Central authority for Claude Code configuration and settings. Covers settings.json files (user, project, enterprise), available settings, permission settings, sandbox settings, settings precedence, plugin configuration, environment variables, and tools available to Claude. Assists with configuring Claude Code behavior, managing permissions, setting up enterprise policies, and troubleshooting configuration issues. Delegates 100% to docs-management skill for official documentation.
Manages Claude Code configuration through settings.json files, permissions, and environment variables. Queries official docs for specific settings when you ask about configuration, permissions, sandboxing, or troubleshooting.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install claude-code-observability@melodic-softwareThis skill is limited to using the following tools:
references/audit-framework.mdSTOP - Before providing ANY response about Claude Code configuration or settings:
- INVOKE
docs-managementskill- QUERY for the user's specific topic
- BASE all responses EXCLUSIVELY on official documentation loaded
Skipping this step results in outdated or incorrect information.
Before responding, verify:
If ANY checkbox is unchecked, STOP and invoke docs-management first.
Central authority for Claude Code configuration and settings. This skill uses 100% delegation to docs-management - it contains NO duplicated official documentation.
Architecture: Pure delegation with keyword registry. All official documentation is accessed via docs-management skill queries.
Keywords: settings, configuration, settings.json, environment variables, permissions, sandbox, enterprise settings, managed-settings.json, user settings, project settings, local settings, tools, hooks configuration, model configuration, plugin settings, precedence
Use this skill when:
Use these keywords when querying docs-management skill for official documentation:
| Topic | Keywords |
|---|---|
| Overview | "settings", "settings.json", "configuration files" |
| User Settings | "user settings", "~/.claude/settings.json" |
| Project Settings | ".claude/settings.json", "project settings" |
| Local Settings | "settings.local.json", "local settings" |
| Enterprise | "managed-settings.json", "enterprise managed policy" |
| Topic | Keywords |
|---|---|
| Settings Table | "available settings", "settings options" |
| Model Setting | "model setting", "model override" |
| Hooks Setting | "hooks setting", "disableAllHooks" |
| Output Style | "outputStyle setting", "output style config" |
| Status Line | "statusLine setting", "status line config" |
| API Key Helper | "apiKeyHelper", "custom script auth" |
| Topic | Keywords |
|---|---|
| Permission Settings | "permission settings", "allow deny ask rules" |
| Allow Rules | "permissions allow", "allow tool rules" |
| Deny Rules | "permissions deny", "deny tool rules", "excluding sensitive files" |
| Ask Rules | "permissions ask", "confirmation rules" |
| Default Mode | "defaultMode", "permission modes" |
| Topic | Keywords |
|---|---|
| Sandbox Settings | "sandbox settings", "bash sandboxing" |
| Sandbox Network | "sandbox network", "allowUnixSockets", "allowLocalBinding" |
| Excluded Commands | "excludedCommands", "sandbox exclusions" |
| Auto Allow | "autoAllowBashIfSandboxed", "auto-approve sandboxed" |
| Topic | Keywords |
|---|---|
| Settings Precedence | "settings precedence", "configuration hierarchy" |
| Override Order | "enterprise project user precedence", "settings override" |
| Topic | Keywords |
|---|---|
| Environment Variables | "environment variables", "ANTHROPIC_API_KEY" |
| Model Variables | "ANTHROPIC_MODEL", "model environment" |
| Proxy Variables | "HTTP_PROXY", "HTTPS_PROXY", "proxy configuration" |
| Telemetry Variables | "DISABLE_TELEMETRY", "telemetry settings" |
| Bedrock Variables | "CLAUDE_CODE_USE_BEDROCK", "bedrock environment" |
| Vertex Variables | "CLAUDE_CODE_USE_VERTEX", "vertex environment" |
| Topic | Keywords |
|---|---|
| Plugin Configuration | "plugin configuration", "enabledPlugins" |
| Marketplaces | "extraKnownMarketplaces", "plugin marketplaces config" |
| Topic | Keywords |
|---|---|
| Available Tools | "tools available to Claude", "tool table" |
| Tool Permissions | "tool permissions", "permission required tools" |
What do you want to do?
User asks: "How do I configure permissions?"
1. Invoke docs-management skill
2. Use keywords: "permission settings", "allow deny rules"
3. Load official documentation
4. Provide guidance based EXCLUSIVELY on official docs
User asks: "I want enterprise settings with sandbox and restricted permissions"
1. Invoke docs-management skill with multiple queries:
- "managed-settings.json", "enterprise managed policy"
- "sandbox settings", "bash sandboxing"
- "permission settings", "deny rules"
2. Synthesize guidance from official documentation
User reports: "My settings aren't taking effect"
1. Invoke docs-management skill
2. Use keywords: "settings precedence", "configuration hierarchy"
3. Guide user through precedence rules from official docs
| Issue | Keywords for docs-management |
|---|---|
| Settings not applied | "settings precedence", "configuration hierarchy" |
| Permission denied | "permission settings", "deny rules" |
| Sandbox blocking commands | "sandbox settings", "excludedCommands" |
| Environment variable not working | "environment variables", specific variable name |
| Enterprise policy override | "managed-settings.json", "enterprise policy" |
| Plugin not loading | "plugin configuration", "enabledPlugins" |
| Tool not available | "tools available", "tool permissions" |
This repository has project-level settings in .claude/settings.json including:
When modifying this repository's settings, ensure changes align with the hook-management skill guidance for hook configurations.
This skill provides the validation criteria used by the settings-auditor agent for formal audits.
| Resource | Location | Purpose |
|---|---|---|
| Audit Framework | references/audit-framework.md | Query guides and scoring criteria |
| Category | Points | Key Criteria |
|---|---|---|
| JSON Validity | 20 | Valid syntax, well-formed |
| Schema Compliance | 25 | Only valid settings options |
| Permission Rules | 25 | Valid patterns, appropriate restrictions |
| Environment Config | 15 | Valid env vars, no secrets |
| Precedence Awareness | 15 | Correct scope usage |
Thresholds: 85+ = PASS, 70-84 = PASS WITH WARNINGS, <70 = FAIL
The settings-auditor agent (Haiku model) performs formal audits using this skill:
skills: settings-management/audit-settings commandWhen auditing settings that reference external technologies (scripts, packages, runtimes), the auditor MUST validate claims using MCP servers before flagging findings.
Technologies Requiring MCP Validation:
Validation Rule:
Never flag a technology usage as incorrect without first:
Stale Data Warning:
Official Documentation (via docs-management skill):
Repository-Specific:
.claude/settings.json.claude/hooks/Date: 2025-11-28 Model: claude-opus-4-5-20251101
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.