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 |
|---|---|---|
v2.1.267fs.write |
Documentation arrivedAnthropic's documentation has since written up fs.write, on Manage mods for your organization.
the line in the docsEach time another mod is about to load, your mod receives the list that `claude plugin validate` prints, in an event named [`plugin.register`](/docs/en/plugins/mods/reference#other-mods). A mod in `prependPlugins` can read that list and re… |
|
v2.1.267fs.read |
Documentation arrivedAnthropic's documentation has since written up fs.read, on Manage mods for your organization.
the line in the docs* **Deny rules and your managed hooks take precedence.** Where the guard loads, a user's mod can't approve a call that a `deny` rule refuses, whichever settings file holds the rule. A block from a `PreToolUse` hook in managed settings is f… |
|
v2.1.269claude plugin eval init |
Documentation arrivedA small documentation edit on Test plugins with evals touched a line naming claude plugin eval init after this was published.
the line in the docs* The same authentication and model provider your normal Claude Code sessions use. Eval runs, judge-scored graders, and `claude plugin eval init` call the model with your credentials, so they count against your plan's usage limits or your … |
|
v2.1.283GIT_CONFIG_VALUE_n |
Documentation arrivedAnthropic's documentation has since written up GIT_CONFIG_VALUE_n, on Customize sessions in self-hosted environments.
the line in the docs| `GIT_CONFIG_COUNT`, `GIT_CONFIG_KEY_n`, `GIT_CONFIG_VALUE_n` | Git settings the runner fixes for the git your hook runs. [Git configuration inside lifecycle hooks](#git-configuration-inside-lifecycle-hooks) describes them. Requires Claud… |
|
v2.1.283GIT_CONFIG_KEY_n |
Documentation arrivedAnthropic's documentation has since written up GIT_CONFIG_KEY_n, on Customize sessions in self-hosted environments.
the line in the docs| `GIT_CONFIG_COUNT`, `GIT_CONFIG_KEY_n`, `GIT_CONFIG_VALUE_n` | Git settings the runner fixes for the git your hook runs. [Git configuration inside lifecycle hooks](#git-configuration-inside-lifecycle-hooks) describes them. Requires Claud… |
|
v2.1.283GIT_CONFIG_COUNT |
Documentation arrivedAnthropic's documentation has since written up GIT_CONFIG_COUNT, on Customize sessions in self-hosted environments.
the line in the docs| `GIT_CONFIG_COUNT`, `GIT_CONFIG_KEY_n`, `GIT_CONFIG_VALUE_n` | Git settings the runner fixes for the git your hook runs. [Git configuration inside lifecycle hooks](#git-configuration-inside-lifecycle-hooks) describes them. Requires Claud… |
|
v2.1.283GIT_CONFIG_COUNT |
Documentation arrivedAnthropic's documentation has since written up GIT_CONFIG_COUNT, on Customize sessions in self-hosted environments.
the line in the docs| `GIT_CONFIG_COUNT`, `GIT_CONFIG_KEY_n`, `GIT_CONFIG_VALUE_n` | Git settings the runner fixes for the git your hook runs. [Git configuration inside lifecycle hooks](#git-configuration-inside-lifecycle-hooks) describes them. Requires Claud… |
|
v2.1.267ui.resolve |
Documentation arrivedAnthropic's documentation has since written up ui.resolve, on Draw in the interface with a mod.
the line in the docsconst { Box, Text } = $.ui.resolve(e) |
|
v2.1.267ui.resolve |
Documentation arrivedAnthropic's documentation has since written up ui.resolve, on Draw in the interface with a mod.
the line in the docsconst { Box, Text } = $.ui.resolve(e) |
|
v2.1.281ui.render |
Documentation arrivedAnthropic's documentation has since written up ui.render, on Draw in the interface with a mod.
the line in the docson('ui.render', { component: 'Spinner' }, async ($, e, next) => { |
|
v2.1.277ui.render |
Documentation arrivedAnthropic's documentation has since written up ui.render, on Draw in the interface with a mod.
the line in the docson('ui.render', { component: 'Spinner' }, async ($, e, next) => { |
|
v2.1.284--model |
Documentation arrivedA small documentation edit on Model configuration touched a line naming --model after this was published.
the line in the docsAdmins can also configure the organization default to override user selection. With override on, it takes precedence over the `model` value in user, project, and local settings, so a model you save with `/model` applies for the current ses… |
|
v2.1.259ANTHROPIC_MODEL |
Documentation arrivedA small documentation edit on Model configuration touched a line naming ANTHROPIC_MODEL after this was published.
the line in the docsAdmins can also configure the organization default to override user selection. With override on, it takes precedence over the `model` value in user, project, and local settings, so a model you save with `/model` applies for the current ses… |
|
v2.1.286bwrap |
Documentation arrivedAnthropic's documentation has since written up bwrap, on Configure the sandboxed Bash tool.
the line in the docsIn an unprivileged container, [bubblewrap](#os-level-enforcement) can't mount a fresh `/proc` filesystem, so sandboxed commands fail with a `bwrap` error such as `Can't mount proc on /newroot/proc: Operation not permitted`. Set [`enableWea… |
|
v2.1.281/copy |
Documentation arrivedAnthropic's documentation has since written up /copy, on Configure the sandboxed Bash tool.
the line in the docsTo put Claude's output on your clipboard, ask Claude to print it in its response, then run [`/copy`](/docs/en/commands). `/copy` writes to the clipboard from the Claude Code process rather than from a sandboxed command. |
|
v2.1.285availableModels |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming availableModels after this was published.
the line in the docsThe classifier runs on Claude Sonnet 5 by default rather than on your `/model` selection. A classifier model that Anthropic configures server-side takes precedence over that default. When your session's model is Claude Sonnet 4.6, or when … |
|
v2.1.283ANTHROPIC_DEFAULT_OPUS_MODEL |
Documentation arrivedA small documentation edit on Model configuration touched a line naming ANTHROPIC_DEFAULT_OPUS_MODEL after this was published.
the line in the docs* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5. When it's excluded, the classifier runs on the session's m… |
|
v2.1.285sandbox.network |
Documentation arrivedAnthropic's documentation has since written up sandbox.network, on All settings.
the line in the docs| [`sandbox.network.allowLocalBinding`](#sandbox-network-allowlocalbinding) | Let [sandboxed](/docs/en/sandboxing) commands listen on network ports and connect to localhost on macOS | Sandbox settings | Any file | |
|
v2.1.285sandbox.network |
Documentation arrivedAnthropic's documentation has since written up sandbox.network, on All settings.
the line in the docs| [`sandbox.network.allowLocalBinding`](#sandbox-network-allowlocalbinding) | Let [sandboxed](/docs/en/sandboxing) commands listen on network ports and connect to localhost on macOS | Sandbox settings | Any file | |
|
v2.1.285socksProxyPort |
Documentation arrivedAnthropic's documentation has since written up socksProxyPort, on Configure the sandboxed Bash tool.
the line in the docs| `excludedCommands`, `ignoreViolations`, `network.allowedDomains`, `network.allowUnixSockets`, `network.allowMachLookup`, `network.httpProxyPort`, `network.socksProxyPort` | Every entry | |
|
v2.1.285httpProxyPort |
Documentation arrivedAnthropic's documentation has since written up httpProxyPort, on Configure the sandboxed Bash tool.
the line in the docs| `excludedCommands`, `ignoreViolations`, `network.allowedDomains`, `network.allowUnixSockets`, `network.allowMachLookup`, `network.httpProxyPort`, `network.socksProxyPort` | Every entry | |
|
v2.1.281sandbox.credentials |
Documentation arrivedAnthropic's documentation has since written up sandbox.credentials, on Configure the sandboxed Bash tool.
the line in the docs* Add [`sandbox.credentials`](#protect-credentials) entries for credential directories such as `~/.aws` and `~/.ssh` and for secret environment variables, since the default read policy still allows them |
|
v2.1.285allowRead |
Documentation arrivedAnthropic's documentation has since written up allowRead, on Configure the sandboxed Bash tool.
the line in the docsClaude Code treats `deny` as `error` whenever the read block wouldn't be enforced: when you [disable filesystem isolation](#disable-filesystem-isolation), and when a `filesystem.allowRead` entry re-opens the file's path. |
|
v2.1.285allowRead |
Documentation arrivedAnthropic's documentation has since written up allowRead, on Configure the sandboxed Bash tool.
the line in the docsClaude Code treats `deny` as `error` whenever the read block wouldn't be enforced: when you [disable filesystem isolation](#disable-filesystem-isolation), and when a `filesystem.allowRead` entry re-opens the file's path. |
|
v2.1.284filesystem.allowRead |
Documentation arrivedAnthropic's documentation has since written up filesystem.allowRead, on Configure the sandboxed Bash tool.
the line in the docsClaude Code treats `deny` as `error` whenever the read block wouldn't be enforced: when you [disable filesystem isolation](#disable-filesystem-isolation), and when a `filesystem.allowRead` entry re-opens the file's path. |
|
v2.1.286bypassPermissions |
Documentation arrivedAnthropic's documentation has since written up bypassPermissions, on Configure the sandboxed Bash tool.
the line in the docs* **`bypassPermissions` mode**: the retry runs without a prompt |
|
v2.1.285bypassPermissions |
Documentation arrivedAnthropic's documentation has since written up bypassPermissions, on Configure the sandboxed Bash tool.
the line in the docs* **`bypassPermissions` mode**: the retry runs without a prompt |
|
v2.1.285allowUnsandboxedCommands |
Documentation arrivedAnthropic's documentation has since written up allowUnsandboxedCommands, on Configure the sandboxed Bash tool.
the line in the docsYou can disable the unsandboxed retry by setting `"allowUnsandboxedCommands": false` in your [sandbox settings](/docs/en/settings-reference#sandbox-settings). With the retry disabled, Claude Code ignores the `dangerouslyDisableSandbox` par… |
|
v2.1.285allowUnsandboxedCommands |
Documentation arrivedAnthropic's documentation has since written up allowUnsandboxedCommands, on Configure the sandboxed Bash tool.
the line in the docsYou can disable the unsandboxed retry by setting `"allowUnsandboxedCommands": false` in your [sandbox settings](/docs/en/settings-reference#sandbox-settings). With the retry disabled, Claude Code ignores the `dangerouslyDisableSandbox` par… |
|
v2.1.285blockReadsOutsideWorkingDirectories |
Documentation arrivedAnthropic's documentation has since written up blockReadsOutsideWorkingDirectories, on Configure the sandboxed Bash tool.
the line in the docs* **[`permissions.blockReadsOutsideWorkingDirectories`](/docs/en/settings-reference#permissions-blockreadsoutsideworkingdirectories)**: [Actions no mode auto-approves](/docs/en/permission-modes#actions-no-mode-auto-approves) covers the ret… |
|
v2.1.284dangerouslyDisableSandbox |
Documentation arrivedAnthropic's documentation has since written up dangerouslyDisableSandbox, on Configure the sandboxed Bash tool.
the line in the docsThe unsandboxed retry is an escape hatch for commands that fail inside the sandbox, such as tools that are incompatible with it. When the sandbox blocks a network connection, Claude Code names the denied host in the command's result, so Cl… |
|
v2.1.284dangerouslyDisableSandbox |
Documentation arrivedAnthropic's documentation has since written up dangerouslyDisableSandbox, on Configure the sandboxed Bash tool.
the line in the docsThe unsandboxed retry is an escape hatch for commands that fail inside the sandbox, such as tools that are incompatible with it. When the sandbox blocks a network connection, Claude Code names the denied host in the command's result, so Cl… |
|
v2.1.285sandbox.failIfUnavailable |
Documentation arrivedAnthropic's documentation has since written up sandbox.failIfUnavailable, on Configure the sandboxed Bash tool.
the line in the docsBy default, if the sandbox can't start because a dependency is missing or the platform is unsupported, Claude Code runs commands without sandboxing. To make Claude Code exit at startup instead, set [`sandbox.failIfUnavailable`](/docs/en/se… |
|
v2.1.284allowedDomains |
Documentation arrivedAnthropic's documentation has since written up allowedDomains, on Configure the sandboxed Bash tool.
the line in the docs| Network | No direct route out. Connections go through a proxy on your machine that checks each host against your allowed domains, which start empty. Your permission mode decides [what happens to other hosts](#hosts-outside-your-allowed-d… |
|
v2.1.285allowWrite |
Documentation arrivedAnthropic's documentation has since written up allowWrite, on Configure the sandboxed Bash tool.
the line in the docs| Writes | The working directory, a per-user temp directory, and [directories you've added](/docs/en/permissions#additional-directories-grant-file-access-not-configuration). [Protected paths](#protected-paths) stay write-denied | [`filesys… |
|
v2.1.285allowWrite |
Documentation arrivedAnthropic's documentation has since written up allowWrite, on Configure the sandboxed Bash tool.
the line in the docs| Writes | The working directory, a per-user temp directory, and [directories you've added](/docs/en/permissions#additional-directories-grant-file-access-not-configuration). [Protected paths](#protected-paths) stay write-denied | [`filesys… |
|
v2.1.284filesystem.denyWrite |
Documentation arrivedAnthropic's documentation has since written up filesystem.denyWrite, on Configure the sandboxed Bash tool.
the line in the docs| Writes | The working directory, a per-user temp directory, and [directories you've added](/docs/en/permissions#additional-directories-grant-file-access-not-configuration). [Protected paths](#protected-paths) stay write-denied | [`filesys… |
|
v2.1.284allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Extend Claude with skills.
the line in the docs* The frontmatter applies in every kind of session, so an `allowed-tools` grant goes through the normal [permission flow](/docs/en/permissions). If your organization sets `allowManagedPermissionRulesOnly`, the grant [doesn't apply](#when-o… |
|
v2.1.284allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Extend Claude with skills.
the line in the docs* The frontmatter applies in every kind of session, so an `allowed-tools` grant goes through the normal [permission flow](/docs/en/permissions). If your organization sets `allowManagedPermissionRulesOnly`, the grant [doesn't apply](#when-o… |
|
v2.1.284allowManagedPermissionRulesOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedPermissionRulesOnly, on Extend Claude with skills.
the line in the docs* The frontmatter applies in every kind of session, so an `allowed-tools` grant goes through the normal [permission flow](/docs/en/permissions). If your organization sets `allowManagedPermissionRulesOnly`, the grant [doesn't apply](#when-o… |
|
v2.1.284allowManagedPermissionRulesOnly |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowManagedPermissionRulesOnly after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.284allowManagedPermissionRulesOnly |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowManagedPermissionRulesOnly after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.284allowManagedPermissionRulesOnly |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowManagedPermissionRulesOnly after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.282allowManagedPermissionRulesOnly |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowManagedPermissionRulesOnly after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.282allowManagedPermissionRulesOnly |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowManagedPermissionRulesOnly after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.283allowed-tools |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowed-tools after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.282allowed-tools |
Documentation arrivedA small documentation edit on Extend agents with skills touched a line naming allowed-tools after this was published.
the line in the docsIn SDK sessions, you can pre-approve tools for a project or personal skill with the skill's [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your … |
|
v2.1.283/code-review ultra |
Documentation arrivedAnthropic's documentation has since written up /code-review ultra, on Find bugs with ultrareview.
the line in the docs`claude -p '/code-review ultra'` doesn't get you the findings, so use `claude ultrareview` in scripts. The `-p` run launches the cloud review and exits without waiting for it. When the review would bill usage credits, the `-p` run stops wi… |
|
v2.1.280/code-review ultra |
Documentation arrivedAnthropic's documentation has since written up /code-review ultra, on Find bugs with ultrareview.
the line in the docs`claude -p '/code-review ultra'` doesn't get you the findings, so use `claude ultrareview` in scripts. The `-p` run launches the cloud review and exits without waiting for it. When the review would bill usage credits, the `-p` run stops wi… |
|
v2.1.280/code-review ultra |
Documentation arrivedAnthropic's documentation has since written up /code-review ultra, on Find bugs with ultrareview.
the line in the docs`claude -p '/code-review ultra'` doesn't get you the findings, so use `claude ultrareview` in scripts. The `-p` run launches the cloud review and exits without waiting for it. When the review would bill usage credits, the `-p` run stops wi… |