command
A Claude Code settings key, read out of the shipped bundle. It was in the build from v2.1.138 and was gone by v2.1.284.
Your MCP allow and deny rules now match servers whose commands or URLs use environment variables.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.219.
In the changelogs
32Releases whose published page names command.
-
v2.1.299
UserPromptSubmit hooks get more detail about the prompt
Information prepared for
UserPromptSubmithooks now includes the command and whether the prompt is an internal onefound in this entry's text
-
v2.1.295
Denials from permission hooks no longer show the hook's raw command
When a hook denies a permission request, its message is now labelled by hook type instead of showing the command
found in this entry's text
-
v2.1.290
Fixed how shell permission checks read flags after
commandClaude Code now checks each flag after the shell command
commandcorrectly when deciding whether a command such as command -v is safefound in this entry's text
-
v2.1.288
Plugin language servers can use variables in their options and settings
Variables in a plugin language server's initializationOptions and settings are now filled in, and an empty command gets a clear error
found in this entry's text
-
v2.1.288
Shorter explanations when a command cannot be checked before it runs
Permission prompts for
timeout,command -p/-vandjobs -xnow give shorter reasons why the command can't be checked in advancefound in this entry's text
-
v2.1.283
Keybinding help now treats
cmdas its own key, separate frommetaThe keybinding reference now says
metais thealtkey andcmdis a separate modifier most terminals never send, with a 3-second chord timeoutfound in this entry's text
-
v2.1.283
Hook type shown as a separate detail in the hooks list
Entries in the hooks list now show each hook's type as a separate detail instead of a [type] prefix on the label
found in this entry's text
-
v2.1.280
Structured error objects with a code+description now get a dedicated short summary
Error messages with a code and description now show a short, dedicated summary instead of a scanned-out file path or command
found in this entry's text
-
v2.1.280
New gated flag 'tengu_iridescent_pascal' controls skill/tool permission-context resets
New gated flag tengu_iridescent_pascal can skip redundant permission-context resets
found in this entry's text
-
v2.1.275
New coordinator-only Bash guardrail restricting to verified read-only commands
A new guardrail restricts the coordinator role to read-only, verified Bash commands
found in this entry's text
-
v2.1.271
Skill inline shell commands can be handed off to the model instead of auto-run
Inline shell commands in a skill's instructions can now be handed to the model to run explicitly instead of executing silently
found in this entry's text
-
v2.1.271
Local command results now record the underlying command/args
Local command results can now record the exact command and arguments that were run
found in this entry's text
-
v2.1.269
Plugin runtime API gains a 'config' surface alongside agent/fs/store/etc.
Plugin runtime API gains a new 'config' capability alongside turn, tool, agent, fs and others
found in this entry's text
-
v2.1.265
Plugin SDK gains a
commandnamespace: register/run/list slash commandsPlugins can now register, run, and list slash commands through a new
$.commandAPIfound in this entry's text
-
v2.1.265
Bash permission matching now accounts for a leading "cd <cwd> &&" wrapper
Bash permission rules now match commands even when prefixed with "cd <folder> &&"
found in this entry's text
-
v2.1.257
Bash tool permission matcher now includes more deciding fields
Bash remote execution lists which input fields decide whether an existing permission still covers a call.
found in this entry's text
-
v2.1.246
Custom keybinding actions now use a
command:prefix instead ofx-Custom keybindings must now be named command:<name>; old x- names no longer validate.
found in this entry's text
-
v2.1.242
A broader classifier for destructive shell commands
A broader detector for destructive shell commands exists, but nothing visibly uses its verdict.
found in this entry's text
-
v2.1.234
Saved artifact HTML is sanitized and refused if it will not round-trip
Artifact saves get sanitized and refused if the content cannot be published cleanly, in a disabled skill.
found in this entry's text
-
v2.1.229
Tool inputs are filtered before being recorded
Only a few named fields of tool input get recorded in history now, and NUL-containing strings are dropped.
found in this entry's text
-
v2.1.229
Plugins can be installed from a command that prints a directory
Marketplaces can install a plugin by running a command that prints a directory path, with your consent.
named in this entry, found in this entry's text
-
v2.1.229
Plugins can be installed from a command that produces the plugin directory
Marketplaces can declare command plugin sources, and admins can block them with one setting.
found in this entry's text
-
v2.1.227
Cloud sessions can run shell commands on your own machine
A cloud session can run shell commands on your own machine, off unless a server flag enables it.
found in this entry's text
-
v2.1.223
Destructive-command warning reads the tool input
The destructive-command warning now reads the real command, but it stays off unless the feature flag is on.
found in this entry's text
-
v2.1.219
MCP allow/deny rules compare expanded env-var values
Your MCP allow and deny rules now match servers whose commands or URLs use environment variables.
found in this entry's text
-
v2.1.195
Monitor Tool WebSocket Support
found in this entry's text
-
v2.1.139
Hook and Plugin Commands Gain Safer Exec Form
found in this entry's text
-
v2.1.122
Remote Session Bash Command Event
found in this entry's text
-
v2.1.105
Plugin Monitors (Background Watch Scripts)
found in this entry's text
-
v2.1.92
Rerun Command Aliases [In Development]
found in this entry's text
-
v2.1.19
Git Workflow Keybindings
found in this entry's text
-
v1.0.120
Enhanced Bash Command Analysis
found in this entry's text
First cited
0No release's published evidence quotes this name. The ledger indexes the Evidence lines of every changelog on this site, so this says nobody here has ever quoted it; it says nothing about how old the name is.
Presence across releases
2Build by build
149One row per release since the first build this name was read out of. Absent means the build was read and the name was not in it, never mined means no bundle for that release was ever archived, and a declared type or a default is only ever what that release's own bundle stated.
Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the settings key does. All settings keys.