default
A Claude Code settings key, read out of the shipped bundle. No mined inventory carries it: everything below comes from what this site has written about it.
Subagent nudging behaviour can be picked per model, but the whole feature stays behind a gate.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.219.
In the changelogs
65Releases whose published page names default.
-
v2.1.304
--toolshelp now says "default" picks the default set of toolsThe help text for --tools now describes "default" as using the default set of tools rather than all tools
found in this entry's text
-
v2.1.299
/effortand/fastnow work in agent viewIn agent view,
/effortand/fastnow take effect instead of telling you to attach to a sessionfound in this entry's text
-
v2.1.296
--toolshandling for cloud sessions reworkedFor cloud sessions,
--toolsis now sorted into the default set, a refused list or another list, and errors now name the refused toolsfound in this entry's text
-
v2.1.290
Hidden --proactivity option for setting a proactivity level
A --proactivity <level> command-line option now exists and is accepted, but it is hidden from the help text
found in this entry's text
-
v2.1.290
New --proactivity flag sets how much Claude does on its own at startup
A
--proactivityflag picks the proactivity level when Claude Code starts, andCLAUDE_CODE_DISABLE_PROACTIVITYturns the selector offfound in this entry's text
-
v2.1.290
Programs hosting Claude Code can force named MCP tools to ask permission
A host can now list tools that must always ask before running, even ones that would normally allow themselves
found in this entry's text
-
v2.1.290
Claude can be told how much to do on its own: low, medium or high proactivity
A proactivity note in the conversation tells Claude whether to ask first, act normally or act on its own for commits, pushes, pull requests and follow-ups
found in this entry's text
-
v2.1.290
A proactivity level can set the permission mode a session starts in
When a proactivity level other than default is set, Claude Code can choose the starting permission mode from it
found in this entry's text
-
v2.1.290
/code-review mediumnow runs the high-effort recipe on most modelsOn every model without its own
/code-reviewrow, Opus 5.5 included,mediumnow runs the eight-angle high recipe instead of a single pass.high,xhighand Opus 5 are unchanged.found in this entry's text
-
v2.1.288
Code review gains --max-findings to control how many findings are reported
The code review command accepts
--max-findings <n>,allordefault, and remembers your choice for later reviewsfound in this entry's text
-
v2.1.288
Autocompact window setting can differ by model
The autocompact window setting can now take a per-model value with a default, and auto falls back to the built-in value
found in this entry's text
-
v2.1.288
The auto-compact window is now saved separately for each model
Setting the auto-compact window in
/confignow applies to the current model only, not every modelfound in this entry's text
-
v2.1.281
Cloud session: better recovery when a launch or create permission mode is refused
Cloud sessions recover more reliably when the permission mode you asked for is refused, with retries and a notice if they fail
found in this entry's text
-
v2.1.275
Permission-mode 'auto' resolves to a concrete mode at request time
'Auto' permission mode now resolves to a concrete mode when a tool request is made
found in this entry's text
-
v2.1.275
auto-allow-bash-if-sandboxed setting surfaced in diagnostics with its source
Diagnostics now report whether autoAllowBashIfSandboxed is on and where that value came from
found in this entry's text
-
v2.1.271
New remote-control-plane commands: MCP reconnect/toggle, session titling/renaming, task stop/backgrounding, and flag settings
Remote control connections can now reconnect/toggle MCP servers, rename sessions, stop tasks, and set effort/ultracode flags
found in this entry's text
-
v2.1.271
Config schema: string settings can now declare a fixed picker of
optionsConfig settings can now define a fixed list of choices for string-type fields
found in this entry's text
-
v2.1.271
New forPromptShellCommand context forces auto mode down to default
Shell commands run as part of a prompt now force permission mode down from auto to default
found in this entry's text
-
v2.1.260
New "proactive" permission-mode resolution
A new proactive permission mode picks bypass or auto-accept mode based on context.
found in this entry's text
-
v2.1.260
AskUserQuestion telemetry can include extended per-question fields and a title
AskUserQuestion telemetry can now capture extended per-question fields and a title.
found in this entry's text
-
v2.1.259
Additional CLI permission modes surfaced when replaying session state
Replayed sessions now round-trip the default, plan, dontAsk and bubble permission modes, not just the three previously handled.
found in this entry's text
-
v2.1.248
Managed-settings consent can no longer be answered by an in-flight keypress
A keystroke already in flight can no longer accept your organization's managed settings prompt.
found in this entry's text
-
v2.1.248
Managed-settings prompt is handed off from login and ignores leftover keystrokes
The managed-settings prompt after login ignores leftover keystrokes so you can't answer by accident.
found in this entry's text
-
v2.1.247
acceptEdits mode reaches remote clients unchanged
acceptEdits mode now reaches remote clients intact instead of being downgraded to default.
found in this entry's text
-
v2.1.246
New cloud sessions can push the permission mode they launched with
New cloud sessions now tell the cloud which permission mode they started in, falling back if refused.
found in this entry's text
-
v2.1.246
Tool inputs with untyped schemas are parsed instead of arriving as text
MCP and plugin tools with loose input schemas now get real data instead of stringified JSON.
found in this entry's text
-
v2.1.242
Server-side refusal fallbacks documented as supported on Claude Platform on AWS
Server-side refusal fallbacks are now documented as working on Claude Platform on AWS, not just the Claude API.
found in this entry's text
-
v2.1.239
Approving a plan keeps a still-running teammate's permission mode
Approving a plan no longer resets the permission mode of a teammate still running.
found in this entry's text
-
v2.1.239
Tool calls relayed from a cloud agent run under a restricted permission mode
Tool calls relayed from a cloud agent are judged strictly: your hooks skip and relaxed permission modes are downgraded.
found in this entry's text
-
v2.1.236
ANTHROPIC_DEFAULT_MODELsets the model when nothing else doesSet ANTHROPIC_DEFAULT_MODEL and it becomes your model whenever no flag or ANTHROPIC_MODEL applies.
found in this entry's text
-
v2.1.232
Forked subagents are on by default
Forked subagents are on by default in interactive sessions; set
CLAUDE_CODE_FORK_SUBAGENTto false to opt out.found in this entry's text
-
v2.1.232
Fixed policy payloads are validated like managed settings
Malformed admin fallback settings payloads are caught at startup instead of silently doing nothing.
found in this entry's text
-
v2.1.232
Managed settings: policy helpers can carry a static fallback payload
Admins can attach a static
defaultSettingspayload used when a policy helper is missing or fails.named in this entry, found in this entry's text
-
v2.1.232
Policy helper settings are now per-OS with a static fallback
Policy helpers now take per-OS entries plus a static settings payload used when they fail.
named in this entry, found in this entry's text
-
v2.1.232
A /config row for messages from your other sessions
A settings row for handling messages from your other sessions exists but is hidden here.
found in this entry's text
-
v2.1.232
Settings errors that block startup no longer appear in the invalid-settings dialog
Startup-blocking settings errors are now reported as fatal rather than listed with the rest.
found in this entry's text
-
v2.1.232
Managed policy can now ship a fixed settings payload, not just a helper program
Admins can ship managed settings directly in policy, including per-OS defaults, without running a helper program.
found in this entry's text
-
v2.1.232
Groundwork for a proactivity setting
Sessions carry a proactivity level with a cycle keybinding, but the picker cannot be opened.
found in this entry's text
-
v2.1.232
A proactivity level is threaded through sessions but does nothing yet
A proactivityLevel setting is passed around sessions but changes nothing about Claude's behaviour yet.
found in this entry's text
-
v2.1.228
Model selection forwarded on restart-in-place
Your selected model is passed along whenever Claude Code re-executes itself.
found in this entry's text
-
v2.1.219
Subagent steering can be resolved per model
Subagent nudging behaviour can be picked per model, but the whole feature stays behind a gate.
found in this entry's text
-
v2.1.215
Subagent Delegation Steering via
CLAUDE_CODE_THISTLE_GREBEfound in this entry's text
-
v2.1.215
Glob Tool Description Is Now Mode-Aware
found in this entry's text
-
v2.1.215
Plan Mode Post-Approval Teammate Hint Is Steering-Aware
found in this entry's text
-
v2.1.213
/import— Migrate Config from Other AI Coding Agentsfound in this entry's text
-
v2.1.202
bypassPermissionsMode Not Restored from Sessions Unless Explicitly Launchedfound in this entry's text
-
v2.1.200
manualas Alias fordefaultPermission Modefound in this entry's text
-
v2.1.199
Model Catalog: max_output_tokens Limits and advisor_rank
found in this entry's text
-
v2.1.187
preset:defaultinallowed-toolsfound in this entry's text
-
v2.1.182
MCP Per-Server Permission Mode Override (Control Channel)
found in this entry's text
-
v2.1.169
Permission Mode Downgrade Notification
found in this entry's text
-
v2.1.166
fallbackModelsetting in settings.jsonfound in this entry's text
- v2.1.163
-
v2.1.119
Auto-Compact Interactive Configuration (
/autocompact)found in this entry's text
-
v2.1.110
/tuiCommand — Switch Terminal Renderersfound in this entry's text
-
v2.1.97
viewModeConfiguration Settingfound in this entry's text
-
v2.1.92
Keybinding Display System Overhaul
found in this entry's text
-
v2.1.75
Plugin Configurable Options
found in this entry's text
-
v2.1.70
Session Color Reset
found in this entry's text
-
v2.1.70
Remote Mode: Restricted defaultMode Settings
found in this entry's text
-
v2.1.30
SDK Schema Documentation
found in this entry's text
-
v1.0.81
Improved Telemetry
found in this entry's text
-
v1.0.48
New Features
found in this entry's text
-
v1.0.22
Enhanced Permission Modes
found in this entry's text
-
v1.0.18
Enhanced Permission Modes
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
0The miner has never read a build containing this name. It is here because a changelog entry of ours names it, which is evidence that it existed and not evidence of which releases carried it. The inventory starts at v2.1.138 and everything older than that was never mined.
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.