設定の抜けを、
貼るだけで見つける。

Pick which model answers when Claude calls the server-side advisor tool. Unset it to turn the advisor off. The advisor must be at least as capable as your main model. See Choose an advisor model for the accepted pairings and what happens when you pick one that isn't accepted.

型

string, one of the aliases "fable", "opus", or "sonnet", which resolve to Claude Code's current default version of that model family, or a full model ID such as "claude-opus-5-5"

既定値

unset, so the advisor is off

置ける場所

Any file

分類

Model and responses

{
  "advisorModel": "opus"
}

キー名をコピー公式ドキュメント

Turn extended thinking off for every session by setting this to false. Thinking is on by default, so true changes nothing. Most people set this through /config rather than by editing the file.

型

Boolean

既定値

unset, so thinking is on for models that support it

置ける場所

Any file

分類

Model and responses

• true no effect; thinking is already on
• false Claude Code turns extended thinking off for every session

{
  "alwaysThinkingEnabled": false
}

キー名をコピー公式ドキュメント

Restrict which models people can select for the main session, subagents, skills, and the advisor. A managed list constrains /model, --model, and the model key in a developer's own files; a model outside it can't be selected. With the default prefix matching, this doesn't touch the Default option on its own; pair it with enforceAvailableModels for that.

型

array of model aliases or IDs

既定値

unset, so every model is available

置ける場所

Any file

分類

Model and responses

{
  "availableModels": ["sonnet", "haiku"]
}

キー名をコピー公式ドキュメント

Choose how availableModels entries match model IDs. By default a model ID entry also permits later versions that extend it, so "claude-opus-5" permits Opus 5.5. With "exact", each model ID entry permits only the version it names, so a newer version of that model stays blocked until you list it. Requires Claude Code v2.1.283 or later.

型

string, one of:

既定値

"prefix"

置ける場所

Managed

分類

Model and responses

• "prefix" a model ID entry permits its version and any model ID that extends it with another segment
• "exact" a model ID entry permits only the version it names, including that version's dated IDs, so "claude-opus-5" permits Opus 5 but not claude-opus-5-5. A family alias such as "opus" still permits the whole family, and best, opusplan, and default entries are ignored

{
  "availableModels": ["claude-opus-5", "claude-sonnet-5"],
  "availableModelsMatch": "exact"
}

キー名をコピー公式ドキュメント

Block specific models, with or without an availableModels allowlist and even when that list permits them. Claude Code hides a blocked model from the /model picker, and the model can't be selected anywhere availableModels is enforced. A session on the Default option doesn't run a blocked model either, as Block specific models or versions describes. Requires Claude Code v2.1.283 or later.

型

array of model aliases or IDs

既定値

unset, so no model is blocked

置ける場所

Managed

分類

Model and responses

{
  "availableModels": ["opus", "sonnet"],
  "deniedModels": ["claude-opus-5-5"]
}

キー名をコピー公式ドキュメント

Set a default effort level for models you haven't saved a level for. Lower levels are faster and cheaper on straightforward tasks, and higher levels reason more deeply on complex problems.

型

string, one of:

既定値

unset

置ける場所

Any file

分類

Model and responses

• "low" the least reasoning, for short, scoped, latency-sensitive tasks that aren't intelligence-sensitive
• "medium" reduces token usage for cost-sensitive work that can trade off some intelligence
• "high" balances token usage and intelligence
• "xhigh" deeper reasoning at higher token spend

{
  "effortLevel": "xhigh"
}

キー名をコピー公式ドキュメント

The /model picker has a Default option, and default model setting describes the model it resolves to. An availableModels allowlist limits the models you can name, but with the default prefix matching it doesn't remap your account type's default, so Default can still resolve to a model outside the list. This key closes that gap. Requires Claude Code v2.1.175 or later.

型

Boolean

既定値

false

置ける場所

Any file

分類

Model and responses

• true when Default would resolve to a model outside availableModels, Claude Code resolves it to the first available model in the list
• false this key doesn't change how Default resolves

{
  "availableModels": ["sonnet", "haiku"],
  "enforceAvailableModels": true
}

キー名をコピー公式ドキュメント

Name backup models for Claude Code to try, in order, when your primary model is overloaded or unavailable. Claude Code switches to the next available model in the chain for the rest of the turn and shows a notice. Without a chain, Claude Code retries the same model and then surfaces the server's error, and you retry or switch models yourself.

型

array of model aliases or IDs; "default" expands to the default model

既定値

unset, so a failed request isn't retried on another model

置ける場所

Any file

分類

Model and responses

{
  "fallbackModel": ["claude-sonnet-5", "claude-haiku-4-5"]
}

キー名をコピー公式ドキュメント

Turn fast mode on for sessions where it's available, for interactive work like rapid iteration or live debugging where you want speed at a higher cost per token. You don't usually edit this key by hand: running /fast writes fastMode: true to ~/.claude/settings.json, and running it again to turn fast mode off removes the key. Fast mode runs only on Opus 5.5, Opus 5, and Opus 4.8: turning it on from another model switches you to Opus, and switching to an unsupported model turns it off. See Switch models while fast mode is on.

型

Boolean

既定値

unset, so fast mode is off

置ける場所

Any file

分類

Model and responses

• true Claude Code turns fast mode on for sessions where it's available
• false fast mode stays off

{
  "fastMode": true
}

キー名をコピー公式ドキュメント

Normally, running /fast saves fastMode to a person's user settings, so fast mode is on at the start of every later session. Set this key to true to stop that: a saved fastMode: true no longer turns fast mode on at session start, and each person has to run /fast in each session they want it. Claude Code leaves the fastMode key in their file, so turning this key off restores the old behavior.

型

Boolean

既定値

false

置ける場所

Any file

分類

Model and responses

• true a saved fastMode: true no longer turns fast mode on at session start, so each person runs /fast in each session they want it; a fastMode: true passed with --settings still counts for that session unless managed settings set this key
• false a saved fastMode: true turns fast mode on at the start of every later session

{
  "fastModePerSessionOptIn": true
}

キー名をコピー公式ドキュメント

Have Claude respond in a language other than English by default. There is no fixed list for responses: Claude Code passes the value verbatim to Claude as an instruction to always respond in that language, so any language name Claude can read works. Claude Code doesn't check the value, so a misspelled name reaches Claude as written rather than producing an error. The same value sets the language for voice dictation, which does have a fixed list of supported dictation languages, and for auto-generated session titles.

型

string, any language name, such as "japanese", "spanish", or "french"; Claude Code doesn't validate it

既定値

unset; session titles then match the language of your conversation

置ける場所

Any file

分類

Model and responses

{
  "language": "japanese"
}

キー名をコピー公式ドキュメント

Cap the effort level a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from /effort, the /model picker, --effort, CLAUDE_CODE_EFFORT_LEVEL, a skill's or subagent's effort frontmatter, or the model's own default. Claude Code applies the cap itself before each request, so it holds on every provider, including Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. Requires Claude Code v2.1.267 or later.

型

string, one of "low", "medium", "high", "xhigh", or "max". A "max" value sets no cap

既定値

unset, so no cap applies

置ける場所

Any file

分類

Model and responses

{
  "maxEffortLevel": "medium",
  "modelSettings": {
    "claude-sonnet-4-6": {
      "maxEffortLevel": "max"
    }
  }
}

キー名をコピー公式ドキュメント

Set the model every new session uses, so you don't have to pick one with /model each time. Setting it here doesn't stop you from switching mid-session. If your admin set an organization default model to override user selection, you get that model even when you set this key in user, project, or local settings.

型

string, a model alias or full model ID

既定値

unset, so Claude Code uses your account's default model

置ける場所

Any file

分類

Model and responses

{
  "model": "claude-sonnet-5"
}

キー名をコピー公式ドキュメント

Map Anthropic model IDs to provider-specific model IDs, such as Amazon Bedrock inference profile ARNs. Each model picker entry then uses its mapped value when calling the provider API. Administrators use this on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry to route each model version to a specific inference profile, version name, or deployment for governance, cost allocation, or regional routing.

型

object mapping model ID to provider model ID

既定値

unset

置ける場所

Any file

分類

Model and responses

{
  "modelOverrides": {
    "claude-opus-4-6": "arn:aws:bedrock:us-east-1:123456789012:inference-profile/example"
  }
}

キー名をコピー公式ドキュメント

List the models the /model picker offers, in the order you write them and under labels you choose, so the picker lists the models your organization runs, after the built-in lineup or instead of it. Each row's model is taken verbatim, so it accepts anything --model accepts: an alias such as opus, an Anthropic model ID, or a provider-format ID for Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or an LLM gateway. Requires Claude Code v2.1.242 or later.

型

object with an options array of rows and an optional replaceBuiltInOptions Boolean

既定値

unset, so the picker shows the built-in lineup

置ける場所

User or managed

分類

Model and responses

{
  "modelPicker": {
    "options": [
      { "model": "us.anthropic.claude-opus-4-8", "label": "Opus (production)" },
      {
        "model": "us.anthropic.claude-sonnet-4-6",
        "label": "Sonnet (production)",
        "description": "Day-to-day work"
      }
    ]
  }
}

キー名をコピー公式ドキュメント

Report spend at the rates your organization pays instead of list price. Set it when your organization has contracted rates, so the dollar figures developers see match your bill. Claude Code applies the rates in /usage, the status line, the Agent SDK's total_cost_usd, the --max-budget-usd limit, and the OpenTelemetry cost metric and events. You supply the rates: Claude Code doesn't read them from your contract or the Claude Console. Requires Claude Code v2.1.242 or later.

型

object with an optional multiplier and an optional overrides map

既定値

unset, so Claude Code reports list price unless a host application supplies a table

置ける場所

Managed

分類

Model and responses

{
  "modelPricing": {
    "multiplier": 0.85,
    "overrides": {
      "claude-sonnet-4-6": {
        "input": 2.4,
        "output": 12,
        "cacheRead": 0.24,
        "cacheWrite": 3
      }
    }
  }
}

キー名をコピー公式ドキュメント

Save an effort level for each model you use. Requires Claude Code v2.1.251 or later.

型

object mapping a model name to an object with any of these fields:

既定値

unset

置ける場所

Any file

分類

Model and responses

• effortLevel one of "low", "medium", "high", or "xhigh"
• autoCompactWindow a number of tokens from 100000 to 1000000, or "auto" for the window tuned for the model. /autocompact saves here. For that model, the value takes precedence over a top-level autoCompactWindow in the same settings file. Requires Claude Code v2.1.288 or later

{
  "modelSettings": {
    "claude-opus-5-5": {
      "effortLevel": "high"
    }
  }
}

キー名をコピー公式ドキュメント

Select an output style by name. An output style is a saved set of instructions that changes Claude's role, tone, and output format, such as the built-in Explanatory and Learning styles or one you wrote yourself.

型

string, the name of a built-in or custom output style

既定値

unset, so Claude Code uses the default style

置ける場所

Any file

分類

Model and responses

{
  "outputStyle": "Explanatory"
}

キー名をコピー公式ドキュメント

Choose how long the prompt cache holds the main conversation. This key applies to your interactive, -p, and Agent SDK turns, together with the helpers Claude Code runs inline with them. The one-hour lifetime keeps the cache warm across longer breaks, and the API bills each cache write at a higher rate than at the five-minute lifetime. Requires Claude Code v2.1.242 or later.

型

string, one of:

既定値

unset, so each main-conversation request gets its default lifetime

置ける場所

Any file

分類

Model and responses

• "5m" the cache holds for five minutes
• "1h" the cache holds for an hour

{
  "promptCacheTtl": "1h",
  "subagentPromptCacheTtl": "5m"
}

キー名をコピー公式ドキュメント

See summaries of Claude's extended thinking in interactive sessions. Set it if you want the full summaries when you expand thinking with Ctrl+O. When unset or false, the Anthropic API redacts thinking blocks and Claude Code shows a collapsed stub; third-party providers don't redact.

型

Boolean

既定値

false

置ける場所

Any file

分類

Model and responses

• true you see full thinking summaries when you expand thinking with Ctrl+O
• false the Anthropic API redacts thinking blocks and Claude Code shows a collapsed stub

{
  "showThinkingSummaries": true
}

キー名をコピー公式ドキュメント

Choose how long the prompt cache holds the requests Claude Code makes outside the main conversation. This key applies to subagents, workflows, and Claude Code's own background and helper requests, such as compaction and session titles. The one-hour lifetime keeps the cache warm across longer breaks, and the API bills each cache write at a higher rate than at the five-minute lifetime. Requires Claude Code v2.1.242 or later.

型

string, one of:

既定値

unset, so each of these requests gets its default lifetime

置ける場所

Any file

分類

Model and responses

• "5m" the cache holds for five minutes
• "1h" the cache holds for an hour

{
  "subagentPromptCacheTtl": "1h"
}

キー名をコピー公式ドキュメント

Choose what happens when a safety classifier flags a request: switch to the fallback model and continue, or pause so you can choose between switching and editing the prompt.

型

Boolean

既定値

true, switch automatically

置ける場所

Any file

分類

Model and responses

• true Claude Code switches to the fallback model and continues
• false in an interactive session Claude Code pauses so you can choose between switching and editing the prompt; where no dialog can show, such as a -p run, the flagged request ends as an error

{
  "switchModelsOnFlag": false
}

キー名をコピー公式ドキュメント

Start sessions with ultracode on. With it on, Claude plans a workflow for each substantive task instead of waiting for you to ask. Claude plans workflows only when dynamic workflows are enabled for you and your model supports xhigh effort. The key doesn't change the session's effort level: ultracode runs at whichever level the session uses. Claude Code reads this key but never writes it: /effort ultracode turns ultracode on for the current session only.

型

Boolean

既定値

unset, so ultracode is off

置ける場所

Any file

分類

Model and responses

• true sessions start with ultracode on when dynamic workflows are enabled for you and your model supports xhigh
• false sessions start with ultracode off

{
  "ultracode": true
}

キー名をコピー公式ドキュメント

Make managed settings the only settings source of permission rules. Claude Code then ignores allow, ask, and deny rules in user, project, local, and --settings files, ignores --allowedTools, hides the always-allow choices in permission prompts, and stops saving new rules.

型

Boolean

既定値

unset, so Claude Code applies permission rules from user, project, and local settings and from --settings, in addition to the managed ones

置ける場所

Managed

分類

Permission settings

• true managed settings become the only settings source of permission rules
• false Claude Code applies permission rules from user, project, local, and --settings files in addition to the managed ones

{
  "allowManagedPermissionRulesOnly": true
}

キー名をコピー公式ドキュメント

Add your own rules to what the auto mode classifier blocks and allows. Use it to tell the classifier which repos, buckets, and domains your organization trusts, so it stops blocking routine internal operations. The classifier ships with built-in allow and deny rules. Include the literal string "$defaults" in an array to keep those built-in rules at that position and add yours around them; leave it out to replace them with yours.

型

object with environment, allow, soft_deny, and hard_deny arrays of prose rules, plus the classifyAllShell Boolean

既定値

unset, so the classifier uses only its built-in rules

置ける場所

User or managed

分類

Permission settings

{
  "autoMode": {
    "soft_deny": ["$defaults", "Never run terraform apply"]
  }
}

キー名をコピー公式ドキュメント

Send every Bash and PowerShell command through the auto mode classifier while auto mode is active. By default, auto mode suspends only allow rules that could run arbitrary code: tool-wide and wildcard rules such as Bash(*), and interpreter or shell-wrapper prefixes such as Bash(python *). A command that any other allow rule matches, such as Bash(npm test), skips the classifier unless it carries per-command allowed domains. When it skips, a destructive argument the rule's prefix didn't anticipate can get through unseen. Setting this key suspends every shell allow rule for the session so the classifier sees every command. Requires Claude Code v2.1.193 or later.

型

Boolean

既定値

false

置ける場所

User or managed

分類

Permission settings

• true while auto mode is active, Claude Code sends every Bash and PowerShell command through the classifier and suspends your shell allow rules; outside auto mode the rules still apply
• false auto mode suspends only allow rules that could run arbitrary code, such as Bash(*) and Bash(python *); a command that any other allow rule matches skips the classifier unless it carries per-command allowed domains, and every other shell command goes through it

{
  "autoMode": {
    "classifyAllShell": true
  }
}

キー名をコピー公式ドキュメント

Remove auto mode from the Shift+Tab cycle. Any session that would otherwise start in auto mode, whether from --permission-mode auto, a settings file, or the built-in default, starts in default instead. Administrators set it in managed settings to prevent developers in their organization from using auto mode.

型

the string "disable"

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "disableAutoMode": "disable"
}

キー名をコピー公式ドキュメント

Control which tools Claude can use without asking, which ones always prompt, and which ones are blocked, and set the permission mode a session starts in. Every permissions.* key below nests under this object.

型

object with allow, ask, deny, additionalDirectories, blockReadsOutsideWorkingDirectories, defaultMode, disableBypassPermissionsMode, and disableAutoMode

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "permissions": {
    "allow": ["Bash(npm run *)"],
    "ask": ["Bash(git push *)"],
    "deny": ["Read(./.env)"],
    "defaultMode": "acceptEdits"
  }
}

キー名をコピー公式ドキュメント

Choose whether Claude Code uses the auto mode classifier to review shell commands in plan mode. With the default true, the classifier reviews each command during planning when auto mode is available and you see no prompt, except for critical-path removals. Set false to get a permission prompt for every command outside the built-in read-only set. Appears in /config as Use auto mode during plan.

型

Boolean

既定値

true

置ける場所

User, local, or managed

分類

Permission settings

• true the same as unset; when auto mode is available, the classifier reviews each shell command during planning instead of prompting you for it, except critical-path removals. A false in any of these files still turns it off
• false you get a permission prompt for every command outside the built-in read-only set

{
  "useAutoModeDuringPlan": false
}

キー名をコピー公式ドキュメント

List the tool uses Claude Code approves without asking you. In an MCP rule, * can appear only in the tool name after the mcp__<server>__ prefix, such as mcp__github__get_*; it can't appear in the server name.

型

array of permission rule strings

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "permissions": {
    "allow": ["Bash(git diff *)", "Read(~/.zshrc)"]
  }
}

キー名をコピー公式ドキュメント

List the tool uses that prompt you for confirmation even in a permission mode that would otherwise approve them, such as acceptEdits or bypassPermissions. In dontAsk mode Claude Code denies a matching tool use instead of prompting.

型

array of permission rule strings

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "permissions": {
    "ask": ["Bash(git push *)"]
  }
}

キー名をコピー公式ドキュメント

List the tool uses Claude Code blocks. Use it for files that hold API keys, secrets, or environment values: Claude Code excludes matching files from file discovery and search results, denies reads of them, and blocks the Edit and Write tools on the matching paths.

型

array of permission rule strings

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./secrets/**)",
      "Read(./config/credentials.json)",
      "Bash(curl *)"
    ]
  }
}

キー名をコピー公式ドキュメント

Give Claude file access to directories outside the one you started in, as additional working directories. Most .claude/ configuration is not discovered from these directories.

型

array of directory paths

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "permissions": {
    "additionalDirectories": ["../docs/"]
  }
}

キー名をコピー公式ドキュメント

Make Claude's file tools refuse reads outside your working directories in every permission mode, including bypassPermissions. Claude Code denies Read, Grep, Glob, and LSP calls on those paths and tells Claude to ask you to add the directory with /add-dir. Files Claude Code itself needs stay readable, such as your skills, plugins, rules, agents, commands, and the CLAUDE.md memory file under ~/.claude/. Requires Claude Code v2.1.257 or later.

型

Boolean

既定値

unset, so reads outside the working directories follow your permission mode

置ける場所

Any file

分類

Permission settings

• true Claude's file tools refuse reads outside the working directories
• false the same as unset; the block still applies if another file sets true

{
  "permissions": {
    "blockReadsOutsideWorkingDirectories": true
  }
}

キー名をコピー公式ドキュメント

Set the permission mode new sessions start in. When you leave it unset, sessions start in the built-in default for your surface.

型

string, one of:

既定値

unset

置ける場所

Any file

分類

Permission settings

• "default" Claude Code runs only reads without asking
• "acceptEdits" Claude Code also runs file edits and common filesystem commands such as mkdir and mv without asking
• "plan" Claude Code reads and plans but blocks edits until you approve a plan
• "auto" Claude Code runs without routine prompts; before actions such as shell commands and network requests run, a background classifier checks that they align with your request
• "dontAsk" Claude Code auto-denies every call that would otherwise prompt; reads, other actions that need no approval, and pre-approved tools still run
• "bypassPermissions" Claude Code runs everything without asking
• "manual" an alias for "default", in Claude Code v2.1.200 or later

{
  "permissions": {
    "defaultMode": "acceptEdits"
  }
}

キー名をコピー公式ドキュメント

Prevent anyone from entering bypassPermissions mode. Claude Code then rejects the --dangerously-skip-permissions flag, and ignores an agent definition's permissionMode: bypassPermissions, so the subagent runs with the parent session's permission mode.

型

the string "disable"

既定値

unset

置ける場所

Any file

分類

Permission settings

{
  "permissions": {
    "disableBypassPermissionsMode": "disable"
  }
}

キー名をコピー公式ドキュメント

Skip the one-time notice describing auto mode that Claude Code shows when you first enter auto mode yourself, for example through your own settings or the mode selector, rather than when the built-in default starts a session in it. Claude Code shows that notice once and then records that it was shown, so this key only matters where the notice hasn't appeared yet.

型

Boolean

既定値

unset, so the notice appears once

置ける場所

User or managed

分類

Permission settings

• true Claude Code skips the notice
• false the same as unset; the notice appears once unless another of these files sets true

{
  "skipAutoPermissionPrompt": true
}

キー名をコピー公式ドキュメント

Skip the confirmation dialog Claude Code shows before a session enters bypassPermissions mode, whether from --dangerously-skip-permissions or from defaultMode: "bypassPermissions". Claude Code writes true here in your user settings when you accept that dialog once.

型

Boolean

既定値

unset, so the dialog appears

置ける場所

User, local, or managed

分類

Permission settings

• true Claude Code skips the confirmation dialog before a session enters bypassPermissions mode
• false the same as unset; the dialog appears unless another of these files sets true

{
  "skipDangerousModePermissionPrompt": true
}

キー名をコピー公式ドキュメント

Isolate the Bash commands Claude runs from your filesystem and network with sandboxing. Turn the sandbox on with enabled, then narrow or widen what sandboxed commands can touch with the filesystem, network, and credentials sub-objects. The sandbox runs on macOS, Linux, and WSL2.

型

object with enabled, failIfUnavailable, autoAllowBashIfSandboxed, excludedCommands, allowUnsandboxedCommands, enableWeakerNestedSandbox, enableWeakerNetworkIsolation, allowAppleEvents, bwrapPath, socatPath, ignoreViolations, and ripgrep, plus the filesystem, network, and credentials objects

既定値

unset, so Claude Code runs commands without a sandbox

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "enabled": true,
    "autoAllowBashIfSandboxed": true,
    "excludedCommands": ["docker *"],
    "filesystem": {
      "allowWrite": ["/tmp/build", "~/.kube"],
      "denyRead": ["~/.aws/credentials"]
    },
    "network": {
      "allowedDomains": ["github.com", "*.npmjs.org"]
    }
  }
}

キー名をコピー公式ドキュメント

Turn on sandboxing for Bash commands. When you pick a mode in the /sandbox panel, Claude Code writes this key to .claude/settings.local.json for the current project; set it in ~/.claude/settings.json to sandbox every project.

型

Boolean

既定値

false

置ける場所

Any file

分類

Sandbox settings

• true Claude Code sandboxes Bash commands
• false Bash commands run unsandboxed

{
  "sandbox": {
    "enabled": true
  }
}

キー名をコピー公式ドキュメント

Make Claude Code exit with an error at startup when sandbox.enabled is true but the sandbox can't start, because a dependency is missing or the platform is unsupported. Without this key, Claude Code runs commands unsandboxed. Managed deployments that require sandboxing as a security gate can use this setting.

型

Boolean

既定値

false

置ける場所

Any file

分類

Sandbox settings

• true Claude Code exits with an error at startup when sandbox.enabled is true but the sandbox can't start
• false Claude Code runs commands unsandboxed when the sandbox can't start

{
  "sandbox": {
    "enabled": true,
    "failIfUnavailable": true
  }
}

キー名をコピー公式ドキュメント

Let Claude Code run sandboxed Bash commands without a permission prompt. Commands that can't run in the sandbox still go through the regular permission flow, and deny rules and content-scoped ask rules such as Bash(git push *) still apply; a bare Bash ask rule is skipped for sandboxed commands. Set it to false to send sandboxed commands through the regular permission flow too, which the /sandbox Mode tab calls regular permissions mode.

型

Boolean

既定値

true

置ける場所

Any file

分類

Sandbox settings

• true Claude Code runs sandboxed Bash commands without a permission prompt, subject to deny rules and content-scoped ask rules; CLAUDE_CODE_SUBPROCESS_ENV_SCRUB turns auto-allow off
• false sandboxed commands go through the regular permission flow, so your allow rules and permission mode decide. The /sandbox Mode tab calls this regular permissions mode

{
  "sandbox": {
    "enabled": true,
    "autoAllowBashIfSandboxed": false
  }
}

キー名をコピー公式ドキュメント

Name commands that Claude Code runs outside the sandbox, such as tools that don't work under it. Each entry uses the same syntax as the content of a Bash(...) permission rule: an exact command, a prefix such as docker *, or a wildcard pattern. A pattern with no wildcard is an exact match, so docker matches only docker with no arguments.

型

array of command patterns

既定値

unset, so no command is excluded

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "excludedCommands": ["docker *"]
  }
}

キー名をコピー公式ドキュメント

Let Claude retry a command outside the sandbox with the dangerouslyDisableSandbox parameter after the sandbox blocks it. When it's false, Claude Code ignores that parameter. While the sandbox is running, commands Claude runs are then sandboxed unless they match an excludedCommands entry. The /sandbox Overrides tab shows that state as Strict sandbox mode. A false in managed settings turns on strict sandbox mode for the developers it covers.

型

Boolean

既定値

true

置ける場所

Any file

分類

Sandbox settings

• true Claude can retry a command outside the sandbox with the dangerouslyDisableSandbox parameter after the sandbox blocks it
• false Claude Code ignores that parameter, so while the sandbox is running, commands Claude runs are sandboxed unless they match an excludedCommands entry

{
  "sandbox": {
    "enabled": true,
    "allowUnsandboxedCommands": false
  }
}

キー名をコピー公式ドキュメント

Control which paths sandboxed commands can read and write. By default they can write to the working directory, the per-user temp directory, and directories you add with --add-dir, /add-dir, or permissions.additionalDirectories, and can read the rest of the filesystem, including credential files. Widen or narrow that with the four path lists, or switch the filesystem layer off with disabled. See Filesystem isolation for the default boundaries.

型

object with allowWrite, denyWrite, denyRead, and allowRead arrays, plus the allowManagedReadPathsOnly and disabled Booleans

既定値

unset, so the default read and write boundaries apply

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "filesystem": {
      "allowWrite": ["/tmp/build", "~/.kube"],
      "denyRead": ["~/.aws/credentials"]
    }
  }
}

キー名をコピー公式ドキュメント

Add paths where sandboxed commands can write, beyond the working directory, the per-user temp directory, and the directories you've added with --add-dir, /add-dir, or permissions.additionalDirectories. Use it when a subprocess such as kubectl or a build tool needs to write outside the project.

型

array of path strings, using the sandbox path prefixes

既定値

unset, so sandboxed commands can write to the working directory, the per-user temp directory, directories you've added with --add-dir or /add-dir, and directories in permissions.additionalDirectories

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "filesystem": {
      "allowWrite": ["/tmp/build", "~/.kube"]
    }
  }
}

キー名をコピー公式ドキュメント

Block sandboxed commands from writing to specific paths, including paths inside a directory that is otherwise writable.

型

array of path strings, using the sandbox path prefixes

既定値

unset

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "filesystem": {
      "denyWrite": ["/etc", "/usr/local/bin"]
    }
  }
}

キー名をコピー公式ドキュメント

Block sandboxed commands from reading specific paths, such as credential files that the default read policy would otherwise expose. To protect a credential file and keep it usable through the sandbox proxy, see sandbox.credentials instead.

型

array of path strings, using the sandbox path prefixes

既定値

unset, so sandboxed commands keep the default read access, which includes credential files such as ~/.aws/credentials

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "filesystem": {
      "denyRead": ["~/.aws/credentials"]
    }
  }
}

キー名をコピー公式ドキュメント

Re-open reading for specific paths inside a region that denyRead blocks, to build workspace-only read access. An exact or wildcard denyRead entry stays blocked inside a broader allowRead, as the overlap table shows. When a wildcard denyRead entry such as ~/**/.env matches a directory, Claude Code blocks reads of its contents as well. Before v2.1.236 on macOS, Claude Code re-opened the paths a wildcard denyRead entry matched wherever a broader allowRead entry covered them, and left a matched directory's contents readable.

型

array of path strings, using the sandbox path prefixes

既定値

unset

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "filesystem": {
      "denyRead": ["~/"],
      "allowRead": ["."]
    }
  }
}

キー名をコピー公式ドキュメント

Honor only the allowRead entries that come from managed settings, so developers can't re-open read access to paths your organization blocked. Claude Code still merges denyRead entries from every settings scope the session loads.

型

Boolean

既定値

false

置ける場所

Managed

分類

Sandbox settings

• true Claude Code honors only the allowRead entries from managed settings
• false allowRead entries from other settings files can merge in

{
  "sandbox": {
    "filesystem": {
      "denyRead": ["~/"],
      "allowRead": ["~/work"],
      "allowManagedReadPathsOnly": true
    }
  }
}

キー名をコピー公式ドキュメント

Skip filesystem isolation while keeping network isolation. Sandboxed commands get unrestricted read and write access to the host filesystem, and their network egress stays confined to network.allowedDomains. Use it when you sandbox to control where commands connect rather than what they write. Requires Claude Code v2.1.216 or later.

型

Boolean

既定値

false, so filesystem isolation stays on

置ける場所

User or managed

分類

Sandbox settings

• true Claude Code skips filesystem isolation and keeps network isolation
• false filesystem isolation stays on

{
  "sandbox": {
    "enabled": true,
    "filesystem": {
      "disabled": true
    },
    "network": {
      "allowedDomains": ["github.com", "*.npmjs.org"]
    }
  }
}

キー名をコピー公式ドキュメント

Silence sandbox violation reports for paths you expect a command to probe and be refused, such as a tool that checks /etc/hosts on startup, so those denials don't show up as violations or in what Claude sees. The sandbox still blocks the access; only the report is suppressed. Keys are substrings to match against the command, with * matching every command, and values are substrings of the violation to ignore for that command, such as a filesystem path.

型

object mapping a command substring to an array of violation substrings, usually paths

既定値

unset, so every violation is reported

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "ignoreViolations": {
      "*": ["/etc/hosts"]
    }
  }
}

キー名をコピー公式ドキュメント

Run the Linux sandbox inside an unprivileged Docker container, where bubblewrap can't mount a fresh /proc. Instead the inner sandbox bind-mounts the container's existing /proc, which exposes process information that a fresh mount would hide. This reduces security; use it only when the outer container already provides the isolation you need.

型

Boolean

既定値

false

置ける場所

Any file

分類

Sandbox settings

• true the inner sandbox bind-mounts the container's existing /proc instead of mounting a fresh one
• false the sandbox mounts a fresh /proc, which doesn't work in an unprivileged Docker container

{
  "sandbox": {
    "enabled": true,
    "enableWeakerNestedSandbox": true
  }
}

キー名をコピー公式ドキュメント

Let sandboxed commands on macOS reach the system TLS trust service, com.apple.trustd.agent. Go-based tools such as gh, gcloud, and terraform need it to verify TLS certificates when you use network.httpProxyPort with a MITM proxy and a custom CA. This reduces security by opening a potential data exfiltration path through the trust service.

型

Boolean

既定値

false

置ける場所

Any file

分類

Sandbox settings

• true sandboxed commands on macOS can reach com.apple.trustd.agent
• false sandboxed commands on macOS can't reach the system TLS trust service

{
  "sandbox": {
    "enabled": true,
    "enableWeakerNetworkIsolation": true
  }
}

キー名をコピー公式ドキュメント

Let sandboxed commands on macOS send Apple Events, which open, osascript, and tools that open URLs in a browser need; without it they fail with error -600. This removes code-execution isolation: sandboxed commands can launch other applications unsandboxed with no user prompt, and can send AppleScript commands to running applications such as Terminal, subject to the per-app macOS automation-consent prompt (TCC).

型

Boolean

既定値

false

置ける場所

User or managed

分類

Sandbox settings

• true sandboxed commands on macOS can send Apple Events
• false sandboxed commands on macOS can't send Apple Events, so open and osascript fail with error -600

{
  "sandbox": {
    "enabled": true,
    "allowAppleEvents": true
  }
}

キー名をコピー公式ドキュメント

Point the sandbox at a ripgrep binary of your own instead of the one Claude Code uses, for example when your platform needs a differently built rg.

型

object with command, the path to the ripgrep binary, and optional args, an array of arguments to prepend

既定値

unset, so the sandbox uses the same ripgrep binary as Claude Code. That is the bundled binary unless you set USE_BUILTIN_RIPGREP to 0

置ける場所

User or managed

分類

Sandbox settings

{
  "sandbox": {
    "ripgrep": {
      "command": "/usr/local/bin/rg"
    }
  }
}

キー名をコピー公式ドキュメント

Point the sandbox at a bubblewrap binary installed outside PATH, such as a vendored copy on an air-gapped host. Claude Code uses the path both for the startup dependency check and when it wraps each sandboxed command.

型

string, an absolute path; Claude Code drops a relative path and falls back to PATH lookup

既定値

unset, so Claude Code finds bwrap on PATH

置ける場所

Managed

分類

Sandbox settings

{
  "sandbox": {
    "enabled": true,
    "bwrapPath": "/opt/admin/bwrap"
  }
}

キー名をコピー公式ドキュメント

Point the sandbox network proxy at a socat binary installed outside PATH.

型

string, an absolute path; Claude Code drops a relative path and falls back to PATH lookup

既定値

unset, so Claude Code finds socat on PATH

置ける場所

Managed

分類

Sandbox settings

{
  "sandbox": {
    "enabled": true,
    "socatPath": "/opt/admin/socat"
  }
}

キー名をコピー公式ドキュメント

Declare the credential files and environment variables to protect from sandboxed commands. Each entry names a file path or a variable name and a mode: deny hides the credential inside the sandbox, and mask shows sandboxed commands a placeholder while the sandbox proxy substitutes the real value on outbound requests. Claude Code protects only the entries you list; there is no built-in credential deny list.

型

object with files, envVars, allowPlaintextInject, awsPairs, and sigv4

既定値

unset, so no credentials are protected

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "credentials": {
      "files": [{ "path": "~/.aws/credentials", "mode": "deny" }],
      "envVars": [{ "name": "GITHUB_TOKEN", "mode": "deny" }]
    }
  }
}

キー名をコピー公式ドキュメント

Protect credential files or directories from sandboxed commands. With "mode": "deny", Claude Code blocks reads of the path inside the sandbox, the same read block as sandbox.filesystem.denyRead. With "mode": "mask", sandboxed commands on Linux and WSL2 read a sentinel copy of the file, and the sandbox proxy substitutes the real value on outbound requests to that entry's injectHosts; on macOS the file is unreadable inside the sandbox instead. "mode": "mask" requires Claude Code v2.1.221 or later.

型

array of objects, each with path and a mode of "deny" or "mask", plus the optional mask fields for files

既定値

unset, so no credential files are protected

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "credentials": {
      "files": [
        { "path": "~/.aws/credentials", "mode": "deny" },
        { "path": "~/.config/gh/hosts.yml", "mode": "mask", "injectHosts": ["api.github.com"] }
      ]
    }
  }
}

キー名をコピー公式ドキュメント

Protect environment variables from sandboxed commands. With "mode": "deny", Claude Code removes the variable from the environment of sandboxed commands. With "mode": "mask", sandboxed commands see a per-session sentinel value, and the sandbox proxy substitutes the real value on outbound requests to that entry's injectHosts, so tools such as gh and npm keep authenticating without ever holding the real credential.

型

array of objects, each with name and a mode of "deny" or "mask", plus the optional mask fields for environment variables

既定値

unset, so no environment variables are protected

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "credentials": {
      "envVars": [
        { "name": "NPM_TOKEN", "mode": "deny" },
        { "name": "GITHUB_TOKEN", "mode": "mask", "injectHosts": ["api.github.com"] }
      ]
    }
  }
}

キー名をコピー公式ドキュメント

Allow mask substitution on plain HTTP requests as well as TLS-terminated HTTPS. On plain HTTP the upstream identity is unverified and the credential travels in cleartext, so leave this off outside trusted test networks.

型

Boolean

既定値

false

置ける場所

User or managed

分類

Sandbox settings

• true Claude Code allows mask substitution on plain HTTP requests as well as TLS-terminated HTTPS
• false Claude Code allows mask substitution only on TLS-terminated HTTPS

{
  "sandbox": {
    "credentials": {
      "allowPlaintextInject": true
    }
  }
}

キー名をコピー公式ドキュメント

Group masked environment variables that form one AWS credential for SigV4 re-signing when your credential lives in variables with non-standard names. Claude Code links the conventional AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_SESSION_TOKEN trio automatically when you mask their whole values, so you need this key only for other names. Requires Claude Code v2.1.224 or later.

型

array of objects, each with accessKeyIdVar, secretAccessKeyVar, and optionally sessionTokenVar, naming sandbox.credentials.envVars entries

既定値

unset, so only the conventional trio is paired

置ける場所

User or managed

分類

Sandbox settings

{
  "sandbox": {
    "credentials": {
      "awsPairs": [
        {
          "accessKeyIdVar": "MY_KEY_ID",
          "secretAccessKeyVar": "MY_SECRET_KEY",
          "sessionTokenVar": "MY_SESSION_TOKEN"
        }
      ]
    }
  }
}

キー名をコピー公式ドキュメント

Choose what the sandbox proxy does with AWS request forms it can't re-sign: streaming for aws-chunked streaming uploads, presigned for presigned URLs, and sigv4a for SigV4A asymmetric signatures. This applies only to requests signed with a masked pair's placeholder access key ID. Requires Claude Code v2.1.224 or later.

型

object with streaming, presigned, and sigv4a, each one of:

既定値

unset, so every form is "deny"

置ける場所

User or managed

分類

Sandbox settings

• "deny" the proxy fails the request
• "passthrough" the proxy forwards the request signed with the masked placeholder, so the tool receives AWS's own rejection

{
  "sandbox": {
    "credentials": {
      "sigv4": {
        "streaming": "passthrough"
      }
    }
  }
}

キー名をコピー公式ドキュメント

Control which hosts, ports, and sockets sandboxed commands can reach. The sandbox routes outbound traffic through a proxy that enforces these lists; see Network isolation for how the proxy decides and when it prompts.

型

object with the sub-keys below

既定値

unset, so no domains are pre-allowed and your permission mode decides what happens to each new host

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "allowedDomains": ["github.com", "*.npmjs.org"],
      "deniedDomains": ["uploads.github.com"],
      "allowLocalBinding": true
    }
  }
}

キー名をコピー公式ドキュメント

List the Unix socket paths sandboxed commands can connect to on macOS. Claude Code ignores this list on Linux and WSL2, where the seccomp filter can't inspect socket paths; use allowAllUnixSockets there instead.

型

array of strings, each a socket path

既定値

unset, so the macOS sandbox blocks every Unix socket

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "allowUnixSockets": ["~/.ssh/agent-socket"]
    }
  }
}

キー名をコピー公式ドキュメント

Let sandboxed commands connect to every Unix socket. On Linux and WSL2, the sandbox's seccomp filter blocks socket(AF_UNIX, ...) calls, so this is the only way to permit Unix sockets there. When the filter is missing, which /sandbox reports on its Dependencies tab, the sandbox doesn't block Unix-socket calls. See Set up Linux and WSL2 for where the filter comes from.

型

Boolean

既定値

false

置ける場所

Any file

分類

Sandbox settings

• true sandboxed commands can connect to every Unix socket
• false the sandbox blocks Unix-socket connections: on macOS except the paths in allowUnixSockets, and on Linux and WSL2 through the seccomp filter when it's present

{
  "sandbox": {
    "network": {
      "allowAllUnixSockets": true
    }
  }
}

キー名をコピー公式ドキュメント

Let sandboxed commands on macOS listen on network ports, for example to start a dev server, and connect to any port on localhost. A command that listens on a non-loopback address accepts connections from other machines. The key has no effect on Linux and WSL2, where each sandboxed command has its own loopback interface. To reach a server on the host from Linux or WSL2, see A command fails to reach a server on localhost.

型

Boolean

既定値

false

置ける場所

Any file

分類

Sandbox settings

• true sandboxed commands on macOS can listen on any local address and connect to any port on localhost
• false sandboxed commands on macOS can't listen on a port or connect directly to servers on localhost

{
  "sandbox": {
    "network": {
      "allowLocalBinding": true
    }
  }
}

キー名をコピー公式ドキュメント

List additional XPC and Mach service names the macOS sandbox may look up. Tools that communicate over XPC, such as the iOS Simulator or Playwright, need their services listed here.

型

array of strings, each a service name; a single trailing * matches a prefix, and "*" alone matches every service

既定値

unset

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "allowMachLookup": ["com.apple.coresimulator.*"]
    }
  }
}

キー名をコピー公式ドキュメント

Pre-allow domains for outbound traffic from sandboxed commands, so the sandbox doesn't prompt for them. Wildcards such as *.example.com match subdomains, and an optional :port suffix limits an entry to one port; an entry without a port matches every port.

型

array of strings, each a domain, wildcard pattern, or IP literal, with an optional :port suffix

既定値

unset, so your permission mode decides what happens to each new host

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "allowedDomains": ["github.com", "*.npmjs.org", "api.example.com:443"]
    }
  }
}

キー名をコピー公式ドキュメント

Block domains for outbound traffic from sandboxed commands, using the same wildcard, port, and IPv6 syntax as allowedDomains. A denied domain stays blocked even when an allowedDomains entry matches it too.

型

array of strings, each a domain, wildcard pattern, or IP literal, with an optional :port suffix

既定値

unset

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "deniedDomains": ["sensitive.cloud.example.com"]
    }
  }
}

キー名をコピー公式ドキュメント

Deny sandboxed commands access to hosts outside the allowlist instead of prompting for approval. The allowlist is allowedDomains plus domains from WebFetch(domain:...) allow rules, or only the managed settings entries when allowManagedDomainsOnly is set. Locks that apply without an admin-required sandbox covers a repository's entries. Requires Claude Code v2.1.219 or later.

型

Boolean

既定値

false

置ける場所

User or managed

分類

Sandbox settings

• true Claude Code denies sandboxed commands access to hosts outside the allowlist
• false unless another trusted settings file sets true, Claude Code decides a host outside the allowlist by permission mode instead of denying it outright: in auto mode it checks the host against the command's per-command allowed domains, in dontAsk mode it denies, in bypassPermissions mode and in interactive terminal plan-mode sessions where bypass is available it allows, and otherwise it asks you

{
  "sandbox": {
    "network": {
      "strictAllowlist": true
    }
  }
}

キー名をコピー公式ドキュメント

Lock the network allowlist to what managed settings define. Claude Code then honors only allowedDomains and WebFetch(domain:...) allow rules from managed settings, ignores domains from user, project, local, and --settings settings, and blocks a non-allowed domain automatically instead of prompting.

型

Boolean

既定値

false

置ける場所

Managed

分類

Sandbox settings

• true Claude Code honors only allowedDomains and WebFetch(domain:...) allow rules from managed settings and blocks a non-allowed domain instead of prompting
• false domains from other settings files can merge into the allowlist

{
  "sandbox": {
    "network": {
      "allowManagedDomainsOnly": true,
      "allowedDomains": ["github.com", "*.npmjs.org"]
    }
  }
}

キー名をコピー公式ドキュメント

Point the sandbox at your own HTTP proxy instead of the one Claude Code runs. Organizations do this to inspect HTTPS traffic, apply their own filtering rules, or log requests. Your proxy takes over filtering, and Claude Code stops applying its domain lists and network prompts to traffic sent there. When unset, Claude Code starts its own proxy for HTTP traffic.

型

number, a local TCP port

既定値

unset, so Claude Code runs its own proxy

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "httpProxyPort": 8080
    }
  }
}

キー名をコピー公式ドキュメント

Point the sandbox at your own SOCKS5 proxy instead of the one Claude Code runs. Your proxy takes over filtering, and Claude Code stops applying its domain lists and network prompts to traffic sent there. When unset, Claude Code starts its own proxy for SOCKS traffic.

型

number, a local TCP port

既定値

unset, so Claude Code runs its own proxy

置ける場所

Any file

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "socksProxyPort": 8081
    }
  }
}

キー名をコピー公式ドキュメント

Make the sandbox proxy terminate TLS so it can read the contents of HTTPS requests. This is experimental, and mask credential substitution requires it. Set {} to generate an ephemeral certificate authority for the session, or set caCertPath and caKeyPath to use your own.

型

object with optional caCertPath and caKeyPath strings, each a file path

既定値

unset, so the proxy doesn't terminate or inspect TLS

置ける場所

User or managed

分類

Sandbox settings

{
  "sandbox": {
    "network": {
      "tlsTerminate": {}
    }
  }
}

キー名をコピー公式ドキュメント

Have Claude Code compact the conversation automatically when context approaches the limit. Appears in /config as Auto-compact, and toggling it there writes this key to your user settings.

型

Boolean

既定値

true

置ける場所

Any file

分類

Memory and context

• true Claude Code compacts the conversation automatically when context approaches the limit
• false Claude Code doesn't compact automatically

{
  "autoCompactEnabled": false
}

キー名をコピー公式ドキュメント

Set how full the context window gets before Claude Code compacts automatically.

型

number of tokens, from 100000 to 1000000. Claude Code caps the value at your model's context window; the models overview lists each model's window

既定値

unset, so Claude Code picks a window tuned for your model

置ける場所

Any file

分類

Memory and context

{
  "autoCompactWindow": 500000
}

キー名をコピー公式ドキュメント

Store auto memory in a directory of your choice instead of the per-project default.

型

string, an absolute or ~/-prefixed directory path

既定値

unset, so Claude Code uses ~/.claude/projects/<project>/memory/

置ける場所

Any file

分類

Memory and context

{
  "autoMemoryDirectory": "~/my-memory-dir"
}

キー名をコピー公式ドキュメント

Turn auto memory on or off. When false, Claude doesn't read from or write to the auto memory directory. You can also toggle it with /memory during a session, which writes this key to your user settings.

型

Boolean

既定値

true

置ける場所

Any file

分類

Memory and context

• true the same as unset; auto memory stays on unless something that outranks this key turns it off for the session, such as --bare, safe mode, or CLAUDE_CODE_DISABLE_AUTO_MEMORY
• false Claude doesn't read from or write to the auto memory directory

{
  "autoMemoryEnabled": false
}

キー名をコピー公式ドキュメント

Set how many characters of a successful Bash or PowerShell command's output Claude receives inline. When output passes the limit, Claude Code saves it to a file and Claude receives a short preview plus the file's path. Raise the limit when command output, such as a verbose build or a full test-suite log, routinely overflows the default and you want Claude to read it without opening the file. Requires Claude Code v2.1.261 or later.

型

number of characters, a positive integer. Claude Code clamps the value into the range 4000 to 128000

既定値

unset, so Claude receives up to 30,000 characters inline

置ける場所

Any file

分類

Memory and context

{
  "bashOutputMaxChars": 100000
}

キー名をコピー公式ドキュメント

Inject CLAUDE.md-style instructions as organization-managed memory without deploying a separate file. Claude Code loads the text as a managed memory entry ahead of user and project CLAUDE.md files.

型

string, the text of a CLAUDE.md file; write it as you would the file, Markdown included, with line breaks as \n

既定値

unset

置ける場所

Managed

分類

Memory and context

{
  "claudeMd": "# Engineering rules\n\n- Always run make lint before committing.\n- Never push directly to main."
}

キー名をコピー公式ドキュメント

Skip specific CLAUDE.md files when Claude Code loads memory. In a large monorepo, use it to skip CLAUDE.md files from other teams that aren't relevant to your work; Exclude irrelevant CLAUDE.md files in the large-codebases guide walks through that case. Patterns match against absolute file paths.

型

array of strings, each a glob pattern or absolute path

既定値

unset, so Claude Code loads every CLAUDE.md it finds

置ける場所

Any file

分類

Memory and context

{
  "claudeMdExcludes": ["**/vendor/**/CLAUDE.md"]
}

キー名をコピー公式ドキュメント

Set environment variables for every session and for the subprocesses Claude Code starts from it. Most variables in the environment variables reference can go here, which is how you apply one to every session or roll it out to your team. Project and local settings can't set some of them.

型

object mapping variable names to string values

既定値

unset

置ける場所

Any file

分類

Memory and context

{
  "env": {
    "DISABLE_AUTO_COMPACT": "1",
    "ANTHROPIC_BASE_URL": "https://proxy.example.com"
  }
}

キー名をコピー公式ドキュメント

Have Claude Code snapshot files before each edit so /rewind can restore them. Appears in /config as Rewind code (checkpoints), and toggling it there writes this key to your user settings.

型

Boolean

既定値

true

置ける場所

Any file

分類

Memory and context

• true Claude Code snapshots files before each edit so /rewind can restore them
• false Claude Code doesn't snapshot files, so /rewind can't restore them

{
  "fileCheckpointingEnabled": false
}

キー名をコピー公式ドキュメント

Choose where Claude Code stores the plan files it writes in plan mode. Claude Code resolves the path relative to the project root and keeps the default when the path resolves outside it.

型

string, a path relative to the project root

既定値

unset, so Claude Code uses ~/.claude/plans

置ける場所

Any file

分類

Memory and context

{
  "plansDirectory": "./plans"
}

キー名をコピー公式ドキュメント

Each turn, Claude sees a listing of your skills with their descriptions, and Claude Code caps that listing at a share of the context window. When the listing is over the cap, Claude Code keeps every skill's name but drops the descriptions of the least-used skills, so Claude can still invoke those skills but is less likely to choose one on its own. Raise this key to keep more descriptions visible at the cost of more context per turn.

型

number, a fraction greater than 0 and at most 1

既定値

0.01, which reserves 1% of the context window

置ける場所

Any file

分類

Memory and context

{
  "skillListingBudgetFraction": 0.02
}

キー名をコピー公式ドキュメント

Each turn, Claude sees a listing of your skills that shows each skill's description and when_to_use text. This key caps how many characters of that text Claude Code shows per skill; longer text is cut at the cap.

型

number of characters, a positive integer

既定値

1536

置ける場所

Any file

分類

Memory and context

{
  "skillListingMaxDescChars": 2048
}

キー名をコピー公式ドキュメント

Through v2.1.276, you set this key to the number of characters of a background task's output that Claude received inline when it read the task with the TaskOutput tool.

置ける場所

Any file

分類

Memory and context

キー名をコピー公式ドキュメント

Let an unanswered AskUserQuestion dialog auto-continue after a period of idle time, submitting whatever options you had already selected. Set it when you step away and want Claude to continue without you. With the default, questions wait until you answer them. For when the timer pauses or never starts, see Question auto-continue timeout. Requires Claude Code v2.1.200 or later.

型

string, one of "60s", "5m", "10m", or "never"

既定値

"never"

置ける場所

User or managed

分類

Interface and terminal

{
  "askUserQuestionTimeout": "5m"
}

キー名をコピー公式ドキュメント

After a claude.ai usage limit stops your session, wait in the open session and continue the task automatically after the reset. See Turn automatic continue off. Requires Claude Code v2.1.234 or later.

型

Boolean

既定値

true

置ける場所

User or managed

分類

Interface and terminal

• true after a claude.ai usage limit stops your session, Claude Code waits in the open session and continues the task automatically after the reset
• false Claude Code doesn't start the wait on its own. You can still start a wait yourself from the usage-limit options menu

{
  "autoContinueAtUsageLimit": false
}

キー名をコピー公式ドキュメント

Follow new output to the bottom of the conversation in fullscreen rendering. Turn it off to stay where you scrolled while Claude keeps working; permission prompts still scroll into view.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true the conversation follows new output to the bottom
• false you stay where you scrolled while Claude keeps working; permission prompts still appear below the transcript

{
  "autoScrollEnabled": false
}

キー名をコピー公式ドキュメント

Render screen-reader friendly output: flat text without decorative borders or animations. Screen-reader mode uses the classic renderer, so the tui setting has no effect while it is active; attached background sessions still render fullscreen.

型

Boolean

既定値

unset, so screen-reader mode is off

置ける場所

Any file

分類

Interface and terminal

• true Claude Code renders flat text without decorative borders or animations, using the classic renderer
• false Claude Code renders normally

{
  "axScreenReader": true
}

キー名をコピー公式ドキュメント

Choose whether Claude Code records which files changed in a Git repository while a Bash command runs. When it records them, you see their diff in the terminal after the command, and your PostToolUse Bash hooks receive the changed-file list.

型

Boolean

既定値

unset, so Claude Code records changes in auto mode and bypassPermissions mode when it directs Claude to edit files through Bash

置ける場所

User or managed

分類

Interface and terminal

{
  "bashEditDiffEnabled": true
}

キー名をコピー公式ドキュメント

Show your organization's announcements to users at startup. When you list more than one, Claude Code picks one at random for each session; on a person's very first launch it shows the first entry.

型

array of strings

既定値

unset, so no announcement shows

置ける場所

Any file

分類

Interface and terminal

{
  "companyAnnouncements": [
    "Welcome to Acme Corp! Review our code guidelines at docs.example.com"
  ]
}

キー名をコピー公式ドキュメント

Choose whether Bash or PowerShell runs the shell commands you type with the ! prefix in the input box, the ones Claude Code runs directly and adds to the session.

型

string, one of:

既定値

"bash", or "powershell" on Windows when Bash isn't available

置ける場所

Any file

分類

Interface and terminal

• "bash" Claude Code runs your ! commands in Bash
• "powershell" Claude Code runs your ! commands in PowerShell

{
  "defaultShell": "powershell"
}

キー名をコピー公式ドキュメント

Set the deadline for dialogs Claude Code forwards to a remote client, such as a Remote Control or SDK host, and for the approval dialog for a held cross-session message. On Claude Code v2.1.236 or later, the same deadline bounds the mid-session Fable usage-credits consent prompt in a session that may have nobody at the terminal. When no answer arrives before the deadline, Claude Code cancels the dialog and continues with its no-action default. Requires Claude Code v2.1.224 or later.

型

string, one of "60s", "5m", "10m", or "never", which disables the deadline

既定値

"5m"

置ける場所

User or managed

分類

Interface and terminal

{
  "dialogExpiry": "10m"
}

キー名をコピー公式ドキュメント

Choose the key binding mode for the input prompt.

型

string, one of:

既定値

"normal"

置ける場所

Any file

分類

Interface and terminal

• "normal" standard key bindings in the prompt input
• "vim" vim-style editing with NORMAL, INSERT, and VISUAL modes

{
  "editorMode": "vim"
}

キー名をコピー公式ドキュメント

Show emoji suggestions when you type : plus a shortcode in the prompt input, and replace a completed shortcode such as :heart: with its emoji. Set it to false to turn off both.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true Claude Code shows emoji suggestions after : and replaces a completed shortcode with its emoji
• false Claude Code neither suggests emoji nor replaces shortcodes

{
  "emojiCompletionEnabled": false
}

キー名をコピー公式ドキュメント

Run your own command to supply @ file path autocomplete instead of the built-in file suggestion. The built-in suggestion uses fast filesystem traversal; a large monorepo may do better with project-specific indexing such as a pre-built file index.

型

object with type, always "command", and command, the shell command to run

既定値

unset, so Claude Code uses the built-in file suggestion

置ける場所

Any file

分類

Interface and terminal

{
  "fileSuggestion": {
    "type": "command",
    "command": "~/.claude/file-suggestion.sh"
  }
}

キー名をコピー公式ドキュメント

Render extra clickable badges in the footer below the input box when a regex matches turn output: tool results, including file contents and fetched pages, and Claude's own responses. Use it to turn IDs printed by project CLIs, such as review tools and issue trackers, into session links.

型

array of objects, each with type set to "regex", a pattern regex, a url template, and an optional label; {name} placeholders in url and label are filled from named capture groups in pattern

既定値

unset, so no badges render

置ける場所

User or managed

分類

Interface and terminal

{
  "footerLinksRegexes": [
    {
      "type": "regex",
      "pattern": "\\b(?<key>PROJ-\\d+)\\b",
      "url": "https://issues.example.com/browse/{key}",
      "label": "{key}"
    }
  ]
}

キー名をコピー公式ドキュメント

In v2.1.238 through v2.1.260, setting it to "readline" made Ctrl+W delete back to the previous whitespace instead of only the previous word.

型

string, "classic" or "readline"

既定値

unset

置ける場所

Any file

分類

Interface and terminal

キー名をコピー公式ドキュメント

Cap the width of the prose in Claude's responses so lines stay readable in a wide terminal. Paragraphs, headings, lists, and blockquotes wrap within this many columns, while tables and code blocks keep the full terminal width. Requires Claude Code v2.1.282 or later.

型

number of terminal columns, a whole number, minimum 40. Claude Code ignores any other value

既定値

unset, so prose wraps at the terminal edge

置ける場所

Any file

分類

Interface and terminal

{
  "maxProseWidth": 80
}

キー名をコピー公式ドキュメント

Reduce or turn off interface animations such as the spinner, shimmer, and flash effects. Appears in /config as Reduce motion.

型

Boolean

既定値

false

置ける場所

Any file

分類

Interface and terminal

• true Claude Code reduces or turns off interface animations such as the spinner, shimmer, and flash effects
• false the same as unset; Claude Code shows its animations

{
  "prefersReducedMotion": true
}

キー名をコピー公式ドキュメント

Show or hide prompt suggestions, the grayed-out predictions that appear in your prompt input. Set it to false, or turn off Prompt suggestions in /config, to hide them.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true you see prompt suggestions in your prompt input
• false Claude Code hides prompt suggestions

{
  "promptSuggestionEnabled": false
}

キー名をコピー公式ドキュメント

Control whether the @ file picker leaves out files that match .gitignore patterns. Appears in /config as Respect .gitignore in file picker.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true the @ file picker leaves out files that match .gitignore patterns
• false the @ file picker includes files that match .gitignore patterns

{
  "respectGitignore": false
}

キー名をコピー公式ドキュメント

Choose whether Claude responds after you run a shell command with the ! prefix in the input box. By default, Claude Code adds the command's output to the conversation and Claude replies to it. Set this key to false to add the output to context without a reply, so you can run several commands and ask about them together.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true Claude Code adds the command's output to the conversation and Claude replies to it
• false Claude Code adds the output to context without a reply

{
  "respondToBashCommands": false
}

キー名をコピー公式ドキュメント

When Claude finishes a plan in plan mode, it shows an approval menu. Planning can use a lot of context, so this key adds a first option to that menu, Yes, clear context and …, that approves the plan, clears the conversation context, and starts implementing from the plan alone. The rest of the label names the permission mode the session continues in, and shows how much of your context the planning used.

型

Boolean

既定値

false

置ける場所

Any file

分類

Interface and terminal

• true the plan approval menu gets a first option, Yes, clear context and …, that approves the plan and clears the conversation context
• false the plan approval menu shows no clear-context option

{
  "showClearContextOnPlanAccept": true
}

キー名をコピー公式ドキュメント

Show or hide the turn duration message after each response, such as "Cooked for 1m 6s · done 6:05 PM". The clock after "done" shows when the turn finished; timeFormat and timeZone control its format and zone. Appears in /config as Show turn duration.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true you see the turn duration message after each response
• false Claude Code hides the turn duration message

{
  "showTurnDuration": false
}

キー名をコピー公式ドキュメント

Underline misspelled words in the prompt input as you type, using a spell checker you install. Claude Code checks only the text in the input box. Check spelling as you type covers installing aspell, hunspell, or ispell and what the checker covers. Requires Claude Code v2.1.235 or later.

型

object with enabled (Boolean), checker ("aspell", "hunspell", "ispell", or "auto"), language (string, passed to the checker as its dictionary name), and color (string, a terminal color name, #rrggbb, rgb(r,g,b), ansi256(n), or ansi:<name>)

既定値

unset, so spell checking is off; checker defaults to "auto", the first of the three found on PATH; language defaults to the checker's own dictionary; color defaults to the theme's error color

置ける場所

User or managed

分類

Interface and terminal

{
  "spellcheck": { "enabled": true, "language": "en_GB" }
}

キー名をコピー公式ドキュメント

While Claude works, the spinner line rotates through short tips about Claude Code features, such as "Use Plan Mode to prepare for a complex request before making changes. Press Shift+Tab twice to enable." Set this key to false to hide them. Appears in /config as Show tips.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true you see tips in the spinner while Claude is working
• false Claude Code hides spinner tips

{
  "spinnerTipsEnabled": false
}

キー名をコピー公式ドキュメント

Add your own tips to the spinner tips that Claude Code shows while Claude works, or replace the built-in tips with yours. Claude Code puts your tips in the same rotation as the built-in ones.

型

object with tips, tipsFile, label, and excludeDefault fields, each optional

既定値

unset, so Claude Code shows only the built-in tips

置ける場所

Any file

分類

Interface and terminal

{
  "spinnerTipsOverride": {
    "label": "Acme tip",
    "tips": [
      "Run /review before opening a PR",
      {
        "id": "gateway-errors",
        "text": "Seeing 5xx errors? Check the gateway status page first",
        "cooldownSessions": 5,
        "priority": 2
      }
    ]
  }
}

キー名をコピー公式ドキュメント

While a turn is in progress, the spinner shows a rotating verb such as "Accomplishing", "Architecting", or "Baking". Use this key to add your own verbs to that rotation or replace the built-in list with yours.

型

object with a verbs array of strings and mode, one of:

既定値

unset, so Claude Code uses the built-in verbs

置ける場所

Any file

分類

Interface and terminal

• "append" Claude Code adds your verbs to the built-in set
• "replace" Claude Code shows only your verbs

{
  "spinnerVerbs": {
    "mode": "append",
    "verbs": ["Pondering", "Crafting"]
  }
}

キー名をコピー公式ドキュメント

Run your own command to render a status line below the prompt with context such as the model, cost, or git branch. Optional fields adjust spacing, add periodic re-runs, and hide the built-in vim mode indicator when your script renders vim.mode itself.

型

object with type set to "command" and a command string, plus optional padding as a number of characters, refreshInterval as a number of seconds, minimum 1, and hideVimModeIndicator as a Boolean

既定値

unset, so no status line

置ける場所

Any file

分類

Interface and terminal

{
  "statusLine": {
    "type": "command",
    "command": "jq -r '\"[\\(.model.display_name)] \\(.context_window.used_percentage // 0)% context\"'",
    "padding": 2
  }
}

キー名をコピー公式ドキュメント

When Claude runs subagents, Claude Code lists them in a task display below the prompt, one row per subagent showing name · description · token count. This key lets you run your own command to rewrite those rows, for example to show each subagent's context usage as a percentage. On each refresh, Claude Code sends the visible rows as one JSON object on stdin, with a tasks array carrying each subagent's id, name, status, model, tokenCount, and more, and replaces the row for each id you write back as a {"id", "content"} line. Rows you don't write back keep the default rendering.

型

object with type set to "command" and a command string

既定値

unset, so Claude Code renders the default rows

置ける場所

Any file

分類

Interface and terminal

{
  "subagentStatusLine": {
    "type": "command",
    "command": "jq -c '.tasks[] | {id, content: \"\\(.name): \\(.tokenCount) tokens\"}'"
  }
}

キー名をコピー公式ドキュメント

Claude Code colors code by language in the diffs, code blocks, and file previews it shows in the terminal, with its built-in highlighter; no plugin or language server is involved. Set this key to true to show them as plain text instead, for example if the colors clash with your terminal theme or slow a screen reader.

型

Boolean

既定値

false

置ける場所

Any file

分類

Interface and terminal

• true Claude Code turns off syntax highlighting in diffs, code blocks, and file previews
• false Claude Code highlights syntax

{
  "syntaxHighlightingDisabled": true
}

キー名をコピー公式ドキュメント

Some terminals can show a progress indicator on the tab or in the taskbar for the program running in them. While Claude is working, Claude Code reports an in-progress state to the terminal, so you can see from another tab or window whether the session is still busy. The indicator stays visible after the turn ends while background subagents or dynamic workflows are still running, and clears once the session is idle.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true you see the terminal progress bar in terminals that support it
• false Claude Code hides the terminal progress bar

{
  "terminalProgressBarEnabled": false
}

キー名をコピー公式ドキュメント

Claude Code sets your terminal tab's title. By default it uses a title it generates from the conversation, and once you give the session a name with /rename or --name, the tab shows that name instead. Set this key to false to keep the generated title on the tab even after you name the session. The name itself still applies, so /resume <name> and the session picker find it.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true the terminal tab title shows the session name you set
• false the tab keeps the title Claude Code generates from your conversation

{
  "terminalTitleFromRename": false
}

キー名をコピー公式ドキュメント

Pick the color theme for the interface. Appears in /config as Theme.

型

string, one of:

既定値

"dark"

置ける場所

Any file

分類

Interface and terminal

• "auto" matches your terminal's light or dark background
• "dark" the dark theme
• "light" the light theme
• "dark-daltonized" the dark theme with colorblind-friendly colors
• "light-daltonized" the light theme with colorblind-friendly colors
• "dark-ansi" the dark theme using only your terminal's ANSI color palette
• "light-ansi" the light theme using only your terminal's ANSI color palette

{
  "theme": "light-daltonized"
}

キー名をコピー公式ドキュメント

Choose how Claude Code writes the times it shows in the interface, such as the done 6:05 PM at the end of each turn duration message and the timestamps in the transcript viewer. To pick a preset, run /config and set Time format. Requires Claude Code v2.1.257 or later.

型

string, one of:

既定値

"auto"

置ける場所

Any file

分類

Interface and terminal

• "auto" the same as unset; each time keeps its built-in format, which follows your locale on the turn duration message
• "12-hour" a 12-hour clock
• "24-hour" a 24-hour clock
• "24-hour-utc" a 24-hour clock in UTC with Z after the minutes, such as 18:05Z; Claude Code ignores timeZone for this preset

{
  "timeFormat": "24-hour"
}

キー名をコピー公式ドキュメント

Show the times in the interface in a time zone other than your system's. Set it to an IANA time zone name, such as "UTC" or "Europe/Dublin". The times that timeFormat controls then show in this zone. If timeFormat is "24-hour-utc", times stay in UTC and Claude Code ignores this key. /config has no row for this key, so set it in a settings file. Requires Claude Code v2.1.257 or later.

型

string, an IANA time zone name. When Claude Code doesn't recognize the name, it uses your system time zone

既定値

unset, so times show in your system time zone

置ける場所

Any file

分類

Interface and terminal

{
  "timeZone": "Europe/Dublin"
}

キー名をコピー公式ドキュメント

Choose the terminal UI renderer. Use "fullscreen" for the flicker-free alt-screen renderer with virtualized scrollback, or "default" for the classic main-screen renderer. Running /tui fullscreen or /tui default writes this key for you.

型

string, one of:

既定値

unset, so Claude Code picks the renderer for you

置ける場所

Any file

分類

Interface and terminal

• "default" the classic main-screen renderer
• "fullscreen" the flicker-free alt-screen renderer with virtualized scrollback

{
  "tui": "fullscreen"
}

キー名をコピー公式ドキュメント

By default, the transcript collapses each tool call to a short summary, such as the command Claude ran and a line count of its output, and you press Ctrl+O to switch the whole transcript to the expanded view when you want the details. Set this key to true to show every tool call's full input and output inline as it happens, which is useful when you're debugging a hook, an MCP server, or a long shell command. Appears in /config as Verbose output.

型

Boolean

既定値

false

置ける場所

Any file

分類

Interface and terminal

• true you see full tool output
• false you see truncated summaries of tool output

{
  "verbose": true
}

キー名をコピー公式ドキュメント

Set the transcript view Claude Code starts in: "default", "verbose", or "focus". When set, it overrides both the sticky /focus selection and the verbose setting.

型

string, one of:

既定値

unset, so the verbose setting and your last /focus choice apply

置ける場所

Any file

分類

Interface and terminal

• "default" the normal transcript with truncated tool output
• "verbose" the transcript with full tool output
• "focus" only your last prompt, a one-line summary of tool calls with edit diffstats, and the final response. Focus view needs the fullscreen renderer

{
  "viewMode": "focus"
}

キー名をコピー公式ドキュメント

Map two-key INSERT-mode sequences to Escape in vim editor mode. Each key is exactly two printable characters typed in sequence, and "<Esc>" is the only supported target; Claude Code ignores other entries. Requires Claude Code v2.1.208 or later.

型

object mapping a two-character sequence to "<Esc>"

既定値

unset

置ける場所

User or managed

分類

Interface and terminal

{
  "vimInsertModeRemaps": {
    "jj": "<Esc>"
  }
}

キー名をコピー公式ドキュメント

Turn on voice dictation and choose how the dictation key behaves. Claude Code writes this object for you when you run /voice.

型

object with enabled as a Boolean, autoSubmit as a Boolean that applies in hold mode only, and mode, one of:

既定値

unset, so dictation is off; when enabled is true and mode is unset, Claude Code uses "hold"

置ける場所

Any file

分類

Interface and terminal

• "hold" you hold the dictation key while speaking and release it to stop
• "tap" you tap the key once to start recording and again to send

{
  "voice": {
    "enabled": true,
    "mode": "tap"
  }
}

キー名をコピー公式ドキュメント

Turn voice dictation on with the single Boolean form that predates the voice object. When both are set, voice.enabled applies.

型

Boolean

既定値

unset

置ける場所

Any file

分類

Interface and terminal

• true voice dictation is on when you're logged in with a claude.ai account and your organization's policy allows voice, unless voice.enabled is set
• false voice dictation is off, unless voice.enabled is set

{
  "voiceEnabled": true
}

キー名をコピー公式ドキュメント

Accelerate mouse-wheel scroll speed during fast scrolls in fullscreen rendering. Set it to false for a constant scroll rate per wheel notch.

型

Boolean

既定値

true

置ける場所

Any file

分類

Interface and terminal

• true Claude Code accelerates mouse-wheel scroll speed during fast scrolls
• false Claude Code scrolls at a constant rate per wheel notch

{
  "wheelScrollAccelerationEnabled": false
}

キー名をコピー公式ドキュメント

Customize the attribution Claude Code adds to git commits and pull requests. Commits get a git trailer such as Co-Authored-By by default; pull request descriptions get plain text. Set each part separately with the sub-keys below.

型

object with commit and pr strings and a sessionUrl Boolean, or false to hide all attribution. The false value requires Claude Code v2.1.281 or later; earlier versions reject it and skip the whole user, project, or local settings file that holds it

既定値

unset, so Claude Code uses the standard attribution shown under each sub-key

置ける場所

Any file

分類

Git and attribution

{
  "attribution": {
    "commit": "Generated with AI\n\nCo-Authored-By: AI <ai@example.com>",
    "pr": "",
    "sessionUrl": false
  }
}

キー名をコピー公式ドキュメント

Use attribution instead, which replaces this key and lets you change or hide the commit trailer, the pull request text, and the session link separately. Claude Code still honors includeCoAuthoredBy: false from settings files that predate attribution, but ignores it once you set attribution.commit or attribution.pr.

型

Boolean

既定値

true

置ける場所

Any file

分類

Git and attribution

• true the same as unset; Claude Code adds the commit trailer and the pull request attribution text
• false Claude Code omits both the commit trailer and the pull request attribution text, unless attribution sets commit or pr, in which case the attribution rules apply

{
  "includeCoAuthoredBy": false
}

キー名をコピー公式ドキュメント

Claude Code gives Claude two git-related pieces of context: its built-in instructions for how to write commits and pull requests, in the Bash tool's description, and a git status snapshot of your repository. The snapshot holds the current branch, the main branch, git status output, and recent commits. Claude Code reads it when a conversation starts.

型

Boolean

既定値

true

置ける場所

Any file

分類

Git and attribution

• true Claude Code includes its built-in commit and pull request workflow instructions and the git status snapshot. Cloud sessions never include the snapshot
• false Claude Code leaves both out

{
  "includeGitInstructions": false
}

キー名をコピー公式ドキュメント

Point the PR links Claude Code renders, in the footer badge and in tool-result summaries, at an internal code-review tool instead of github.com. Claude Code substitutes {host}, {owner}, {repo}, {number}, and {url} from the PR URL. GitLab merge request links on both surfaces keep their GitLab URL.

型

string, a URL template using any of the five placeholders

既定値

unset

置ける場所

Any file

分類

Git and attribution

{
  "prUrlTemplate": "https://reviews.example.com/{owner}/{repo}/pull/{number}"
}

キー名をコピー公式ドキュメント

Set the attribution text Claude Code adds to git commits, including any trailers. Set it to an empty string to hide commit attribution.

型

string

既定値

unset, so Claude Code adds Co-Authored-By: <name> <noreply@anthropic.com>. The name is the model in use when the commit is made, such as Claude Sonnet 5. When a subagent makes the commit, the trailer names the subagent's model.

置ける場所

Any file

分類

Git and attribution

{
  "attribution": {
    "commit": "Generated with AI\n\nCo-Authored-By: AI <ai@example.com>"
  }
}

キー名をコピー公式ドキュメント

Set the attribution text Claude Code adds to pull request descriptions. Set it to an empty string to hide pull request attribution.

型

string

既定値

unset, so Claude Code adds 🤖 Generated with Claude Code

置ける場所

Any file

分類

Git and attribution

{
  "attribution": {
    "pr": ""
  }
}

キー名をコピー公式ドキュメント

Choose whether Claude Code appends the claude.ai session link when it commits or opens a pull request from a cloud or Remote Control session. Claude Code adds the link as a Claude-Session trailer on commits and as a link in pull request descriptions. Set it to false to omit the link.

型

Boolean

既定値

true

置ける場所

Any file

分類

Git and attribution

• true Claude Code appends the claude.ai session link when it commits or opens a pull request from a cloud or Remote Control session
• false Claude Code omits the link

{
  "attribution": {
    "sessionUrl": false
  }
}

キー名をコピー公式ドキュメント

Limit which URLs HTTP hooks can target. When you define this key, Claude Code runs an HTTP hook only if its URL matches one of the patterns and blocks the rest without running them; an empty array blocks every HTTP hook.

型

array of URL patterns, with * as a wildcard

既定値

unset, so any URL is allowed

置ける場所

Any file

分類

Hooks and automation

{
  "allowedHttpHookUrls": ["https://hooks.example.com/*", "http://localhost:*"]
}

キー名をコピー公式ドキュメント

Restrict hook execution to hooks your organization deploys.

型

Boolean

既定値

unset, so hooks from every settings scope and plugin run

置ける場所

Managed

分類

Hooks and automation

• true only managed hooks run, plus Agent SDK hooks and hooks from plugins your managed settings force-enable. See What runs under allowManagedHooksOnly
• false hooks from every settings scope and plugin run

{
  "allowManagedHooksOnly": true
}

キー名をコピー公式ドキュメント

Turn off hooks, any custom status line, and any custom file suggestion command. Use it to turn all of these off temporarily without deleting them from your settings.

型

Boolean

既定値

unset, so hooks run

置ける場所

Any file

分類

Hooks and automation

• true Claude Code turns off hooks, any custom status line, and any custom file suggestion command
• false hooks, the status line, and the file suggestion command run

{
  "disableAllHooks": true
}

キー名をコピー公式ドキュメント

Turn off dynamic workflows and the bundled workflow commands for everyone your settings reach, such as an organization through managed settings. To turn workflows on or off just for yourself, use enableWorkflows instead, which the Dynamic workflows toggle in /config writes to your user settings.

型

Boolean

既定値

false

置ける場所

Any file

分類

Hooks and automation

• true Claude Code turns off dynamic workflows and the bundled workflow commands for everyone your settings reach
• false the same as unset; whether workflows are on then follows enableWorkflows and your plan's default

{
  "disableWorkflows": true
}

キー名をコピー公式ドキュメント

Turn dynamic workflows on or off for yourself when your plan's default isn't what you want. Appears in /config as Dynamic workflows, which writes this key to your user settings and removes it again when you toggle back to your plan's default. To turn workflows off for everyone from managed settings, use disableWorkflows instead.

型

Boolean

既定値

unset, so workflows are on unless you're on the Pro plan, where they're off

置ける場所

Any file

分類

Hooks and automation

• true Claude Code turns dynamic workflows on for you
• false Claude Code turns dynamic workflows off for you

{
  "enableWorkflows": true
}

キー名をコピー公式ドキュメント

Run your own commands, prompts, agents, HTTP requests, or MCP tools as hooks at points in Claude Code's lifecycle, such as before a tool call or when a session starts; the hooks reference lists every event, its payload, and its exit codes. Each event maps to a list of matcher groups, and each group lists the handlers to run when the matcher applies.

型

object keyed by hook event; each value is an array of { "matcher", "hooks" } groups whose hooks entries have a type of "command", "prompt", "agent", "http", or "mcp_tool"

既定値

unset, so no hooks run

置ける場所

Any file

分類

Hooks and automation

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          { "type": "command", "command": "~/.claude/hooks/check-bash.sh" }
        ]
      }
    ]
  }
}

キー名をコピー公式ドキュメント

An HTTP hook can put the value of an environment variable into a request header, for example an Authorization: Bearer $HOOK_TOKEN header, but only for variables the hook lists in its own allowedEnvVars. This key sets an outer limit on that list for every HTTP hook: a hook can use a variable only if both its own allowedEnvVars and this key name it. Use it to stop a hook from reading a secret it shouldn't, even when the hook's definition asks for it.

型

array of environment variable names

既定値

unset, so each hook's own allowedEnvVars list applies

置ける場所

Any file

分類

Hooks and automation

{
  "httpHookAllowedEnvVars": ["MY_TOKEN", "HOOK_SECRET"]
}

キー名をコピー公式ドキュメント

Choose whether typing the keyword ultracode in a prompt triggers a dynamic workflow. Set it to false to type the word without triggering one.

型

Boolean

既定値

true

置ける場所

Any file

分類

Hooks and automation

• true typing ultracode in a prompt triggers a dynamic workflow
• false you can type the word without triggering one

{
  "workflowKeywordTriggerEnabled": false
}

キー名をコピー公式ドキュメント

Set the agent count Claude aims for in the dynamic workflows it writes. Claude Code sends the value to Claude as advice, not an enforced cap: "small" asks for fewer than 5 agents, "medium" fewer than 10, and "large" fewer than 50. Choose "small" when you want to bound what a workflow spends. Requires Claude Code v2.1.219 or later.

型

string, one of:

既定値

"medium", or "small" when you're signed in on a Pro plan with Claude Code v2.1.271 or later

置ける場所

Any file

分類

Hooks and automation

• "unrestricted" no guideline, so Claude sizes the workflow to the task
• "small" Claude aims for fewer than 5 agents
• "medium" Claude aims for fewer than 10 agents
• "large" Claude aims for fewer than 50 agents

{
  "workflowSizeGuideline": "small"
}

キー名をコピー公式ドキュメント

Turn off the skills and workflows included with Claude Code. Claude Code removes bundled skills and workflows entirely, while built-in commands such as /init stay typable but are hidden from the model.

型

Boolean

既定値

unset, so bundled skills load

置ける場所

Any file

分類

Plugins and skills

• true Claude Code removes bundled skills and workflows and hides built-in commands such as /init from the model
• false bundled skills load

{
  "disableBundledSkills": true
}

キー名をコピー公式ドキュメント

Turn off inline shell execution for ` !... and ``! blocks in skills and custom commands from user, project, plugin, or additional-directory sources. Claude Code replaces each command with [shell command execution disabled by policy] instead of running it.`

型

Boolean

既定値

unset, so inline shell runs

置ける場所

Any file

分類

Plugins and skills

• true Claude Code replaces each inline shell command with [shell command execution disabled by policy] instead of running it
• false inline shell runs

{
  "disableSkillShellExecution": true
}

キー名をコピー公式ドキュメント

Hide or collapse a skill without editing its SKILL.md. Claude Code applies the value under each skill's name to the skill list Claude sees and to your / autocomplete.

型

object mapping skill name to one of:

既定値

unset, so every skill is "on"

置ける場所

Any file

分類

Plugins and skills

• "on" Claude sees the skill and you can type /name
• "name-only" Claude sees the skill by name without its description
• "user-invocable-only" Claude doesn't see the skill, but you can still type /name
• "off" Claude doesn't see the skill and /name is hidden from autocomplete

{
  "skillOverrides": {
    "legacy-context": "name-only",
    "deploy": "off"
  }
}

キー名をコピー公式ドキュメント

Turn off the download of the skills enabled for your claude.ai account. Claude Code downloads them into ~/.claude/skills/synced/ in terminal sessions where you sign in with your claude.ai account, interactive or non-interactive, and in Cowork and cloud sessions. Set false to stop that download and stop loading the skills it already synced. Claude Code honors only false: true is the same as unset and doesn't turn syncing on where it's otherwise off.

型

Boolean

既定値

unset, so sessions signed in with your claude.ai account sync your skills

置ける場所

User, local, or managed

分類

Plugins and skills

• false Claude Code stops downloading synced skills and stops loading the ones already in ~/.claude/skills/synced/. In user or managed settings, it also moves them to ~/.claude/skills/.trash/
• true the same as unset

{
  "syncClaudeAiSkills": false
}

キー名をコピー公式ドキュメント

Turn off the download of the plugins enabled for your claude.ai account. Claude Code downloads them into ~/.claude/plugins/synced/ at the start of terminal sessions where you sign in with your claude.ai account and in Cowork sessions, and loads each one as <name>@synced. Set false to stop that download and stop loading the plugins it already synced. Claude Code honors only false: true is the same as unset and doesn't turn syncing on where it's otherwise off. Requires Claude Code v2.1.273 or later.

型

Boolean

既定値

unset, so sessions signed in with your claude.ai account sync your plugins

置ける場所

User, local, or managed

分類

Plugins and skills

• false Claude Code stops downloading synced plugins and stops loading the ones already in ~/.claude/plugins/synced/. In user or managed settings, it also moves them to ~/.claude/plugins/.trash/
• true the same as unset

{
  "syncClaudeAiPlugins": false
}

キー名をコピー公式ドキュメント

Choose which channel plugins can push messages into sessions in your organization. When you set it, Claude Code uses your list in place of the default Anthropic allowlist; each entry names a plugin and the marketplace it comes from.

型

array of objects, each with marketplace and plugin strings. An entry can instead be a "plugin@marketplace" string such as "telegram@claude-plugins-official", which Claude Code treats as the equivalent object. The string form requires Claude Code v2.1.267 or later; earlier versions reject the whole allowedChannelPlugins value when it contains one

既定値

unset, so Claude Code uses the default Anthropic allowlist

置ける場所

Managed

分類

Plugins and skills

{
  "channelsEnabled": true,
  "allowedChannelPlugins": [
    { "marketplace": "claude-plugins-official", "plugin": "telegram" }
  ]
}

キー名をコピー公式ドキュメント

Block plugin marketplace sources for your organization. Claude Code checks the blocklist on marketplace add and on plugin install, update, refresh, and auto-update, so a marketplace someone added before you set the policy can't be used to fetch plugins either. Blocked sources are checked before download, so they never touch the filesystem.

型

array of marketplace source objects, in the same forms as strictKnownMarketplaces

既定値

unset, so no marketplace is blocked

置ける場所

Managed

分類

Plugins and skills

{
  "blockedMarketplaces": [
    { "source": "github", "repo": "untrusted/plugins" }
  ]
}

キー名をコピー公式ドキュメント

Allow channels for your organization. On claude.ai Team and Enterprise plans, Claude Code blocks channels until you set this to true. For Anthropic Console accounts that authenticate with an API key, channels are allowed by default. If your organization deploys managed settings, Claude Code blocks channels on those accounts too until you set this key to true.

型

Boolean

既定値

unset; channels are blocked on Team and Enterprise plans and on Console accounts with managed settings, and allowed on Pro and Max plans and on Console accounts without managed settings

置ける場所

Managed

分類

Plugins and skills

• true Claude Code allows channels for your organization
• false the same as unset; whether channels are blocked depends on your plan, as the Default says

{
  "channelsEnabled": true
}

キー名をコピー公式ドキュメント

Block the command plugin source, which installs a plugin by running a marketplace-declared command on the user's machine. When you set it to true, Claude Code never runs the command, doesn't install or update command-sourced plugins, and stops loading the ones already installed. Set it to false to allow them explicitly. Whenever it blocks command sources, whether you set it to true or leave it unset under allowManagedHooksOnly, it also blocks marketplace headersHelper commands, except for a marketplace that managed settings themselves declare. Requires Claude Code v2.1.229 or later, and the headersHelper block requires v2.1.238 or later.

型

Boolean

既定値

unset, so Claude Code follows allowManagedHooksOnly: an organization that restricts hook execution to managed settings gets command sources disabled too

置ける場所

Managed

分類

Plugins and skills

• true Claude Code never runs the marketplace-declared command, doesn't install or update command-sourced plugins, and stops loading the ones already installed
• false Claude Code allows command-sourced plugins explicitly

{
  "disableCommandPluginSources": true
}