update-config
GitHub用于通过修改 settings.json 配置 Claude Code 环境,包括设置自动化钩子、权限、环境变量及插件等。
Trigger Scenarios
Install
npx skills add asgeirtj/system_prompts_leaks --skill update-config -g -y
SKILL.md
Frontmatter
{
"name": "update-config",
"description": "Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before\/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory\/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json\/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme\/model, suggest the \/config command."
}
Update Config Skill
Modify Claude Code configuration by updating settings.json files.
When Hooks Are Required (Not Memory)
If the user wants something to happen automatically in response to an EVENT, they need a hook configured in settings.json. Memory/preferences cannot trigger automated actions.
These require hooks:
- "Before compacting, ask me what to preserve" → PreCompact hook
- "After writing files, run prettier" → PostToolUse hook with Write|Edit matcher
- "When I run bash commands, log them" → PreToolUse hook with Bash matcher
- "Always run tests after code changes" → PostToolUse hook
Hook events: PreToolUse, PostToolUse, PreCompact, PostCompact, Stop, Notification, SessionStart
CRITICAL: Read Before Write
Always read the existing settings file before making changes. Merge new settings with existing ones - never replace the entire file.
CRITICAL: Use AskUserQuestion for Ambiguity
When the user's request is ambiguous, use AskUserQuestion to clarify:
- Which settings file to modify (user/project/local)
- Whether to add to existing arrays or replace them
- Specific values when multiple options exist
Decision: /config command vs Direct Edit
Suggest the /config slash command for these simple settings:
theme,editorMode,verbose,modellanguage,alwaysThinkingEnabledpermissions.defaultMode
Edit settings.json directly for:
- Hooks (PreToolUse, PostToolUse, etc.)
- Complex permission rules (allow/deny arrays)
- Environment variables
- MCP server configuration
- Plugin configuration
Workflow
- Clarify intent - Ask if the request is ambiguous
- Read existing file - Use Read tool on the target settings file
- Merge carefully - Preserve existing settings, especially arrays
- Edit file - Use Edit tool (if file doesn't exist, ask user to create it first)
- Confirm - Tell user what was changed
Merging Arrays (Important!)
When adding to permission arrays or hook arrays, merge with existing, don't replace:
WRONG (replaces existing permissions):
{ "permissions": { "allow": ["Bash(npm *)"] } }
RIGHT (preserves existing + adds new):
{
"permissions": {
"allow": [
"Bash(git *)", // existing
"Edit(.claude)", // existing
"Bash(npm *)" // new
]
}
}
Settings File Locations
Choose the appropriate file based on scope:
| File | Scope | Git | Use For |
|---|---|---|---|
~/.claude/settings.json |
Global | N/A | Personal preferences for all projects |
.claude/settings.json |
Project | Commit | Team-wide hooks, permissions, plugins |
.claude/settings.local.json |
Project | Gitignore | Personal overrides for this project |
Settings load in order: user → project → local (later overrides earlier).
Settings Schema Reference
Permissions
{
"permissions": {
"allow": ["Bash(npm *)", "Edit(.claude)", "Read"],
"deny": ["Bash(rm -rf *)"],
"ask": ["Edit(//etc/*)"],
"defaultMode": "default" | "plan" | "acceptEdits" | "dontAsk",
"additionalDirectories": ["/extra/dir"]
}
}
Permission Rule Syntax:
- Exact match:
"Bash(npm run test)" - Prefix wildcard:
"Bash(git *)"- matchesgit,git status,git commit, etc. - Tool only:
"Read"- allows all Read operations
Environment Variables
{
"env": {
"DEBUG": "true",
"MY_API_KEY": "value"
}
}
Model & Agent
{
"model": "sonnet", // or "fable", "opus", "haiku", full model ID
"agent": "agent-name",
"alwaysThinkingEnabled": true
}
Attribution (Commits & PRs)
{
"attribution": {
"commit": "Custom commit trailer text",
"pr": "Custom PR description text"
}
}
Set commit or pr to empty string "" to hide that attribution.
MCP Server Management
{
"enableAllProjectMcpServers": true,
"enabledMcpjsonServers": ["server1", "server2"],
"disabledMcpjsonServers": ["blocked-server"]
}
Plugins
{
"enabledPlugins": {
"formatter@anthropic-tools": true
}
}
Plugin syntax: plugin-name@source where source is claude-code-marketplace, claude-plugins-official, or builtin.
Other Settings
language: Preferred response language (e.g., "japanese")cleanupPeriodDays: Days to keep transcripts before automatic cleanup (default: 30; minimum 1)respectGitignore: Whether to respect .gitignore (default: true)spinnerTipsEnabled: Show tips in spinnerspinnerVerbs: Customize spinner verbs ({ "mode": "append" | "replace", "verbs": [...] })spinnerTipsOverride: Override spinner tips ({ "excludeDefault": true, "tips": ["Custom tip"] })syntaxHighlightingDisabled: Disable diff highlighting
Hooks Configuration
Hooks run commands at specific points in Claude Code's lifecycle.
Hook Structure
{
"hooks": {
"EVENT_NAME": [
{
"matcher": "ToolName|OtherTool",
"hooks": [
{
"type": "command",
"command": "your-command-here",
"timeout": 60,
"statusMessage": "Running..."
}
]
}
]
}
}
Hook Events
| Event | Matcher | Purpose |
|---|---|---|
| PermissionRequest | Tool name | Run before permission prompt |
| PreToolUse | Tool name | Run before tool, can block |
| PostToolUse | Tool name | Run after successful tool |
| PostToolUseFailure | Tool name | Run after tool fails |
| Notification | Notification type | Run on notifications |
| Stop | - | Run when Claude stops (including clear, resume, compact) |
| PreCompact | "manual"/"auto" | Before compaction |
| PostCompact | "manual"/"auto" | After compaction (receives summary) |
| UserPromptSubmit | - | When user submits |
| SessionStart | - | When session starts |
Common tool matchers: Bash, Write, Edit, Read, Glob, Grep
Hook Types
1. Command Hook - Runs a shell command:
{ "type": "command", "command": "prettier --write $FILE", "timeout": 30 }
2. Prompt Hook - Evaluates a condition with LLM:
{ "type": "prompt", "prompt": "Is this safe? $ARGUMENTS" }
Only available for tool events: PreToolUse, PostToolUse, PermissionRequest.
3. Agent Hook - Runs an agent with tools:
{ "type": "agent", "prompt": "Verify tests pass: $ARGUMENTS" }
Only available for tool events: PreToolUse, PostToolUse, PermissionRequest.
Hook Input (stdin JSON)
{
"session_id": "abc123",
"tool_name": "Write",
"tool_input": { "file_path": "/path/to/file.txt", "content": "..." },
"tool_response": { "success": true } // PostToolUse only
}
Hook JSON Output
Hooks can return JSON to control behavior:
{
"systemMessage": "Warning shown to user in UI",
"continue": false,
"stopReason": "Message shown when blocking",
"suppressOutput": false,
"decision": "block",
"reason": "Explanation for decision",
"hookSpecificOutput": {
"hookEventName": "PostToolUse",
"additionalContext": "Context injected back to model"
}
}
Fields:
systemMessage- Display a message to the user (all hooks)continue- Set tofalseto block/stop (default: true)stopReason- Message shown whencontinueis falsesuppressOutput- Hide stdout from transcript (default: false)decision- "block" for PostToolUse/Stop/UserPromptSubmit hooks (deprecated for PreToolUse, use hookSpecificOutput.permissionDecision instead)reason- Explanation for decisionhookSpecificOutput- Event-specific output (must includehookEventName):additionalContext- Text injected into model contextpermissionDecision- "allow", "deny", or "ask" (PreToolUse only)permissionDecisionReason- Reason for the permission decision (PreToolUse only)updatedInput- Modified tool input (PreToolUse only)
Common Patterns
Auto-format after writes:
{
"hooks": {
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "jq -r '.tool_response.filePath // .tool_input.file_path' | { read -r f; prettier --write \"$f\"; } 2>/dev/null || true"
}]
}]
}
}
Log all bash commands:
{
"hooks": {
"PreToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "jq -r '.tool_input.command' >> ~/.claude/bash-log.txt"
}]
}]
}
}
Stop hook that displays message to user:
Command must output JSON with systemMessage field:
# Example command that outputs: {"systemMessage": "Session complete!"}
echo '{"systemMessage": "Session complete!"}'
Run tests after code changes:
{
"hooks": {
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "jq -r '.tool_input.file_path // .tool_response.filePath' | grep -E '\\.(ts|js)$' && npm test || true"
}]
}]
}
}
Constructing a Hook (with verification)
Given an event, matcher, target file, and desired behavior, follow this flow. Each step catches a different failure class — a hook that silently does nothing is worse than no hook.
-
Dedup check. Read the target file. If a hook already exists on the same event+matcher, show the existing command and ask: keep it, replace it, or add alongside.
-
Construct the command for THIS project — don't assume. The hook receives JSON on stdin. Build a command that:
- Extracts any needed payload safely — use
jq -rinto a quoted variable or{ read -r f; ... "$f"; }, NOT unquoted| xargs(splits on spaces) - Invokes the underlying tool the way this project runs it (npx/bunx/yarn/pnpm? Makefile target? globally-installed?)
- Skips inputs the tool doesn't handle (formatters often have
--ignore-unknown; if not, guard by extension) - Stays RAW for now — no
|| true, no stderr suppression. You'll wrap it after the pipe-test passes.
- Extracts any needed payload safely — use
-
Pipe-test the raw command. Synthesize the stdin payload the hook will receive and pipe it directly:
Pre|PostToolUseonWrite|Edit:echo '{"tool_name":"Edit","tool_input":{"file_path":"<a real file from this repo>"}}' | <cmd>Pre|PostToolUseonBash:echo '{"tool_name":"Bash","tool_input":{"command":"ls"}}' | <cmd>Stop/UserPromptSubmit/SessionStart: most commands don't read stdin, soecho '{}' | <cmd>suffices
Check exit code AND side effect (file actually formatted, test actually ran). If it fails you get a real error — fix (wrong package manager? tool not installed? jq path wrong?) and retest. Once it works, wrap with
2>/dev/null || true(unless the user wants a blocking check). -
Write the JSON. Merge into the target file (schema shape in the "Hook Structure" section above). If this creates
.claude/settings.local.jsonfor the first time, add it to .gitignore — the Write tool doesn't auto-gitignore it. -
Validate syntax + schema in one shot:
jq -e '.hooks.<event>[] | select(.matcher == "<matcher>") | .hooks[] | select(.type == "command") | .command' <target-file>Exit 0 + prints your command = correct. Exit 4 = matcher doesn't match. Exit 5 = malformed JSON or wrong nesting. A broken settings.json silently disables ALL settings from that file — fix any pre-existing malformation too.
-
Prove the hook fires — only for
Pre|PostToolUseon a matcher you can trigger in-turn (Write|Editvia Edit,Bashvia Bash).Stop/UserPromptSubmit/SessionStartfire outside this turn — skip to step 7.For a formatter on
PostToolUse/Write|Edit: introduce a detectable violation via Edit (two consecutive blank lines, bad indentation, missing semicolon — something this formatter corrects; NOT trailing whitespace, Edit strips that before writing), re-read, confirm the hook fixed it. For anything else: temporarily prefix the command in settings.json withecho "$(date) hook fired" >> /tmp/claude-hook-check.txt;, trigger the matching tool (Edit forWrite|Edit, a harmlesstrueforBash), read the sentinel file.Always clean up — revert the violation, strip the sentinel prefix — whether the proof passed or failed.
If proof fails but pipe-test passed and
jq -epassed: the settings watcher isn't watching.claude/— it only watches directories that had a settings file when this session started. The hook is written correctly. Tell the user to open/hooksonce (reloads config) or restart — you can't do this yourself;/hooksis a user UI menu and opening it ends this turn. -
Handoff. Tell the user the hook is live (or needs
/hooks/restart per the watcher caveat). Point them at/hooksto review, edit, or disable it later. The UI only shows "Ran N hooks" if a hook errors or is slow — silent success is invisible by design.
Example Workflows
Adding a Hook
User: "Format my code after Claude writes it"
- Clarify: Which formatter? (prettier, gofmt, etc.)
- Read:
.claude/settings.json(or create if missing) - Merge: Add to existing hooks, don't replace
- Result:
{
"hooks": {
"PostToolUse": [{
"matcher": "Write|Edit",
"hooks": [{
"type": "command",
"command": "jq -r '.tool_response.filePath // .tool_input.file_path' | { read -r f; prettier --write \"$f\"; } 2>/dev/null || true"
}]
}]
}
}
Adding Permissions
User: "Allow npm commands without prompting"
- Read: Existing permissions
- Merge: Add
Bash(npm *)to allow array - Result: Combined with existing allows
Environment Variables
User: "Set DEBUG=true"
- Decide: User settings (global) or project settings?
- Read: Target file
- Merge: Add to env object
{ "env": { "DEBUG": "true" } }
Common Mistakes to Avoid
- Replacing instead of merging - Always preserve existing settings
- Wrong file - Ask user if scope is unclear
- Invalid JSON - Validate syntax after changes
- Forgetting to read first - Always read before write
Troubleshooting Hooks
If a hook isn't running:
- Check the settings file - Read ~/.claude/settings.json or .claude/settings.json
- Verify JSON syntax - Invalid JSON silently fails
- Check the matcher - Does it match the tool name? (e.g., "Bash", "Write", "Edit")
- Check hook type - Is it "command", "prompt", or "agent"?
- Test the command - Run the hook command manually to see if it works
- Use --debug - Run
claude --debugto see hook execution logs
Full Settings JSON Schema
IMPORTANT: Do not update the env unless explicitly instructed to do so.
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"$schema": {
"description": "JSON Schema reference for Claude Code settings",
"type": "string"
},
"apiKeyHelper": {
"description": "Path to a script that outputs authentication values",
"type": "string"
},
"proxyAuthHelper": {
"description": "Shell command that outputs a Proxy-Authorization header value (EAP)",
"type": "string"
},
"awsCredentialExport": {
"description": "Path to a script that exports AWS credentials",
"type": "string"
},
"awsAuthRefresh": {
"description": "Path to a script that refreshes AWS authentication",
"type": "string"
},
"gcpAuthRefresh": {
"description": "Command to refresh GCP authentication (e.g., gcloud auth application-default login)",
"type": "string"
},
"policyHelper": {
"description": "Executable that computes managed settings at startup. Honored only from admin-controlled policy sources.",
"type": "object",
"properties": {
"path": {
"description": "Absolute path to the helper executable",
"type": "string"
},
"timeoutMs": {
"type": "integer",
"minimum": 1000,
"maximum": 9007199254740991
},
"refreshIntervalMs": {
"anyOf": [
{
"type": "number",
"const": 0
},
{
"type": "integer",
"minimum": 60000,
"maximum": 9007199254740991
}
]
}
},
"required": [
"path"
],
"additionalProperties": false
},
"fileSuggestion": {
"description": "Custom file suggestion configuration for @ mentions",
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "command"
},
"command": {
"type": "string"
}
},
"required": [
"type",
"command"
],
"additionalProperties": false
},
"respectGitignore": {
"description": "Whether file picker should respect .gitignore files (default: true). Note: .ignore files are always respected.",
"type": "boolean"
},
"breakReminder": {
"description": "@internal Opt-in break reminder. When enabled, shows a dismissible nudge after sustained continuous use. Never blocks — just a friendly heads-up.",
"type": "object",
"properties": {
"enabled": {
"description": "Show a friendly nudge after sustained continuous use (default false). Must be true for the reminder to fire.",
"type": "boolean"
},
"intervalMinutes": {
"description": "Minutes of continuous use before the reminder fires (default 120). Re-fires every interval until you take a break.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"breakThresholdMinutes": {
"description": "Minutes of inactivity that count as a break and reset the timer (default 15)",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"message": {
"description": "Custom reminder text. Leave unset for a rotating set of friendly nudges.",
"type": "string"
}
},
"additionalProperties": false
},
"quietHours": {
"description": "@internal Opt-in quiet hours. When enabled, shows a single soft nudge per session while inside the configured local-time window. Never blocks.",
"type": "object",
"properties": {
"enabled": {
"description": "Show a one-time nudge when you start or keep using the CLI inside your quiet-hours window (default false).",
"type": "boolean"
},
"start": {
"description": "Start of the quiet-hours window, 24-hour local time \"HH:MM\".",
"type": "string",
"pattern": "^([01]?\\d|2[0-3]):[0-5]\\d$"
},
"end": {
"description": "End of the quiet-hours window, 24-hour local time \"HH:MM\". May be earlier than start for an overnight range.",
"type": "string",
"pattern": "^([01]?\\d|2[0-3]):[0-5]\\d$"
}
},
"additionalProperties": false
},
"cleanupPeriodDays": {
"description": "Number of days to retain chat transcripts before automatic cleanup (default: 30). Minimum 1. Use a large value for long retention; use --no-session-persistence to disable transcript writes entirely.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"skillListingMaxDescChars": {
"description": "Per-skill description character cap in the skill listing sent to Claude (default: 1536). Descriptions longer than this are truncated. Raise to opt in to higher per-turn context cost.",
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
"skillListingBudgetFraction": {
"description": "Fraction of the context window (in characters) reserved for the skill listing sent to Claude (default: 0.01 = 1%). When the listing exceeds this, descriptions are shortened to fit. Raise to opt in to higher per-turn context cost.",
"type": "number",
"exclusiveMinimum": 0,
"maximum": 1
},
"wslInheritsWindowsSettings": {
"description": "When set to true in either admin-only Windows source — the HKLM SOFTWARE/Policies/ClaudeCode registry key or C:/Program Files/ClaudeCode/managed-settings.json — WSL reads managed settings from the full Windows policy chain (HKLM, C:/Program Files/ClaudeCode via DrvFs, HKCU) in addition to /etc/claude-code. Windows sources take priority. The flag is also required in HKCU itself for HKCU policy to apply on WSL (double opt-in: admin enables the chain, user confirms HKCU). On native Windows the flag has no effect.",
"type": "boolean"
},
"env": {
"description": "Environment variables to set for Claude Code sessions",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"attribution": {
"description": "Customize attribution text for commits and PRs. Each field defaults to the standard Claude Code attribution if not set.",
"type": "object",
"properties": {
"commit": {
"description": "Attribution text for git commits, including any trailers. Empty string hides attribution.",
"type": "string"
},
"pr": {
"description": "Attribution text for pull request descriptions. Empty string hides attribution.",
"type": "string"
}
},
"additionalProperties": false
},
"includeCoAuthoredBy": {
"description": "Deprecated: Use attribution instead. Whether to include Claude's co-authored by attribution in commits and PRs (defaults to true)",
"type": "boolean"
},
"includeGitInstructions": {
"description": "Include built-in commit and PR workflow instructions in Claude's system prompt (default: true)",
"type": "boolean"
},
"permissions": {
"description": "Tool usage permissions configuration",
"type": "object",
"properties": {
"allow": {
"description": "List of permission rules for allowed operations",
"type": "array",
"items": {
"type": "string"
}
},
"deny": {
"description": "List of permission rules for denied operations",
"type": "array",
"items": {
"type": "string"
}
},
"ask": {
"description": "List of permission rules that should always prompt for confirmation",
"type": "array",
"items": {
"type": "string"
}
},
"defaultMode": {
"description": "Default permission mode when Claude Code needs access",
"type": "string",
"enum": [
"acceptEdits",
"auto",
"bypassPermissions",
"default",
"dontAsk",
"plan"
]
},
"disableBypassPermissionsMode": {
"description": "Disable the ability to bypass permission prompts",
"type": "string",
"enum": [
"disable"
]
},
"disableAutoMode": {
"description": "Disable auto mode",
"type": "string",
"enum": [
"disable"
]
},
"additionalDirectories": {
"description": "Additional directories to include in the permission scope",
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": {}
},
"model": {
"description": "Override the default model used by Claude Code",
"type": "string"
},
"fallbackModel": {
"description": "Fallback model(s) tried in order when the primary model is overloaded or unavailable. Each element accepts a model name or alias; \"default\" expands to the default model. CLI --fallback-model takes precedence.",
"type": "array",
"items": {
"type": "string"
}
},
"availableModels": {
"description": "Allowlist of models that users can select. Accepts family aliases (\"opus\" allows any opus version), version prefixes (\"opus-4-5\" allows only that version), and full model IDs. If undefined, all models are available. If empty array, only the default model is available. Typically set in managed settings by enterprise administrators.",
"type": "array",
"items": {
"type": "string"
}
},
"enforceAvailableModels": {
"description": "When true and availableModels is a non-empty array, the Default model selection is also constrained: if the default model for the user tier is not in availableModels, Default resolves to the first allowed availableModels entry instead. Has no effect when availableModels is unset or an empty array. Typically set in managed settings by enterprise administrators.",
"type": "boolean"
},
"modelOverrides": {
"description": "Override mapping from Anthropic model ID (e.g. \"claude-opus-4-6\") to provider-specific model ID (e.g. a Bedrock inference profile ARN). Typically set in managed settings by enterprise administrators.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"enableAllProjectMcpServers": {
"description": "Whether to automatically approve all MCP servers in the project",
"type": "boolean"
},
"enabledMcpjsonServers": {
"description": "List of approved MCP servers from .mcp.json",
"type": "array",
"items": {
"type": "string"
}
},
"disabledMcpjsonServers": {
"description": "List of rejected MCP servers from .mcp.json",
"type": "array",
"items": {
"type": "string"
}
},
"skillOverrides": {
"description": "Per-skill listing overrides keyed by skill name. \"name-only\" lists the skill without its description; \"user-invocable-only\" hides it from the model but keeps /name; \"off\" hides it from both. Absent = on.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string",
"enum": [
"on",
"name-only",
"user-invocable-only",
"off"
]
}
},
"disableBundledSkills": {
"description": "Disable the skills and workflows that ship with Claude Code: bundled skills and workflows are removed entirely; built-in slash commands stay typable but are hidden from the model. Plugins, .claude/skills/, and .claude/commands/ are unaffected. Equivalent to CLAUDE_CODE_DISABLE_BUNDLED_SKILLS=1.",
"type": "boolean"
},
"allowedMcpServers": {
"description": "Enterprise allowlist of MCP servers that can be used. Applies to all scopes including enterprise servers from managed-mcp.json. If undefined, all servers are allowed. If empty array, no servers are allowed. Denylist takes precedence - if a server is on both lists, it is denied.",
"type": "array",
"items": {
"type": "object",
"properties": {
"serverName": {
"description": "Name of the MCP server that users are allowed to configure",
"type": "string",
"pattern": "^[a-zA-Z0-9_-]+$"
},
"serverCommand": {
"description": "Command array [command, ...args] to match exactly for allowed stdio servers",
"minItems": 1,
"type": "array",
"items": {
"type": "string"
}
},
"serverUrl": {
"description": "URL pattern with wildcard support (e.g., \"https://*.example.com/*\") for allowed remote MCP servers",
"type": "string"
}
},
"additionalProperties": false
}
},
"deniedMcpServers": {
"description": "Enterprise denylist of MCP servers that are explicitly blocked. If a server is on the denylist, it will be blocked across all scopes including enterprise. Denylist takes precedence over allowlist - if a server is on both lists, it is denied.",
"type": "array",
"items": {
"type": "object",
"properties": {
"serverName": {
"description": "Name of the MCP server that is explicitly blocked",
"type": "string",
"pattern": "^[a-zA-Z0-9_-]+$"
},
"serverCommand": {
"description": "Command array [command, ...args] to match exactly for blocked stdio servers",
"minItems": 1,
"type": "array",
"items": {
"type": "string"
}
},
"serverUrl": {
"description": "URL pattern with wildcard support (e.g., \"https://*.example.com/*\") for blocked remote MCP servers",
"type": "string"
}
},
"additionalProperties": false
}
},
"hooks": {
"description": "Custom commands to run before/after tool executions",
"type": "object",
"propertyNames": {
"anyOf": [
{
"type": "string",
"enum": [
"PreToolUse",
"PostToolUse",
"PostToolUseFailure",
"PostToolBatch",
"Notification",
"UserPromptSubmit",
"UserPromptExpansion",
"SessionStart",
"SessionEnd",
"Stop",
"StopFailure",
"SubagentStart",
"SubagentStop",
"PreCompact",
"PostCompact",
"PermissionRequest",
"PermissionDenied",
"Setup",
"TeammateIdle",
"TaskCreated",
"TaskCompleted",
"Elicitation",
"ElicitationResult",
"ConfigChange",
"WorktreeCreate",
"WorktreeRemove",
"InstructionsLoaded",
"CwdChanged",
"FileChanged",
"MessageDisplay"
]
},
{
"not": {}
}
]
},
"additionalProperties": {
"type": "array",
"items": {
"type": "object",
"properties": {
"matcher": {
"description": "String pattern to match (e.g. tool names like \"Write\")",
"type": "string"
},
"hooks": {
"description": "List of hooks to execute when the matcher matches",
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"type": {
"description": "Shell command hook type",
"type": "string",
"const": "command"
},
"command": {
"description": "Shell command to execute",
"type": "string"
},
"args": {
"description": "Argument list for exec form. When present, `command` is resolved as an executable and spawned directly with these arguments — no shell. Path placeholders like ${CLAUDE_PLUGIN_ROOT} are substituted per-element as plain strings, so paths with quotes, $, or backticks never reach a shell parser. When absent, `command` runs through a shell (bash on POSIX, PowerShell on Windows without Git Bash).",
"type": "array",
"items": {
"type": "string"
}
},
"if": {
"description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.",
"type": "string"
},
"shell": {
"description": "Shell interpreter. 'bash' uses your $SHELL (bash/zsh/sh); 'powershell' uses pwsh. Defaults to bash (powershell on Windows without Git Bash).",
"type": "string",
"enum": [
"bash",
"powershell"
]
},
"timeout": {
"description": "Timeout in seconds for this specific command",
"type": "number",
"exclusiveMinimum": 0
},
"statusMessage": {
"description": "Custom status message to display in spinner while hook runs",
"type": "string"
},
"once": {
"description": "If true, hook runs once and is removed after execution",
"type": "boolean"
},
"async": {
"description": "If true, hook runs in background without blocking",
"type": "boolean"
},
"asyncRewake": {
"description": "If true, hook runs in background and wakes the model on exit code 2 (blocking error). Implies async.",
"type": "boolean"
},
"rewakeMessage": {
"description": "@internal Custom prefix for the system-reminder shown to the model when an asyncRewake hook exits with code 2. The hook output is appended after this prefix.",
"type": "string",
"minLength": 1
},
"rewakeSummary": {
"description": "@internal One-line summary shown to the user in the terminal when an asyncRewake hook exits with code 2. Defaults to \"Stop hook feedback\".",
"type": "string",
"minLength": 1
}
},
"required": [
"type",
"command"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"type": {
"description": "LLM prompt hook type",
"type": "string",
"const": "prompt"
},
"prompt": {
"description": "Prompt to evaluate with LLM. Use $ARGUMENTS placeholder for hook input JSON.",
"type": "string"
},
"if": {
"description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.",
"type": "string"
},
"timeout": {
"description": "Timeout in seconds for this specific prompt evaluation",
"type": "number",
"exclusiveMinimum": 0
},
"model": {
"description": "Model to use for this prompt hook (e.g., \"claude-sonnet-4-6\"). If not specified, uses the default small fast model.",
"type": "string"
},
"continueOnBlock": {
"description": "Sets the continue value for the decision:\"block\" produced when ok is false. Default false (turn ends). Whether continue:true lets the turn proceed depends on the event's decision:\"block\" semantics. On PostToolUse, the reason is fed back to Claude and the turn continues.",
"type": "boolean"
},
"statusMessage": {
"description": "Custom status message to display in spinner while hook runs",
"type": "string"
},
"once": {
"description": "If true, hook runs once and is removed after execution",
"type": "boolean"
}
},
"required": [
"type",
"prompt"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"type": {
"description": "Agentic verifier hook type",
"type": "string",
"const": "agent"
},
"prompt": {
"description": "Prompt describing what to verify (e.g. \"Verify that unit tests ran and passed.\"). Use $ARGUMENTS placeholder for hook input JSON.",
"type": "string"
},
"if": {
"description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.",
"type": "string"
},
"timeout": {
"description": "Timeout in seconds for agent execution (default 60)",
"type": "number",
"exclusiveMinimum": 0
},
"model": {
"description": "Model to use for this agent hook (e.g., \"claude-sonnet-4-6\"). If not specified, uses Haiku.",
"type": "string"
},
"statusMessage": {
"description": "Custom status message to display in spinner while hook runs",
"type": "string"
},
"once": {
"description": "If true, hook runs once and is removed after execution",
"type": "boolean"
}
},
"required": [
"type",
"prompt"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"type": {
"description": "HTTP hook type",
"type": "string",
"const": "http"
},
"url": {
"description": "URL to POST the hook input JSON to",
"type": "string",
"format": "uri"
},
"if": {
"description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.",
"type": "string"
},
"timeout": {
"description": "Timeout in seconds for this specific request",
"type": "number",
"exclusiveMinimum": 0
},
"headers": {
"description": "Additional headers to include in the request. Values may reference environment variables using $VAR_NAME or ${VAR_NAME} syntax (e.g., \"Authorization\": \"Bearer $MY_TOKEN\"). Only variables listed in allowedEnvVars will be interpolated.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"allowedEnvVars": {
"description": "Explicit list of environment variable names that may be interpolated in header values. Only variables listed here will be resolved; all other $VAR references are left as empty strings. Required for env var interpolation to work.",
"type": "array",
"items": {
"type": "string"
}
},
"statusMessage": {
"description": "Custom status message to display in spinner while hook runs",
"type": "string"
},
"once": {
"description": "If true, hook runs once and is removed after execution",
"type": "boolean"
}
},
"required": [
"type",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"type": {
"description": "MCP tool hook type",
"type": "string",
"const": "mcp_tool"
},
"server": {
"description": "Name of an already-configured MCP server to invoke",
"type": "string"
},
"tool": {
"description": "Name of the tool on that server to call",
"type": "string"
},
"input": {
"description": "Arguments passed to the MCP tool. String values support ${path} interpolation from the hook input JSON (e.g. \"${tool_input.file_path}\").",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"if": {
"description": "Permission rule syntax to filter when this hook runs (e.g., \"Bash(git *)\"). Only runs if the tool call matches the pattern. Avoids spawning hooks for non-matching commands.",
"type": "string"
},
"timeout": {
"description": "Timeout in seconds for this specific tool call",
"type": "number",
"exclusiveMinimum": 0
},
"statusMessage": {
"description": "Custom status message to display in spinner while hook runs",
"type": "string"
},
"once": {
"description": "If true, hook runs once and is removed after execution",
"type": "boolean"
}
},
"required": [
"type",
"server",
"tool"
],
"additionalProperties": false
}
]
}
}
},
"required": [
"hooks"
],
"additionalProperties": false
}
}
},
"worktree": {
"description": "Git worktree configuration for --worktree flag.",
"type": "object",
"properties": {
"symlinkDirectories": {
"description": "Directories to symlink from main repository to worktrees to avoid disk bloat. Must be explicitly configured - no directories are symlinked by default. Common examples: \"node_modules\", \".cache\", \".bin\"",
"type": "array",
"items": {
"type": "string"
}
},
"sparsePaths": {
"description": "Directories to include when creating worktrees, via git sparse-checkout (cone mode). Dramatically faster in large monorepos — only the listed paths are written to disk.",
"type": "array",
"items": {
"type": "string"
}
},
"baseRef": {
"description": "Which ref new worktrees branch from. 'fresh' (default) branches from origin/<default-branch> for a clean tree. 'head' branches from your current local HEAD so unpushed commits and feature-branch state are present. Applies to --worktree, EnterWorktree, and agent isolation.",
"type": "string",
"enum": [
"fresh",
"head"
]
},
"bgIsolation": {
"description": "Isolation mode for background sessions in this repo. 'worktree' (default) blocks Edit/Write in the main checkout until EnterWorktree is called. 'none' lets background jobs edit the working copy directly.",
"type": "string",
"enum": [
"worktree",
"none"
]
}
},
"additionalProperties": false
},
"disableAllHooks": {
"description": "Disable all hooks and statusLine execution",
"type": "boolean"
},
"disableAgentView": {
"description": "Disable agent view (`claude agents`, `--bg`, /background, the on-demand daemon). Typically set in managed settings. Equivalent to CLAUDE_CODE_DISABLE_AGENT_VIEW=1.",
"type": "boolean"
},
"disableRemoteControl": {
"description": "Disable Remote Control (claude.ai/code, `claude remote-control`, `--remote-control`/`--rc`, auto-start, and the in-session toggle). Typically set in managed settings.",
"type": "boolean"
},
"disableWorkflows": {
"description": "Disable the Workflows feature (also via CLAUDE_CODE_DISABLE_WORKFLOWS).",
"type": "boolean"
},
"disableArtifact": {
"description": "Disable the Artifact tool (also via CLAUDE_CODE_DISABLE_ARTIFACT).",
"type": "boolean"
},
"enableWorkflows": {
"description": "Enable or disable the Workflows feature for this user. Unset = default by plan once the feature is available.",
"type": "boolean"
},
"workflowKeywordTriggerEnabled": {
"description": "Enable the \"ultracode\" keyword trigger: including the keyword in a prompt opts that turn into the Workflow tool. Set to false to disable the trigger. Default: true.",
"type": "boolean"
},
"disableSkillShellExecution": {
"description": "Disable inline shell execution in skills and custom slash commands from user, project, or plugin sources. Commands are replaced with a placeholder instead of being run.",
"type": "boolean"
},
"defaultShell": {
"description": "Default shell for input-box ! commands. Defaults to 'bash' on all platforms (no Windows auto-flip).",
"type": "string",
"enum": [
"bash",
"powershell"
]
},
"allowManagedHooksOnly": {
"description": "When true (and set in managed settings), only hooks from managed settings run. User, project, and local hooks are ignored.",
"type": "boolean"
},
"allowedHttpHookUrls": {
"description": "Allowlist of URL patterns that HTTP hooks may target. Supports * as a wildcard (e.g. \"https://hooks.example.com/*\"). When set, HTTP hooks with non-matching URLs are blocked. If undefined, all URLs are allowed. If empty array, no HTTP hooks are allowed. Arrays merge across settings sources (same semantics as allowedMcpServers).",
"type": "array",
"items": {
"type": "string"
}
},
"httpHookAllowedEnvVars": {
"description": "Allowlist of environment variable names HTTP hooks may interpolate into headers. When set, each hook's effective allowedEnvVars is the intersection with this list. If undefined, no restriction is applied. Arrays merge across settings sources (same semantics as allowedMcpServers).",
"type": "array",
"items": {
"type": "string"
}
},
"allowManagedPermissionRulesOnly": {
"description": "When true (and set in managed settings), only permission rules (allow/deny/ask) from managed settings are respected. User, project, local, and CLI argument permission rules are ignored.",
"type": "boolean"
},
"allowManagedMcpServersOnly": {
"description": "When true (and set in managed settings), allowedMcpServers is only read from managed settings. deniedMcpServers still merges from all sources, so users can deny servers for themselves. Users can still add their own MCP servers, but only the admin-defined allowlist applies.",
"type": "boolean"
},
"allowAllClaudeAiMcps": {
"description": "When true (and set in managed settings), claude.ai cloud MCP connectors load alongside managed-mcp.json instead of being suppressed by its exclusive-control lockdown. Default off preserves the lockdown. Read from managed settings only.",
"type": "boolean"
},
"strictPluginOnlyCustomization": {
"description": "When set in managed settings, blocks non-plugin customization sources for the listed surfaces. Array form locks specific surfaces (e.g. [\"skills\", \"hooks\"]); `true` locks all four; `false` is an explicit no-op. Blocked: ~/.claude/{surface}/, .claude/{surface}/ (project), settings.json hooks, .mcp.json. NOT blocked: managed (policySettings) sources, plugin-provided customizations. Composes with strictKnownMarketplaces for end-to-end admin control — plugins gated by marketplace allowlist, everything else blocked here.",
"anyOf": [
{
"type": "boolean"
},
{
"type": "array",
"items": {
"type": "string",
"enum": [
"skills",
"agents",
"hooks",
"mcp"
]
}
}
]
},
"statusLine": {
"description": "Custom status line display configuration",
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "command"
},
"command": {
"type": "string"
},
"padding": {
"type": "number"
},
"refreshInterval": {
"description": "Re-run the status line command every N seconds in addition to event-driven updates",
"type": "number",
"minimum": 1
},
"hideVimModeIndicator": {
"description": "Hide the built-in `-- INSERT --` / `-- VISUAL --` indicator below the prompt. Use this when your status line script renders `vim.mode` itself.",
"type": "boolean"
}
},
"required": [
"type",
"command"
],
"additionalProperties": false
},
"prUrlTemplate": {
"description": "URL template for PR links in the footer link badges and inline messages. The detected git PR is rendered as the first footer-link badge. Placeholders: {host} {owner} {repo} {number} {url}. Example: \"https://reviews.example.com/{owner}/{repo}/pull/{number}\"",
"type": "string"
},
"footerLinksRegexes": {
"description": "Extra clickable footer badges that appear when a regex matches turn output (tool results and assistant responses). Read from user, flag, and managed settings only; ignored in project .claude/settings.json and local .claude/settings.local.json. At most 5 badges render; the oldest is displaced by newer matches and /clear removes them. Use to surface IDs printed by project CLIs as session links."
},
"subagentStatusLine": {
"description": "Custom per-subagent status line shown in the agent panel; receives row context as JSON on stdin",
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "command"
},
"command": {
"type": "string"
}
},
"required": [
"type",
"command"
],
"additionalProperties": false
},
"enabledPlugins": {
"description": "Enabled plugins using plugin-id@marketplace-id format. Example: { \"formatter@anthropic-tools\": true }. Also supports extended format with version constraints. Settings precedence is user < project < local < flag < policy, so to disable a plugin that project settings enable, set it to false in .claude/settings.local.json — setting false in ~/.claude/settings.json is overridden by the project.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "boolean"
},
{
"not": {}
}
]
}
},
"extraKnownMarketplaces": {
"description": "Additional marketplaces to make available for this repository. Typically used in repository .claude/settings.json to ensure team members have required plugin sources.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"properties": {
"source": {
"description": "Where to fetch the marketplace from",
"anyOf": [
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "url"
},
"url": {
"description": "Direct URL to marketplace.json file",
"type": "string",
"format": "uri"
},
"headers": {
"description": "Custom HTTP headers (e.g., for authentication)",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "github"
},
"repo": {
"description": "GitHub repository in owner/repo format",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"path": {
"description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)",
"type": "string"
},
"sparsePaths": {
"description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.",
"type": "array",
"items": {
"type": "string"
}
},
"skipLfs": {
"description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.",
"type": "boolean"
}
},
"required": [
"source",
"repo"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "git"
},
"url": {
"description": "Full git repository URL",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"path": {
"description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)",
"type": "string"
},
"sparsePaths": {
"description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.",
"type": "array",
"items": {
"type": "string"
}
},
"skipLfs": {
"description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.",
"type": "boolean"
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "npm"
},
"package": {
"description": "NPM package containing marketplace.json",
"type": "string"
}
},
"required": [
"source",
"package"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "file"
},
"path": {
"description": "Local file path to marketplace.json",
"type": "string"
}
},
"required": [
"source",
"path"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "directory"
},
"path": {
"description": "Local directory containing .claude-plugin/marketplace.json",
"type": "string"
}
},
"required": [
"source",
"path"
],
"additionalProperties": false
},
{
"description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "skills-dir"
}
},
"required": [
"source"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "hostPattern"
},
"hostPattern": {
"description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").",
"type": "string"
}
},
"required": [
"source",
"hostPattern"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "pathPattern"
},
"pathPattern": {
"description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.",
"type": "string"
}
},
"required": [
"source",
"pathPattern"
],
"additionalProperties": false
},
{
"description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "settings"
},
"name": {
"description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.",
"type": "string",
"minLength": 1
},
"plugins": {
"description": "Plugin entries declared inline in settings.json",
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"description": "Plugin name as it appears in the target repository",
"type": "string",
"minLength": 1
},
"source": {
"description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.",
"anyOf": [
{
"description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)",
"type": "string",
"pattern": "^\\.\\/.*"
},
{
"description": "NPM package as plugin source",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "npm"
},
"package": {
"description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)",
"anyOf": [
{
"type": "string"
},
{
"type": "string"
}
]
},
"version": {
"description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)",
"type": "string"
},
"registry": {
"description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)",
"type": "string",
"format": "uri"
}
},
"required": [
"source",
"package"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "url"
},
"url": {
"description": "Full git repository URL (https:// or git@)",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "github"
},
"repo": {
"description": "GitHub repository in owner/repo format",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"repo"
],
"additionalProperties": false
},
{
"description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "git-subdir"
},
"url": {
"description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL",
"type": "string"
},
"path": {
"description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.",
"type": "string",
"minLength": 1
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"url",
"path"
],
"additionalProperties": false
},
{
"description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "unsupported"
}
},
"required": [
"source"
],
"additionalProperties": false
}
]
},
"description": {
"type": "string"
},
"version": {
"type": "string"
},
"strict": {
"type": "boolean"
}
},
"required": [
"name",
"source"
],
"additionalProperties": false
}
},
"owner": {
"type": "object",
"properties": {
"name": {
"description": "Display name of the plugin author or organization",
"type": "string",
"minLength": 1
},
"email": {
"description": "Contact email for support or feedback",
"type": "string"
},
"url": {
"description": "Website, GitHub profile, or organization URL",
"type": "string"
}
},
"required": [
"name"
],
"additionalProperties": false
}
},
"required": [
"source",
"name",
"plugins"
],
"additionalProperties": false
}
]
},
"installLocation": {
"description": "Local cache path where marketplace manifest is stored (auto-generated if not provided)",
"type": "string"
},
"autoUpdate": {
"description": "Whether to automatically update this marketplace and its installed plugins on startup",
"type": "boolean"
}
},
"required": [
"source"
],
"additionalProperties": false
}
},
"strictKnownMarketplaces": {
"description": "Enterprise strict list of allowed marketplace sources. When set in managed settings, ONLY these exact sources can be added as marketplaces. The check happens BEFORE downloading, so blocked sources never touch the filesystem. Note: this is a policy gate only — it does NOT register marketplaces. To pre-register allowed marketplaces for users, also set extraKnownMarketplaces.",
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "url"
},
"url": {
"description": "Direct URL to marketplace.json file",
"type": "string",
"format": "uri"
},
"headers": {
"description": "Custom HTTP headers (e.g., for authentication)",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "github"
},
"repo": {
"description": "GitHub repository in owner/repo format",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"path": {
"description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)",
"type": "string"
},
"sparsePaths": {
"description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.",
"type": "array",
"items": {
"type": "string"
}
},
"skipLfs": {
"description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.",
"type": "boolean"
}
},
"required": [
"source",
"repo"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "git"
},
"url": {
"description": "Full git repository URL",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"path": {
"description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)",
"type": "string"
},
"sparsePaths": {
"description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.",
"type": "array",
"items": {
"type": "string"
}
},
"skipLfs": {
"description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.",
"type": "boolean"
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "npm"
},
"package": {
"description": "NPM package containing marketplace.json",
"type": "string"
}
},
"required": [
"source",
"package"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "file"
},
"path": {
"description": "Local file path to marketplace.json",
"type": "string"
}
},
"required": [
"source",
"path"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "directory"
},
"path": {
"description": "Local directory containing .claude-plugin/marketplace.json",
"type": "string"
}
},
"required": [
"source",
"path"
],
"additionalProperties": false
},
{
"description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "skills-dir"
}
},
"required": [
"source"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "hostPattern"
},
"hostPattern": {
"description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").",
"type": "string"
}
},
"required": [
"source",
"hostPattern"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "pathPattern"
},
"pathPattern": {
"description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.",
"type": "string"
}
},
"required": [
"source",
"pathPattern"
],
"additionalProperties": false
},
{
"description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "settings"
},
"name": {
"description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.",
"type": "string",
"minLength": 1
},
"plugins": {
"description": "Plugin entries declared inline in settings.json",
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"description": "Plugin name as it appears in the target repository",
"type": "string",
"minLength": 1
},
"source": {
"description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.",
"anyOf": [
{
"description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)",
"type": "string",
"pattern": "^\\.\\/.*"
},
{
"description": "NPM package as plugin source",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "npm"
},
"package": {
"description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)",
"anyOf": [
{
"type": "string"
},
{
"type": "string"
}
]
},
"version": {
"description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)",
"type": "string"
},
"registry": {
"description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)",
"type": "string",
"format": "uri"
}
},
"required": [
"source",
"package"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "url"
},
"url": {
"description": "Full git repository URL (https:// or git@)",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "github"
},
"repo": {
"description": "GitHub repository in owner/repo format",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"repo"
],
"additionalProperties": false
},
{
"description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "git-subdir"
},
"url": {
"description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL",
"type": "string"
},
"path": {
"description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.",
"type": "string",
"minLength": 1
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"url",
"path"
],
"additionalProperties": false
},
{
"description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "unsupported"
}
},
"required": [
"source"
],
"additionalProperties": false
}
]
},
"description": {
"type": "string"
},
"version": {
"type": "string"
},
"strict": {
"type": "boolean"
}
},
"required": [
"name",
"source"
],
"additionalProperties": false
}
},
"owner": {
"type": "object",
"properties": {
"name": {
"description": "Display name of the plugin author or organization",
"type": "string",
"minLength": 1
},
"email": {
"description": "Contact email for support or feedback",
"type": "string"
},
"url": {
"description": "Website, GitHub profile, or organization URL",
"type": "string"
}
},
"required": [
"name"
],
"additionalProperties": false
}
},
"required": [
"source",
"name",
"plugins"
],
"additionalProperties": false
}
]
}
},
"blockedMarketplaces": {
"description": "Enterprise blocklist of marketplace sources. When set in managed settings, these exact sources are blocked from being added as marketplaces. The check happens BEFORE downloading, so blocked sources never touch the filesystem.",
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "url"
},
"url": {
"description": "Direct URL to marketplace.json file",
"type": "string",
"format": "uri"
},
"headers": {
"description": "Custom HTTP headers (e.g., for authentication)",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "github"
},
"repo": {
"description": "GitHub repository in owner/repo format",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"path": {
"description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)",
"type": "string"
},
"sparsePaths": {
"description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.",
"type": "array",
"items": {
"type": "string"
}
},
"skipLfs": {
"description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.",
"type": "boolean"
}
},
"required": [
"source",
"repo"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "git"
},
"url": {
"description": "Full git repository URL",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"path": {
"description": "Path to marketplace.json within repo (defaults to .claude-plugin/marketplace.json)",
"type": "string"
},
"sparsePaths": {
"description": "Directories to include via git sparse-checkout (cone mode). Use for monorepos where the marketplace lives in a subdirectory. Example: [\".claude-plugin\", \"plugins\"]. If omitted, the full repository is cloned.",
"type": "array",
"items": {
"type": "string"
}
},
"skipLfs": {
"description": "Skip Git LFS smudge during clone and update (sets GIT_LFS_SKIP_SMUDGE=1) so LFS pointer files stay as pointers instead of downloading their content. Use for marketplaces hosted in repos with large LFS objects.",
"type": "boolean"
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "npm"
},
"package": {
"description": "NPM package containing marketplace.json",
"type": "string"
}
},
"required": [
"source",
"package"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "file"
},
"path": {
"description": "Local file path to marketplace.json",
"type": "string"
}
},
"required": [
"source",
"path"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "directory"
},
"path": {
"description": "Local directory containing .claude-plugin/marketplace.json",
"type": "string"
}
},
"required": [
"source",
"path"
],
"additionalProperties": false
},
{
"description": "Policy-list sentinel for the ~/.claude/skills/ auto-load (@skills-dir plugins). In strictKnownMarketplaces: opt the scan back IN (by default any allowlist blocks it). In blockedMarketplaces: turn the scan OFF without otherwise restricting marketplaces. Only meaningful in those two managed-settings lists (areLocalPluginDirsAllowedByPolicy); known_marketplaces.json / marketplace add etc. ignore it.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "skills-dir"
}
},
"required": [
"source"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "hostPattern"
},
"hostPattern": {
"description": "Regex pattern to match the host/domain extracted from any marketplace source type. For github sources, matches against \"github.com\". For git sources (SSH or HTTPS), extracts the hostname from the URL. Use in strictKnownMarketplaces to allow all marketplaces from a specific host (e.g., \"^github\\.mycompany\\.com$\").",
"type": "string"
}
},
"required": [
"source",
"hostPattern"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "pathPattern"
},
"pathPattern": {
"description": "Regex pattern matched against the .path field of file and directory sources. Use in strictKnownMarketplaces to allow filesystem-based marketplaces alongside hostPattern restrictions for network sources. Use \".*\" to allow all filesystem paths, or a narrower pattern (e.g., \"^/opt/approved/\") to restrict to specific directories.",
"type": "string"
}
},
"required": [
"source",
"pathPattern"
],
"additionalProperties": false
},
{
"description": "Inline marketplace manifest defined directly in settings.json. The reconciler writes a synthetic marketplace.json to the cache; diffMarketplaces detects edits via isEqual on the stored source (the plugins array is inside this object, so edits surface as sourceChanged).",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "settings"
},
"name": {
"description": "Marketplace name. Must match the extraKnownMarketplaces key (enforced); the synthetic manifest is written under this name. Same validation as PluginMarketplaceSchema plus reserved-name rejection — validateOfficialNameSource runs after the disk write, too late to clean up.",
"type": "string",
"minLength": 1
},
"plugins": {
"description": "Plugin entries declared inline in settings.json",
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"description": "Plugin name as it appears in the target repository",
"type": "string",
"minLength": 1
},
"source": {
"description": "Where to fetch the plugin from. Must be a remote source — relative paths have no marketplace repository to resolve against.",
"anyOf": [
{
"description": "Path to the plugin root, relative to the marketplace root (the directory containing .claude-plugin/, not .claude-plugin/ itself)",
"type": "string",
"pattern": "^\\.\\/.*"
},
{
"description": "NPM package as plugin source",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "npm"
},
"package": {
"description": "Package name (or url, or local path, or anything else that can be passed to `npm` as a package)",
"anyOf": [
{
"type": "string"
},
{
"type": "string"
}
]
},
"version": {
"description": "Specific version or version range (e.g., ^1.0.0, ~2.1.0)",
"type": "string"
},
"registry": {
"description": "Custom NPM registry URL (defaults to using system default, likely npmjs.org)",
"type": "string",
"format": "uri"
}
},
"required": [
"source",
"package"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "url"
},
"url": {
"description": "Full git repository URL (https:// or git@)",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "github"
},
"repo": {
"description": "GitHub repository in owner/repo format",
"type": "string"
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"repo"
],
"additionalProperties": false
},
{
"description": "Plugin located in a subdirectory of a larger repository (monorepo). Only the specified subdirectory is materialized; the rest of the repo is not downloaded.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "git-subdir"
},
"url": {
"description": "Git repository: GitHub owner/repo shorthand, https://, or git@ URL",
"type": "string"
},
"path": {
"description": "Subdirectory within the repo containing the plugin (e.g., \"tools/claude-plugin\"). Cloned sparsely using partial clone (--filter=tree:0) to minimize bandwidth for monorepos.",
"type": "string",
"minLength": 1
},
"ref": {
"description": "Git branch or tag to use (e.g., \"main\", \"v1.0.0\"). Defaults to repository default branch.",
"type": "string"
},
"sha": {
"description": "Specific commit SHA to use",
"type": "string",
"minLength": 40,
"maxLength": 40,
"pattern": "^[a-f0-9]{40}$"
}
},
"required": [
"source",
"url",
"path"
],
"additionalProperties": false
},
{
"description": "Placeholder for source types this Claude Code version does not recognize. Never authored by hand — PluginMarketplaceSchema rewrites unparseable sources to this so the entry remains in marketplace.plugins (detectDelistedPlugins must not see it as removed). Install attempts fail at cachePlugin with a clear \"update Claude Code\" message.",
"type": "object",
"properties": {
"source": {
"type": "string",
"const": "unsupported"
}
},
"required": [
"source"
],
"additionalProperties": false
}
]
},
"description": {
"type": "string"
},
"version": {
"type": "string"
},
"strict": {
"type": "boolean"
}
},
"required": [
"name",
"source"
],
"additionalProperties": false
}
},
"owner": {
"type": "object",
"properties": {
"name": {
"description": "Display name of the plugin author or organization",
"type": "string",
"minLength": 1
},
"email": {
"description": "Contact email for support or feedback",
"type": "string"
},
"url": {
"description": "Website, GitHub profile, or organization URL",
"type": "string"
}
},
"required": [
"name"
],
"additionalProperties": false
}
},
"required": [
"source",
"name",
"plugins"
],
"additionalProperties": false
}
]
}
},
"pluginSuggestionMarketplaces": {
"description": "Marketplace names whose plugins may surface as contextual install suggestions (relevance-based tips). No marketplace-declared suggestions surface without this allowlist; the built-in first-party frontend-design tip is unaffected. Only honored when set in managed settings (policy scope); the key is ignored in user, project, and local settings. A name only takes effect when the marketplace is registered on the machine AND its registered source is also declared in managed settings, either as the extraKnownMarketplaces entry for that name or as an entry of strictKnownMarketplaces. A marketplace registered from a different source under an allowlisted name is ignored. The official marketplace is exempt from the source requirement: allowlisting its name alone suffices, since that name can only register from the official Anthropic source.",
"type": "array",
"items": {
"type": "string"
}
},
"forceLoginMethod": {
"description": "Force a specific login method: \"claudeai\" for Claude Pro/Max, \"console\" for Console billing, \"gateway\" for the Cloud gateway OIDC device flow",
"type": "string",
"enum": [
"claudeai",
"console",
"gateway"
]
},
"forceLoginGatewayUrl": {
"description": "@internal Cloud gateway URL to pre-fill and auto-connect to during login. Typically set in local managed settings alongside forceLoginMethod: \"gateway\" so users never type the URL. Hidden from public SDK types until Cloud gateway is documented.",
"type": "string",
"format": "uri"
},
"parentSettingsBehavior": {
"description": "Controls whether the SDK parent tier (Options.managedSettings / --managed-settings) layers under this admin tier. \"first-wins\" (default): parent is dropped — admin tiers are the only policy source. \"merge\": parent's restrictive-only-filtered settings union under the admin winner. Has no effect when no admin tier exists (parent applies as the sole policy tier, still filtered restrictive-only).",
"type": "string",
"enum": [
"first-wins",
"merge"
]
},
"forceLoginOrgUUID": {
"description": "Organization UUID to require for OAuth login. Accepts a single UUID string or an array of UUIDs (any one is permitted). When set in managed settings, login fails if the authenticated account does not belong to a listed organization.",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"forceRemoteSettingsRefresh": {
"description": "When set in managed settings, the CLI blocks startup until remote managed settings are freshly fetched, and exits if the fetch fails",
"type": "boolean"
},
"otelHeadersHelper": {
"description": "Path to a script that outputs OpenTelemetry headers",
"type": "string"
},
"outputStyle": {
"description": "Controls the output style for assistant responses",
"type": "string"
},
"viewMode": {
"description": "Default transcript view mode on startup",
"type": "string",
"enum": [
"default",
"verbose",
"focus"
]
},
"language": {
"description": "Preferred language for Claude responses and voice dictation (e.g., \"japanese\", \"spanish\")",
"type": "string"
},
"skipWebFetchPreflight": {
"description": "Skip the WebFetch blocklist check for enterprise environments with restrictive security policies",
"type": "boolean"
},
"sandbox": {
"type": "object",
"properties": {
"enabled": {
"type": "boolean"
},
"failIfUnavailable": {
"description": "Exit with an error at startup if sandbox.enabled is true but the sandbox cannot start (missing dependencies or unsupported platform). When false (default), a warning is shown and commands run unsandboxed. Intended for managed-settings deployments that require sandboxing as a hard gate.",
"type": "boolean"
},
"autoAllowBashIfSandboxed": {
"type": "boolean"
},
"allowUnsandboxedCommands": {
"description": "Allow commands to run outside the sandbox via the dangerouslyDisableSandbox parameter. When false, the dangerouslyDisableSandbox parameter is completely ignored and all commands must run sandboxed. Default: true.",
"type": "boolean"
},
"network": {
"type": "object",
"properties": {
"allowedDomains": {
"type": "array",
"items": {
"type": "string"
}
},
"deniedDomains": {
"description": "Domains that are always blocked, even if matched by allowedDomains. Supports the same wildcard syntax as allowedDomains. Merged from all settings sources regardless of allowManagedDomainsOnly.",
"type": "array",
"items": {
"type": "string"
}
},
"allowManagedDomainsOnly": {
"description": "When true (and set in managed settings), only allowedDomains and WebFetch(domain:...) allow rules from managed settings are respected. User, project, local, and flag settings domains are ignored. Denied domains are still respected from all sources.",
"type": "boolean"
},
"allowUnixSockets": {
"description": "macOS only: Unix socket paths to allow. Ignored on Linux (seccomp cannot filter by path).",
"type": "array",
"items": {
"type": "string"
}
},
"allowAllUnixSockets": {
"description": "If true, allow all Unix sockets (disables blocking on both platforms).",
"type": "boolean"
},
"allowLocalBinding": {
"type": "boolean"
},
"allowMachLookup": {
"description": "macOS only: Additional XPC/Mach service names to allow looking up. Supports trailing-wildcard prefix matching (e.g., \"com.apple.coresimulator.*\"). Needed for tools that communicate via XPC such as the iOS Simulator or Playwright.",
"type": "array",
"items": {
"type": "string"
}
},
"httpProxyPort": {
"type": "number"
},
"socksProxyPort": {
"type": "number"
},
"tlsTerminate": {
"description": "[EXPERIMENTAL] Enable in-process TLS termination so the per-request filter can see HTTPS request bodies. Provide a CA cert+key, or omit both to have sandbox-runtime generate an ephemeral one for the session.",
"type": "object",
"properties": {
"caCertPath": {
"type": "string",
"minLength": 1
},
"caKeyPath": {
"type": "string",
"minLength": 1
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
"filesystem": {
"type": "object",
"properties": {
"allowWrite": {
"description": "Additional paths to allow writing within the sandbox. Merged with paths from Edit(...) allow permission rules.",
"type": "array",
"items": {
"type": "string"
}
},
"denyWrite": {
"description": "Additional paths to deny writing within the sandbox. Merged with paths from Edit(...) deny permission rules.",
"type": "array",
"items": {
"type": "string"
}
},
"denyRead": {
"description": "Additional paths to deny reading within the sandbox. Merged with paths from Read(...) deny permission rules.",
"type": "array",
"items": {
"type": "string"
}
},
"allowRead": {
"description": "Paths to re-allow reading within denyRead regions. Takes precedence over denyRead for matching paths.",
"type": "array",
"items": {
"type": "string"
}
},
"allowManagedReadPathsOnly": {
"description": "When true (set in managed settings), only allowRead paths from policySettings are used.",
"type": "boolean"
}
},
"additionalProperties": false
},
"ignoreViolations": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"enableWeakerNestedSandbox": {
"type": "boolean"
},
"enableWeakerNetworkIsolation": {
"description": "macOS only: Allow access to com.apple.trustd.agent in the sandbox. Needed for Go-based CLI tools (gh, gcloud, terraform, etc.) to verify TLS certificates when using httpProxyPort with a MITM proxy and custom CA. **Reduces security** — opens a potential data exfiltration vector through the trustd service. Default: false",
"type": "boolean"
},
"excludedCommands": {
"type": "array",
"items": {
"type": "string"
}
},
"ripgrep": {
"description": "Custom ripgrep configuration for bundled ripgrep support",
"type": "object",
"properties": {
"command": {
"type": "string"
},
"args": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"command"
],
"additionalProperties": false
},
"bwrapPath": {
"description": "Linux/WSL only: Absolute path to the bwrap (bubblewrap) binary. Overrides auto-detection via PATH. Only honored from admin-controlled managed settings.",
"type": "string"
},
"socatPath": {
"description": "Linux/WSL only: Absolute path to the socat binary used for the sandbox network proxy. Overrides auto-detection via PATH. Only honored from admin-controlled managed settings.",
"type": "string"
}
},
"additionalProperties": {}
},
"feedbackSurveyRate": {
"description": "Probability (0–1) that the session quality survey appears when eligible. 0.05 is a reasonable starting point.",
"type": "number",
"minimum": 0,
"maximum": 1
},
"spinnerTipsEnabled": {
"description": "Whether to show tips in the spinner",
"type": "boolean"
},
"spinnerVerbs": {
"description": "Customize spinner verbs. mode: \"append\" adds verbs to defaults, \"replace\" uses only your verbs.",
"type": "object",
"properties": {
"mode": {
"type": "string",
"enum": [
"append",
"replace"
]
},
"verbs": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"mode",
"verbs"
],
"additionalProperties": false
},
"spinnerTipsOverride": {
"description": "Override spinner tips. tips: array of tip strings. excludeDefault: if true, only show custom tips (default: false).",
"type": "object",
"properties": {
"excludeDefault": {
"type": "boolean"
},
"tips": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"tips"
],
"additionalProperties": false
},
"syntaxHighlightingDisabled": {
"description": "Whether to disable syntax highlighting in diffs",
"type": "boolean"
},
"terminalTitleFromRename": {
"description": "Whether /rename updates the terminal tab title (defaults to true). Set to false to keep auto-generated topic titles.",
"type": "boolean"
},
"alwaysThinkingEnabled": {
"description": "When false, thinking is disabled. When absent or true, thinking is enabled automatically for supported models.",
"type": "boolean"
},
"effortLevel": {
"description": "Persisted effort level for supported models.",
"type": "string",
"enum": [
"low",
"medium",
"high",
"xhigh"
]
},
"ultracode": {
"description": "Enable ultracode for the session: xhigh effort plus standing dynamic-workflow orchestration. Session-scoped — typically provided via --settings or the apply_flag_settings control request; interactive toggles never persist it. Requires workflows to be enabled and an xhigh-capable model.",
"type": "boolean"
},
"autoCompactWindow": {
"description": "Auto-compact window size",
"type": "integer",
"minimum": 100000,
"maximum": 1000000
},
"advisorModel": {
"description": "Advisor model for the server-side advisor tool.",
"type": "string"
},
"fastMode": {
"description": "When true, fast mode is enabled. When absent or false, fast mode is off.",
"type": "boolean"
},
"fastModePerSessionOptIn": {
"description": "When true, fast mode does not persist across sessions. Each session starts with fast mode off.",
"type": "boolean"
},
"promptSuggestionEnabled": {
"description": "When false, prompt suggestions are disabled. When absent or true, prompt suggestions are enabled.",
"type": "boolean"
},
"awaySummaryEnabled": {
"description": "@internal When false, the session recap (shown when you return after being away for 5+ minutes) is disabled. When absent or true, recap is enabled. Hidden from public SDK types until external launch.",
"type": "boolean"
},
"showClearContextOnPlanAccept": {
"description": "When true, the plan-approval dialog offers a \"clear context\" option. Defaults to false.",
"type": "boolean"
},
"agent": {
"description": "Name of an agent (built-in or custom) to use for the main thread. Applies the agent's system prompt, tool restrictions, and model.",
"type": "string"
},
"companyAnnouncements": {
"description": "Company announcements to display at startup (one will be randomly selected if multiple are provided)",
"type": "array",
"items": {
"type": "string"
}
},
"pluginConfigs": {
"description": "Per-plugin configuration including MCP server user configs, keyed by plugin ID (plugin@marketplace format)",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"properties": {
"mcpServers": {
"description": "User configuration values for MCP servers keyed by server name",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
}
},
"options": {
"description": "Non-sensitive option values from plugin manifest userConfig, keyed by option name. Sensitive values go to secure storage instead.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
}
},
"additionalProperties": false
}
},
"remote": {
"description": "Cloud session configuration",
"type": "object",
"properties": {
"defaultEnvironmentId": {
"description": "Default environment ID to use for cloud sessions",
"type": "string"
}
},
"additionalProperties": false
},
"autoUpdatesChannel": {
"description": "Release channel for auto-updates (latest or stable)",
"type": "string",
"enum": [
"latest",
"stable",
"rc"
]
},
"minimumVersion": {
"description": "Minimum version to stay on - prevents downgrades when switching to stable channel",
"type": "string"
},
"requiredMinimumVersion": {
"description": "Minimum Claude Code version required to start. If the running version is older, Claude Code exits at startup with instructions to update. Only enforced from managed (policy) settings.",
"type": "string"
},
"requiredMaximumVersion": {
"description": "Maximum Claude Code version allowed to start. If the running version is newer, Claude Code exits at startup with instructions to install an approved version. Only enforced from managed (policy) settings.",
"type": "string"
},
"plansDirectory": {
"description": "Custom directory for plan files, relative to project root. If not set, defaults to ~/.claude/plans/",
"type": "string"
},
"tui": {
"description": "Terminal UI renderer. \"fullscreen\" uses the flicker-free alt-screen renderer with virtualized scrollback (equivalent to CLAUDE_CODE_NO_FLICKER=1). \"default\" uses the classic main-screen renderer.",
"type": "string",
"enum": [
"default",
"fullscreen"
]
},
"voice": {
"description": "Voice mode settings (hold-to-talk / tap-to-toggle dictation)",
"type": "object",
"properties": {
"enabled": {
"type": "boolean"
},
"mode": {
"description": "'hold' (default): hold to talk. 'tap': tap to start, tap to stop+submit.",
"type": "string",
"enum": [
"hold",
"tap"
]
},
"autoSubmit": {
"description": "Submit the prompt when hold-to-talk is released (hold mode only)",
"type": "boolean"
}
},
"additionalProperties": false
},
"channelsEnabled": {
"description": "Managed-org opt-in for channel notifications (MCP servers with the claude/channel capability pushing inbound messages). claude.ai Teams/Enterprise: default off. Console: default on unless managed settings exist. Set true to allow; users then select servers via --channels.",
"type": "boolean"
},
"allowedChannelPlugins": {
"description": "Managed-org allowlist of channel plugins. When set, replaces the default Anthropic allowlist — admins decide which plugins may push inbound messages. Undefined falls back to the default. Requires channelsEnabled: true.",
"type": "array",
"items": {
"type": "object",
"properties": {
"marketplace": {
"type": "string"
},
"plugin": {
"type": "string"
}
},
"required": [
"marketplace",
"plugin"
],
"additionalProperties": false
}
},
"prefersReducedMotion": {
"description": "Reduce or disable animations for accessibility (spinner shimmer, flash effects, etc.)",
"type": "boolean"
},
"doneMeansMerged": {
"description": "@internal When true, Claude keeps working until the PR is ready for you to merge, a cron/Monitor is armed to resume later, or it hands you a self-contained next step.",
"type": "boolean"
},
"totalTokensReminder": {
"description": "@internal Emit a <total_tokens>N tokens left</total_tokens> block in the system prompt and after each tool result. 'infinite' uses the literal value Infinite, 'fixed' uses 5000000, 'countdown' uses the live remaining context-window tokens. Defaults to off. Env var CLAUDE_CODE_TOTAL_TOKENS_REMINDER overrides.",
"type": "string",
"enum": [
"off",
"infinite",
"fixed",
"countdown"
]
},
"autoMemoryEnabled": {
"description": "Enable auto-memory for this project. When false, Claude will not read from or write to the auto-memory directory.",
"type": "boolean"
},
"autoMemoryDirectory": {
"description": "Custom directory path for auto-memory storage. Supports ~/ prefix for home directory expansion. Ignored if set in projectSettings (checked-in .claude/settings.json) for security. When unset, defaults to ~/.claude/projects/<sanitized-cwd>/memory/.",
"type": "string"
},
"autoDreamEnabled": {
"description": "Enable background memory consolidation (auto-dream). When set, overrides the server-side default.",
"type": "boolean"
},
"showThinkingSummaries": {
"description": "Request API-side thinking summaries and show them in the conversation and in the transcript view (ctrl+o). Set explicitly to override the default for your install.",
"type": "boolean"
},
"skipDangerousModePermissionPrompt": {
"description": "Whether the user has accepted the bypass permissions mode dialog",
"type": "boolean"
},
"skipWorkflowUsageWarning": {
"description": "@internal Whether the user has accepted the multi-agent workflow usage warning. Until set, auto permission mode prompts before running a workflow.",
"type": "boolean"
},
"disableAutoMode": {
"description": "Disable auto mode",
"type": "string",
"enum": [
"disable"
]
},
"sshConfigs": {
"description": "SSH connection configurations for remote environments. Typically set in managed settings by enterprise administrators to pre-configure SSH connections for team members.",
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"description": "Unique identifier for this SSH config. Used to match configs across settings sources.",
"type": "string"
},
"name": {
"description": "Display name for the SSH connection",
"type": "string"
},
"sshHost": {
"description": "SSH host in format \"user@hostname\" or \"hostname\", or a host alias from ~/.ssh/config",
"type": "string"
},
"sshPort": {
"description": "SSH port (default: 22)",
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"sshIdentityFile": {
"description": "Path to SSH identity file (private key)",
"type": "string"
},
"startDirectory": {
"description": "Default working directory on the remote host. Supports tilde expansion (e.g. ~/projects). If not specified, defaults to the remote user home directory. Can be overridden by the [dir] positional argument in `claude ssh <config> [dir]`.",
"type": "string"
}
},
"required": [
"id",
"name",
"sshHost"
],
"additionalProperties": false
}
},
"claudeMd": {
"description": "CLAUDE.md-style instructions injected as organization-managed memory. Only honored from managed/policy settings.",
"type": "string"
},
"claudeMdExcludes": {
"description": "Glob patterns or absolute paths of CLAUDE.md files to exclude from loading. Patterns are matched against absolute file paths using picomatch. Only applies to User, Project, and Local memory types (Managed/policy files cannot be excluded). Examples: \"/home/user/monorepo/CLAUDE.md\", \"**/code/CLAUDE.md\", \"**/some-dir/.claude/rules/**\"",
"type": "array",
"items": {
"type": "string"
}
},
"pluginTrustMessage": {
"description": "Custom message to append to the plugin trust warning shown before installation. Only read from policy settings (managed-settings.json / MDM). Useful for enterprise administrators to add organization-specific context (e.g., \"All plugins from our internal marketplace are vetted and approved.\").",
"type": "string"
},
"theme": {
"description": "Color theme for the UI",
"anyOf": [
{
"type": "string",
"enum": [
"auto",
"dark",
"light",
"light-daltonized",
"dark-daltonized",
"light-ansi",
"dark-ansi"
]
},
{}
]
},
"editorMode": {
"description": "Key binding mode for the prompt input",
"type": "string",
"enum": [
"normal",
"vim"
]
},
"verbose": {
"description": "Show full tool output instead of truncated summaries",
"type": "boolean"
},
"preferredNotifChannel": {
"description": "Preferred OS notification channel",
"type": "string",
"enum": [
"auto",
"iterm2",
"iterm2_with_bell",
"terminal_bell",
"kitty",
"ghostty",
"notifications_disabled"
]
},
"autoCompactEnabled": {
"description": "Automatically compact conversation when context fills",
"type": "boolean"
},
"precomputeCompactionEnabled": {
"description": "@internal Precompute the compaction summary in the background before it is needed. Only applies when auto-compact is on.",
"type": "boolean"
},
"switchModelsOnFlag": {
"description": "When safety measures flag a message, automatically switch to a different model to keep chatting. When off, your session will pause instead.",
"type": "boolean"
},
"autoScrollEnabled": {
"description": "Auto-scroll the conversation view to bottom (fullscreen mode only)",
"type": "boolean"
},
"wheelScrollAccelerationEnabled": {
"description": "Ramp mouse-wheel scroll speed during fast scrolls (fullscreen mode only)",
"type": "boolean"
},
"fileCheckpointingEnabled": {
"description": "Snapshot files before edits so /rewind can restore them",
"type": "boolean"
},
"showTurnDuration": {
"description": "Show \"Cooked for Nm Ns\" after each assistant turn",
"type": "boolean"
},
"showMessageTimestamps": {
"description": "Stamp each assistant message with its arrival time",
"type": "boolean"
},
"terminalProgressBarEnabled": {
"description": "Emit OSC 9;4 progress sequences during long operations",
"type": "boolean"
},
"todoFeatureEnabled": {
"description": "Enable the todo / task tracking panel",
"type": "boolean"
},
"teammateMode": {
"description": "How spawned teammates execute (tmux, in-process, auto)",
"type": "string",
"enum": [
"auto",
"tmux",
"in-process"
]
},
"remoteControlAtStartup": {
"description": "Start Remote Control bridge automatically each session",
"type": "boolean"
},
"isolatePeerMachines": {
"description": "Require explicit approval before SendMessage can reach a peer session on another machine via Remote Control",
"type": "boolean"
},
"daemonColdStart": {
"description": "When no background service is running: 'transient' spawns one for this login session; 'ask' offers to install it persistently",
"type": "string",
"enum": [
"transient",
"ask"
]
},
"autoUploadSessions": {
"description": "Mirror local sessions to claude.ai as view-only (no remote control)",
"type": "boolean"
},
"inputNeededNotifEnabled": {
"description": "Push to mobile when a permission prompt or question is waiting",
"type": "boolean"
},
"agentPushNotifEnabled": {
"description": "Allow Claude to push proactive mobile notifications",
"type": "boolean"
},
"skipAutoPermissionPrompt": {
"description": "Whether the user has accepted the auto mode opt-in dialog",
"type": "boolean"
},
"useAutoModeDuringPlan": {
"description": "Whether plan mode uses auto mode semantics when auto mode is available (default: true)",
"type": "boolean"
},
"autoMode": {
"description": "Auto mode classifier prompt customization",
"type": "object",
"properties": {
"allow": {
"description": "Rules for the auto mode classifier allow section. Include the literal string \"$defaults\" to inherit the built-in rules at that position.",
"type": "array",
"items": {
"type": "string"
}
},
"soft_deny": {
"description": "Rules for the auto mode classifier SOFT BLOCK section — destructive/irreversible actions that user intent can clear. Include the literal string \"$defaults\" to inherit the built-in rules at that position.",
"type": "array",
"items": {
"type": "string"
}
},
"hard_deny": {
"description": "Rules for the auto mode classifier HARD BLOCK section — security boundaries that user intent does NOT clear. Include the literal string \"$defaults\" to inherit the built-in rules at that position.",
"type": "array",
"items": {
"type": "string"
}
},
"environment": {
"description": "Entries for the auto mode classifier environment section. Include the literal string \"$defaults\" to inherit the built-in entries at that position.",
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"disableDeepLinkRegistration": {
"description": "Prevent claude-cli:// protocol handler registration with the OS",
"type": "string",
"enum": [
"disable"
]
},
"voiceEnabled": {
"description": "Enable voice mode (hold-to-talk dictation)",
"type": "boolean"
},
"defaultView": {
"description": "Default transcript view: chat (SendUserMessage checkpoints only) or transcript (full)",
"type": "string",
"enum": [
"chat",
"transcript"
]
}
},
"additionalProperties": {}
}
Version History
- a7d0a26 Current 2026-08-29 04:39


