234tui |
Documentation arrivedA small documentation edit on Error reference touched a line naming tui after this was published.
the line in the docsThese errors come from the `claude` command line and its subcommands, from a command name you submit at the prompt, and from commands such as `/security-review` that gather context by running shell commands before their prompt runs. They a… |
|
v2.1.248/tui |
Documentation arrivedA small documentation edit on Error reference touched a line naming /tui after this was published.
the line in the docsThese errors come from the `claude` command line and its subcommands, from a command name you submit at the prompt, and from commands such as `/security-review` that gather context by running shell commands before their prompt runs. They a… |
|
v2.1.234/tui |
Documentation arrivedA small documentation edit on Error reference touched a line naming /tui after this was published.
the line in the docsThese errors come from the `claude` command line and its subcommands, from a command name you submit at the prompt, and from commands such as `/security-review` that gather context by running shell commands before their prompt runs. They a… |
|
v2.1.234/tui |
Documentation arrivedA small documentation edit on Error reference touched a line naming /tui after this was published.
the line in the docsThese errors come from the `claude` command line and its subcommands, from a command name you submit at the prompt, and from commands such as `/security-review` that gather context by running shell commands before their prompt runs. They a… |
|
v2.1.232/tui |
Documentation arrivedA small documentation edit on Error reference touched a line naming /tui after this was published.
the line in the docsThese errors come from the `claude` command line and its subcommands, from a command name you submit at the prompt, and from commands such as `/security-review` that gather context by running shell commands before their prompt runs. They a… |