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 |
|---|---|---|
v2.1.282skillOverrides |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming skillOverrides after this was published.
the line in the docsTo audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides… |
|
v2.1.282skillOverrides |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming skillOverrides after this was published.
the line in the docsTo audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides… |
|
v2.1.283/skills |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /skills after this was published.
the line in the docsTo audit one file or directory instead, pass its path, for example `/doctor prompt-audit .claude/skills/deploy`. The audit runs through the bundled `/claude-api` skill, so it's unavailable while that skill is turned off in [`skillOverrides… |
|
v2.1.283models |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming models after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.283models |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming models after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.283/doctor prompt-audit |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /doctor prompt-audit after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.269doctor |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming doctor after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.280/doctor |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /doctor after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.280/doctor |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /doctor after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.261/doctor |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /doctor after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.257/doctor |
Documentation arrivedA small documentation edit on How Claude remembers your project touched a line naming /doctor after this was published.
the line in the docsTo have Claude check these files for outdated or conflicting instructions, run `/doctor prompt-audit` in a session. Claude reads your CLAUDE.md, CLAUDE.local.md, and AGENTS.md files, plus the rules, skills, commands, subagents, and output … |
|
v2.1.282allowUnsandboxedCommands |
Documentation arrivedAnthropic's documentation has since written up allowUnsandboxedCommands, on Deploy managed settings.
the line in the docs* Claude Code treats every other invalid Boolean as the value that keeps the sandbox strictest until you fix it. A key that turns the sandbox or one of its restrictions on, such as `enabled` or `network.allowManagedDomainsOnly`, counts as … |
|
v2.1.283/status |
Documentation arrivedAnthropic's documentation has since written up /status, on Deploy managed settings.
the line in the docs* If you set a Boolean key to a quoted `"true"` or `"false"`, the value counts as that Boolean. Instead of a warning, `/status` shows a notice asking you to remove the quotes. |
|
v2.1.283claude plugin list |
Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin list after this was published.
the line in the docsWhen a registered marketplace stops loading because its name imitates an official one, `claude plugin list` and `/plugin` report `Claude Code refuses the marketplace name "<name>"`. The message tells you to remove the marketplace. Removing… |
|
v2.1.265claude plugin list |
Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin list after this was published.
the line in the docsWhen a registered marketplace stops loading because its name imitates an official one, `claude plugin list` and `/plugin` report `Claude Code refuses the marketplace name "<name>"`. The message tells you to remove the marketplace. Removing… |
|
v2.1.283/hooks |
Documentation arrivedAnthropic's documentation has since written up /hooks, on Plugin manifest reference.
the line in the docsIf you leave one of these variables outside quotes in a shell-form command in a hooks file, `claude plugin validate` warns about it unless the hook sets [`shell`](/docs/en/hooks#command-hook-fields) to `"powershell"`. |
|
v2.1.283claude plugin validate |
Documentation arrivedAnthropic's documentation has since written up claude plugin validate, on Plugin manifest reference.
the line in the docsIf you leave one of these variables outside quotes in a shell-form command in a hooks file, `claude plugin validate` warns about it unless the hook sets [`shell`](/docs/en/hooks#command-hook-fields) to `"powershell"`. |
|
v2.1.281--scope |
Documentation arrivedAnthropic's documentation has since written up --scope, on Plugin commands reference.
the line in the docs| `-s, --scope <scope>` | Scope to update: `user`, `project`, `local`, or `managed`. Auto-detected when omitted | |
|
v2.1.268failureCode |
Documentation arrivedAnthropic's documentation has since written up failureCode, on Error reference.
the line in the docs`claude plugin uninstall` exits 1, and with `--json` the result carries `failureCode: "settings_still_on"`. `/plugin` shows the same message. |
|
v2.1.283enabledPlugins |
Documentation arrivedAnthropic's documentation has since written up enabledPlugins, on Error reference.
the line in the docsWhen Claude Code removed the plugin's entry from `enabledPlugins` and read that scope's settings files back, either the plugin was still switched on there, or a file that could switch it on couldn't be read or checked. Deleting the plugin'… |
|
v2.1.283claude plugin uninstall |
Documentation arrivedAnthropic's documentation has since written up claude plugin uninstall, on Error reference.
the line in the docsYou ran [`claude plugin uninstall`](/docs/en/plugins/cli-reference#plugin-uninstall), or chose **Uninstall** in the `/plugin` **Installed** tab, and the uninstall stopped with a message starting `"<plugin>" was not uninstalled:`. |
|
v2.1.283claude plugin marketplace remove |
Documentation arrivedAnthropic's documentation has since written up claude plugin marketplace remove, on Error reference.
the line in the docs* Run `claude plugin marketplace remove <name>`. This also uninstalls the plugins installed from the marketplace and deletes their saved data |
|
v2.1.277claude plugin marketplace add |
Documentation arrivedAnthropic's documentation has since written up claude plugin marketplace add, on Error reference.
the line in the docsFor an imitating name, the marketplace's own error reads `Claude Code refuses this marketplace's name: it looks like one of Anthropic's own` instead. `claude plugin marketplace add` refuses any impersonating name with `Marketplace name imp… |
|
v2.1.283claude plugin list |
Documentation arrivedAnthropic's documentation has since written up claude plugin list, on Error reference.
the line in the docsIf a marketplace was registered under such a name before the check blocked it, the marketplace and the plugins installed from it stop loading, because Claude Code checks the name every time it reads the marketplace's catalog. When the name… |
|
v2.1.283mcp_tool |
Documentation arrivedA small documentation edit on Automate actions with hooks touched a line naming mcp_tool after this was published.
the line in the docs* `"type": "mcp_tool"`: call a tool on a configured MCP server. See [MCP tool hooks](/docs/en/hooks#mcp-tool-hook-fields). |
|
v2.1.281mcp_tool |
Documentation arrivedA small documentation edit on Automate actions with hooks touched a line naming mcp_tool after this was published.
the line in the docs* `"type": "mcp_tool"`: call a tool on a configured MCP server. See [MCP tool hooks](/docs/en/hooks#mcp-tool-hook-fields). |
|
v2.1.283/hooks |
Documentation arrivedA small documentation edit on Automate actions with hooks touched a line naming /hooks after this was published.
the line in the docs* `"type": "mcp_tool"`: call a tool on a configured MCP server. See [MCP tool hooks](/docs/en/hooks#mcp-tool-hook-fields). |
|
v2.1.283/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Hooks reference.
the line in the docs`SessionStart` at launch, including with `--continue` or `--resume`, and every `Setup` event fire before the session's MCP servers are available to hooks. Claude Code skips their `mcp_tool` hooks without calling the tool, and the [debug lo… |
|
v2.1.283/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Hooks reference.
the line in the docs`SessionStart` at launch, including with `--continue` or `--resume`, and every `Setup` event fire before the session's MCP servers are available to hooks. Claude Code skips their `mcp_tool` hooks without calling the tool, and the [debug lo… |
|
v2.1.283--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Hooks reference.
the line in the docs`SessionStart` at launch, including with `--continue` or `--resume`, and every `Setup` event fire before the session's MCP servers are available to hooks. Claude Code skips their `mcp_tool` hooks without calling the tool, and the [debug lo… |
|
v2.1.283mcp_tool |
Documentation arrivedAnthropic's documentation has since written up mcp_tool, on Hooks reference.
the line in the docs* **[MCP tool hooks](#mcp-tool-hook-fields)** (`type: "mcp_tool"`): call a tool on a configured [MCP server](/docs/en/mcp). The tool's text output is treated like command-hook stdout. |
|
v2.1.283/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Hooks reference.
the line in the docs* **[MCP tool hooks](#mcp-tool-hook-fields)** (`type: "mcp_tool"`): call a tool on a configured [MCP server](/docs/en/mcp). The tool's text output is treated like command-hook stdout. |
|
v2.1.283/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Hooks reference.
the line in the docs* **[MCP tool hooks](#mcp-tool-hook-fields)** (`type: "mcp_tool"`): call a tool on a configured [MCP server](/docs/en/mcp). The tool's text output is treated like command-hook stdout. |
|
v2.1.265BigQuery |
Documentation arrivedA small documentation edit on Network requirements touched a line naming BigQuery after this was published.
the line in the docs<Note>If your Google Cloud project uses VPC Service Controls, an IP-based access level doesn't admit Claude's queries through the [BigQuery connection](/docs/claude-tag/admins/connections/bigquery). See [Allow the connection through a VPC … |
|
v2.1.265BigQuery |
Documentation arrivedAnthropic's documentation has since written up BigQuery, on Connect BigQuery.
the line in the docsIf the Google Cloud project that holds your BigQuery data is inside a [VPC Service Controls](https://cloud.google.com/vpc-service-controls/docs/overview) perimeter, Claude's queries fail with `Request is prohibited by organization's policy… |
|
v2.1.282CLAUDE_CONFIG_DIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CONFIG_DIR, on Error reference.
the line in the docsWindows reported an error (EBADF) when Claude Code read this session's transcript file, although the file had opened normally. This can happen when other software intercepts file reads — security, encryption or endpoint-management tools, f… |
|
v2.1.282/feedback |
Documentation arrivedAnthropic's documentation has since written up /feedback, on Error reference.
the line in the docsYou sent a report from the [`/feedback`, `/bug`, or `/share` dialog](/docs/en/commands#all-commands) and the upload to Anthropic failed. The dialog keeps your text so you can retry. |
|
v2.1.257disableRemoteControl |
Documentation arrivedAnthropic's documentation has since written up disableRemoteControl, on Continue local sessions from any device with Remote Control.
the line in the docs* **The error mentions `disableRemoteControl`**: your IT administrator has disabled Remote Control on this device through [managed settings](/docs/en/managed-settings), independent of the organization-wide toggle and of how you're signed i… |
|
v2.1.257disableRemoteControl |
Documentation arrivedAnthropic's documentation has since written up disableRemoteControl, on Continue local sessions from any device with Remote Control.
the line in the docs* **The error mentions `disableRemoteControl`**: your IT administrator has disabled Remote Control on this device through [managed settings](/docs/en/managed-settings), independent of the organization-wide toggle and of how you're signed i… |
|
v2.1.251disableRemoteControl |
Documentation arrivedAnthropic's documentation has since written up disableRemoteControl, on Continue local sessions from any device with Remote Control.
the line in the docs* **The error mentions `disableRemoteControl`**: your IT administrator has disabled Remote Control on this device through [managed settings](/docs/en/managed-settings), independent of the organization-wide toggle and of how you're signed i… |
|
v2.1.280claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Continue local sessions from any device with Remote Control.
the line in the docsRun `claude auth login` and choose the claude.ai option. If the message names `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN`, remove it wherever it's set: your shell environment or the `env` block of a [settings file](/docs/en/settings-refe… |
|
v2.1.274claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Continue local sessions from any device with Remote Control.
the line in the docsRun `claude auth login` and choose the claude.ai option. If the message names `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN`, remove it wherever it's set: your shell environment or the `env` block of a [settings file](/docs/en/settings-refe… |
|
v2.1.282/focus |
Documentation arrivedAnthropic's documentation has since written up /focus, on Continue local sessions from any device with Remote Control.
the line in the docs* `/focus`, from v2.1.281: pass `on` or `off` as an argument, for example `/focus on`, or run it with no argument to toggle the [focus view](/docs/en/commands#all-commands). Both forms apply to the current session only and leave your saved… |
|
v2.1.281/focus |
Documentation arrivedAnthropic's documentation has since written up /focus, on Continue local sessions from any device with Remote Control.
the line in the docs* `/focus`, from v2.1.281: pass `on` or `off` as an argument, for example `/focus on`, or run it with no argument to toggle the [focus view](/docs/en/commands#all-commands). Both forms apply to the current session only and leave your saved… |
|
v2.1.269/focus |
Documentation arrivedAnthropic's documentation has since written up /focus, on Continue local sessions from any device with Remote Control.
the line in the docs* `/focus`, from v2.1.281: pass `on` or `off` as an argument, for example `/focus on`, or run it with no argument to toggle the [focus view](/docs/en/commands#all-commands). Both forms apply to the current session only and leave your saved… |
|
v2.1.282/recap |
Documentation arrivedAnthropic's documentation has since written up /recap, on Continue local sessions from any device with Remote Control.
the line in the docs* Text-output commands: `/compact`, `/clear`, `/context`, `/usage`, `/exit`, `/usage-credits`, `/recap`, and `/reload-plugins`. `/usage-credits` prints the billing URL instead of opening a browser. `/reload-plugins` works only when the ses… |
|
v2.1.281/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Continue local sessions from any device with Remote Control.
the line in the docs* Text-output commands: `/compact`, `/clear`, `/context`, `/usage`, `/exit`, `/usage-credits`, `/recap`, and `/reload-plugins`. `/usage-credits` prints the billing URL instead of opening a browser. `/reload-plugins` works only when the ses… |
|
v2.1.282/resume |
Documentation arrivedAnthropic's documentation has since written up /resume, on Continue local sessions from any device with Remote Control.
the line in the docs* **Some commands are local-only**: commands that only run in the terminal interface, such as `/plugin` or `/resume`, work only from the local CLI, whether or not you pass an argument. The following work from mobile and web: |
|
v2.1.282/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on Continue local sessions from any device with Remote Control.
the line in the docs* **Effort level**: when you set the [effort level](/docs/en/model-config#adjust-effort-level) from a connected device, with `/effort` or the device's effort control, Claude Code applies it to the session on your machine. If you pinned a l… |
|
v2.1.282autoMode |
Documentation arrivedA small documentation edit on Configure auto mode touched a line naming autoMode after this was published.
the line in the docsSet `autoMode.classifyAllShell` to `true` to suspend every Bash and PowerShell allow rule while auto mode is active, so the classifier evaluates every shell command regardless of your allow list, except [critical-path removals](/docs/en/pe… |