settings-deep-dive
# Claude Code Settings Deep Dive
What this skill does
# Claude Code Settings Deep Dive
Complete reference for every settings option, configuration key, and customization.
## Settings File Locations
| Location | Scope | Git Tracked |
|----------|-------|-------------|
| Managed (system-level) | Organization | `/Library/...` (macOS), `/etc/claude-code/` (Linux), `C:\Program Files\...` (Win) |
| `~/.claude/settings.json` | User (all projects) | N/A |
| `.claude/settings.json` | Project (shared) | Yes |
| `.claude/settings.local.json` | Project (personal) | No (gitignored) |
## Complete Settings Schema
```json
{
// === PERMISSIONS ===
"permissions": {
"allow": ["Tool(pattern)"],
"ask": ["Tool(pattern)"],
"deny": ["Tool(pattern)"],
"defaultMode": "default"
},
// === HOOKS ===
"hooks": {
"PreToolUse": [
{
"matcher": "ToolName",
"hooks": [
{
"type": "command",
"command": "bash script.sh",
"timeout": 10000
}
]
}
],
"PostToolUse": [],
"Notification": [],
"Stop": [],
"SubagentStop": []
},
// === ENVIRONMENT ===
"env": {
"VARIABLE_NAME": "value"
},
// === MODEL ===
"model": "claude-sonnet-4-6",
"smallFastModel": "claude-haiku-4-5-20251001",
// === BEHAVIOR ===
"autoMemory": true,
"autoCompact": true,
"language": "en",
"outputStyle": "Explanatory",
"spinnerVerbs": true,
"spinnerTipsEnabled": true,
"showTurnDuration": false,
"respectGitignore": true,
"cleanupPeriodDays": 30,
"fastModePerSessionOptIn": false,
"autoUpdatesChannel": "stable",
// === STATUS LINE ===
"statusLine": {
"enabled": true,
"showModel": true,
"showTokens": true,
"showCost": true
},
// === FILE SUGGESTIONS ===
"fileSuggestion": true,
// === CONTEXT WINDOW ===
"contextWindow": {
"compactThreshold": 0.8,
"warningThreshold": 0.9
},
// === MCP ===
"enableAllProjectMcpServers": false,
"enabledMcpjsonServers": [],
"allowedMcpServers": [],
// === SANDBOX ===
"sandbox": {
"enabled": true,
"filesystem": {
"allowWrite": ["//tmp/build"],
"denyRead": ["~/.aws/credentials"]
},
"network": {
"allowedDomains": ["github.com", "*.npmjs.org"]
}
},
// === HOOKS ===
"disableAllHooks": false,
"allowManagedHooksOnly": false,
"allowedHttpHookUrls": [],
"httpHookAllowedEnvVars": [],
// === AUTH & LOGIN ===
"forceLoginMethod": null,
// === PLUGINS ===
"pluginTrustMessage": "",
"extraKnownMarketplaces": [],
"strictKnownMarketplaces": false,
"blockedMarketplaces": [],
// === CLAUDE.md ===
"claudeMdExcludes": [],
// === MODELS ===
"availableModels": [],
// === ATTRIBUTION ===
"attribution": {
"commit": "Generated with AI\n\nCo-Authored-By: AI <[email protected]>",
"pr": ""
},
"includeCoAuthoredBy": true, // DEPRECATED: use attribution instead
// === CHANNELS (v2.1.80+) ===
"channelsEnabled": true, // Managed only - master switch for Team/Enterprise
"allowedChannelPlugins": [ // Managed only - restrict which channel plugins
{ "marketplace": "claude-plugins-official", "plugin": "telegram" }
],
// === AGENT TEAMS (experimental) ===
"teammateMode": "auto", // "auto" | "in-process" | "tmux"
// === WORKTREE ===
"worktree": {
"symlinkDirectories": ["node_modules", ".cache"],
"sparsePaths": ["packages/my-app", "shared/utils"]
},
// === AUTO MODE ===
"autoMode": {
"environment": ["Trusted repo: github.example.com/acme"],
"allow": ["Read any file in the project"],
"soft_deny": ["Never delete production databases"]
},
"disableAutoMode": "disable", // Set to "disable" to block auto mode; omit or remove key to allow
"useAutoModeDuringPlan": true,
// === EFFORT & VOICE ===
"effortLevel": "high", // "low" | "medium" | "high" (Opus 4.6, Sonnet 4.6)
"voiceEnabled": false,
"alwaysThinkingEnabled": false,
// === UI CUSTOMIZATION ===
"spinnerTipsOverride": {
"excludeDefault": true,
"tips": ["Use our internal tool X"]
},
"prefersReducedMotion": false,
"terminalProgressBarEnabled": true,
"showClearContextOnPlanAccept": false,
"plansDirectory": "~/.claude/plans",
// === MODELS ===
"availableModels": ["sonnet", "haiku", "opus"],
"modelOverrides": {
"claude-opus-4-6": "arn:aws:bedrock:us-east-1:..."
}
}
```
## Permissions Deep Dive
### Tool Names
```
Read — File reading
Write — File creation/overwriting
Edit — File modification
Glob — File pattern search
Grep — Content search
Bash — Shell command execution
WebFetch — Web content fetching
WebSearch — Web searching
Agent — Sub-agent spawning
TodoWrite — Task tracking
NotebookEdit — Jupyter notebook editing
AskUserQuestion — User interaction (always allowed)
Skill — Slash command invocation
ExitPlanMode — Plan mode completion
```
### Bash Pattern Matching
```json
{
"permissions": {
"allow": [
"Bash(npm test)", // Exact match
"Bash(npm run *)", // npm run anything
"Bash(npx *)", // Any npx command
"Bash(git status)", // Exact git status
"Bash(git diff *)", // git diff with any args
"Bash(git log *)", // git log with any args
"Bash(git add *)", // git add specific files
"Bash(git commit *)", // git commit
"Bash(ls *)", // Any ls command
"Bash(cat *)", // Any cat command
"Bash(head *)", // Any head command
"Bash(tail *)", // Any tail command
"Bash(wc *)", // Word count
"Bash(mkdir *)", // Create directories
"Bash(pwd)", // Print working directory
"Bash(echo *)", // Echo commands
"Bash(which *)", // Find executables
"Bash(python3 *)", // Python execution
"Bash(node *)" // Node execution
],
"deny": [
"Bash(rm -rf /)", // Block root delete
"Bash(rm -rf ~)", // Block home delete
"Bash(sudo *)", // Block sudo
"Bash(chmod 777 *)", // Block world-writable
"Bash(curl * | sh)", // Block pipe to shell
"Bash(curl * | bash)", // Block pipe to bash
"Bash(wget * | sh)", // Block wget pipe
"Bash(eval *)", // Block eval
"Bash(> /dev/*)", // Block device writes
"Bash(dd *)" // Block disk operations
]
}
}
```
### MCP Tool Patterns
```json
{
"permissions": {
"allow": [
"mcp__filesystem__read_file", // Specific tool
"mcp__filesystem__list_directory", // Specific tool
"mcp__postgres__*", // All postgres tools
"mcp__*" // All MCP tools
],
"deny": [
"mcp__filesystem__write_file", // Block writes
"mcp__filesystem__delete_file" // Block deletes
]
}
}
```
## Hook Configuration Deep Dive
### Matcher Patterns
| Pattern | Scope |
|---------|-------|
| `"Bash"` | Only Bash tool |
| `"Read"` | Only Read tool |
| `"Write"` | Only Write tool |
| `"Edit"` | Only Edit tool |
| `"Glob"` | Only Glob tool |
| `"Grep"` | Only Grep tool |
| `"WebFetch"` | Only WebFetch tool |
| `"Agent"` | Only Agent tool |
| `"mcp__*"` | All MCP tools |
| `"mcp__server__*"` | Specific MCP server |
| `"*"` | ALL tools |
| `""` | Default/all (for non-tool hooks) |
### Hook Script Interface
**Input (stdin):** JSON object
PreToolUse:
```json
{
"tool_name": "string",
"tool_input": { /* tool-specific */ },
"session_id": "string"
}
```
PostToolUse:
```json
{
"tool_name": "string",
"tool_input": { /* tool-sRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.