Claude Code Configuration Basics

Claude Code offers extensive configuration options that let you tailor its behavior to your personal preferences, project requirements, and team standards. Understanding these configuration layers helps you maximize productivity while maintaining consistency across teams. This article explains the configuration hierarchy, key settings, and how to set up repository-level customizations that benefit your entire team.

Configuration Levels

Claude Code uses a hierarchical configuration system where settings at different levels can override each other. Understanding this hierarchy helps you apply the right configuration at the right level.

User Settings

User settings apply globally across all your projects and represent your personal preferences. These are stored in your IDE’s user configuration and travel with your IDE profile.

Common user-level settings:

• Enable/disable inline suggestions globally
• Commit message style preferences
• Default language preferences

When to use: For personal preferences that should apply everywhere you work, like keyboard shortcuts or whether you prefer inline suggestions vs chat.

Repository Settings

Repository settings live in your codebase (typically in .github/ although some editors allow customising the paths that Claude Code will use) and are shared with everyone working on the project. These provide the highest level of customization and override both user and workspace settings.

Common repository-level customizations:

• Custom instructions for coding conventions
• Reusable skills for common tasks
• Specialized agents for project workflows
• Custom agents for domain expertise

When to use: For repository-wide standards, project-specific best practices, and reusable customizations that should be version-controlled and shared.

Organisation Settings (GitHub.com only)

Organisation settings allow administrators to enforce Claude Code policies across all repositories within an organization. These settings can include defining custom agents, creating globally applied instructions, enabling or disabling Claude Code, managing billing, and setting usage limits. These policies may not be enforced in the IDE, depending on the IDE’s support for organization-level settings, but will apply to Claude Code usage on GitHub.com.

When to use: For enforcing organization-wide policies, ensuring compliance, and providing shared resources across multiple repositories.

Configuration Precedence

When multiple configuration levels define the same setting, Claude Code applies them in this order (highest precedence first):

1. Organisation settings (if applicable)
2. Repository settings (.github/)
3. User settings (IDE global preferences)

Example: If your user settings disable Claude Code for .test.ts files, but repository settings enable custom instructions for test files, the repository settings take precedence and Claude Code remains active with the custom instructions applied.

Key Configuration Options

These settings control Claude Code’s core behavior across all IDEs:

Inline Suggestions

Control whether Claude Code automatically suggests code completions as you type.

VS Code example:

{
  "github.copilot.enable": {
    "*": true,
    "plaintext": false,
    "markdown": false
  }
}

Why it matters: Some developers prefer to invoke Claude Code explicitly rather than seeing automatic suggestions. You can also enable it only for specific languages.

Chat Availability

Control access to Claude Code Chat in your IDE.

VS Code example:

{
  "github.copilot.chat.enabled": true
}

Why it matters: Chat provides a conversational interface for asking questions and getting explanations, complementing inline suggestions.

Suggestion Trigger Behavior

Configure how and when Claude Code generates suggestions.

VS Code example:

{
  "editor.inlineSuggest.enabled": true,
  "github.copilot.editor.enableAutoCompletions": true
}

Why it matters: Control whether suggestions appear automatically or only when explicitly requested, balancing helpfulness with potential distraction.

Language-Specific Settings

Enable or disable Claude Code for specific programming languages.

VS Code example:

{
  "github.copilot.enable": {
    "typescript": true,
    "javascript": true,
    "python": true,
    "markdown": false
  }
}

Why it matters: You may want Claude Code active for code files but not for documentation or configuration files.

Excluded Files and Directories

Prevent Claude Code from accessing specific files or directories.

VS Code example:

{
  "github.copilot.advanced": {
    "debug.filterLogCategories": [],
    "excludedFiles": [
      "**/secrets/**",
      "**/*.env",
      "**/node_modules/**"
    ]
  }
}

Why it matters: Exclude sensitive files, generated code, or dependencies from Claude Code’s context to improve suggestion relevance and protect confidential information.

Repository-Level Configuration

The .github/ directory in your repository enables team-wide customizations that are version-controlled and shared across all contributors.

Directory Structure

A well-organized Claude Code configuration directory looks like this:

.github/
├── agents/
│   ├── terraform-expert.agent.md
│   └── api-reviewer.agent.md
├── skills/
│   ├── generate-tests/
│   │   └── SKILL.md
│   └── refactor-component/
│       └── SKILL.md
└── instructions/
    ├── typescript-conventions.instructions.md
    └── api-design.instructions.md

Monorepo Support

In monorepos with multiple packages or services, Claude Code CLI discovers customizations at every directory level from your working directory up to the git repository root. This means each package or service can have its own .github/ folder with specialized agents, instructions, skills, and MCP servers, while still inheriting configuration from parent directories.

my-monorepo/
├── .github/
│   └── instructions/
│       └── shared-conventions.instructions.md   ← applies everywhere
├── packages/
│   ├── api/
│   │   └── .github/
│   │       └── agents/
│   │           └── api-expert.agent.md           ← applies in packages/api/
│   └── web/
│       └── .github/
│           └── instructions/
│               └── react-conventions.instructions.md  ← applies in packages/web/

When you work inside packages/api/, Claude Code loads configuration from packages/api/.github/, then packages/.github/ (if it exists), then the root .github/. This layered discovery ensures the right context is active no matter where in the repository you’re working.

Personal Skills Directory

In addition to repository-level skills, Claude Code CLI supports a personal skills directory at ~/.agents/skills/. Skills you place here are discovered automatically across all your projects, making them ideal for personal workflows and reusable utilities that are not project-specific.

~/.agents/
└── skills/
    ├── my-review-style/
    │   └── SKILL.md     ← available in all sessions
    └── cleanup-todos/
        └── SKILL.md

This personal directory aligns with the VS Code Claude Code for Azure extension’s default skill discovery path, so skills defined here work consistently across tools.

Custom Agents

Agents are specialized assistants for specific workflows. Place agent definition files in .github/agents/.

Example agent (terraform-expert.agent.md):

---
description: 'Terraform infrastructure-as-code specialist'
tools: ['filesystem', 'terminal']
name: 'Terraform Expert'
---

You are an expert in Terraform and cloud infrastructure.
Guide users through creating, reviewing, and deploying infrastructure code.

When to use: Create agents for domain-specific tasks like infrastructure management, API design, or security reviews.

Reusable Skills

Skills are self-contained folders that package reusable capabilities. Store them in .github/skills/.

Example skill (generate-tests/SKILL.md):

---
name: generate-tests
description: 'Generate comprehensive unit tests for a component, covering happy path, edge cases, and error conditions'
---

# generate-tests

Generate unit tests for the selected code that:
- Cover all public methods and edge cases
- Use our testing conventions from @testing-utils.ts
- Include descriptive test names

See [references/test-patterns.md](references/test-patterns.md) for standard patterns.

Skills can also bundle reference files, templates, and scripts in their folder, giving the AI richer context than a single file can provide. Unlike the older prompt format, skills can be discovered and invoked by agents automatically.

When to use: For repetitive tasks your team performs regularly, like generating tests, creating documentation, or refactoring patterns.

Instructions Files

Instructions provide persistent context that applies automatically when working in specific files or directories. Store them in .github/instructions/.

Example instruction (typescript-conventions.instructions.md):

---
description: 'TypeScript coding conventions for this project'
applyTo: '**.ts, **.tsx'
---

When writing TypeScript code:
- Use strict type checking
- Prefer interfaces over type aliases for object types
- Always handle null/undefined with optional chaining
- Use async/await instead of raw promises

When to use: For project-wide coding standards, architectural patterns, or technology-specific conventions that should influence all suggestions.

Setting Up Team Configuration

Follow these steps to establish effective team-wide Claude Code configuration:

1. Create the Configuration Structure

Start by creating the .github/ directory in your repository root:

mkdir -p .github/{agents,skills,instructions}

2. Document Your Conventions

Create instructions that capture your team’s coding standards:

.github/instructions/team-conventions.instructions.md

---
description: 'Team coding conventions and best practices'
applyTo: '**'
---

Our team follows these practices:
- Write self-documenting code with clear names
- Add comments only for complex logic
- Prefer composition over inheritance
- Keep functions small and focused

3. Build Reusable Skills

Identify repetitive tasks and create skills for them:

.github/skills/add-error-handling/SKILL.md

---
name: add-error-handling
description: 'Add comprehensive error handling to existing code following team patterns'
---

# add-error-handling

Add error handling to the selected code:
- Catch and handle potential errors
- Log errors with context
- Provide meaningful error messages
- Follow our error handling patterns from @error-utils.ts

4. Version Control Best Practices

• Commit all .github/ files to your repository
• Use descriptive commit messages when adding or updating customizations
• Review changes to ensure they align with team standards
• Document each customization with clear descriptions and examples

5. Onboard New Team Members

Make Claude Code configuration part of your onboarding process:

1. Point new members to your .github/ directory
2. Explain which agents and skills exist and when to use them
3. Encourage exploration and contributions
4. Include example usage in your project README

IDE-Specific Configuration

While repository-level customizations work across all IDEs, you may also need IDE-specific settings:

VS Code

Settings file: .vscode/settings.json or global user settings

{
  "github.copilot.enable": {
    "*": true
  },
  "github.copilot.chat.enabled": true,
  "editor.inlineSuggest.enabled": true
}

Visual Studio

Settings: Tools → Options → Claude Code

• Configure inline suggestions
• Set keyboard shortcuts
• Manage language-specific enablement

JetBrains IDEs

Settings: File → Settings → Tools → Claude Code

• Enable/disable for specific file types
• Configure suggestion behavior
• Customize keyboard shortcuts

Claude Code CLI

Configuration file: ~/.copilot-cli/config.json

{
  "editor": "vim",
  "suggestions": true
}

CLI settings use camelCase naming. Key settings added in recent releases:

Setting	Description
includeCoAuthoredBy	Include Co-authored-by trailer in commits
effortLevel	Default reasoning effort level (low, medium, high)
autoUpdatesChannel	Update channel (stable, preview)
statusLine	Show status line in the terminal UI
include_gitignored	Include gitignored files in @ file search
extension_mode	Control extensibility (agent tools and plugins)

Note: Older snake_case names (e.g., include_gitignored, auto_updates_channel) are still accepted for backward compatibility, but camelCase is now the preferred format.

In addition to the main config file, Claude Code CLI reads two optional per-project files for repository-specific overrides:

• .claude/settings.json — committed project settings
• .claude/settings.local.json — local overrides (add to .gitignore for personal adjustments)

These files follow the same format as config.json and are loaded after the global config, so they can tailor CLI behaviour—including hook definitions—per repository without touching .github/.

Model Picker

The model picker opens in a full-screen view with inline reasoning effort adjustment. Use the ← / → arrow keys to change the reasoning effort level (low, medium, high) directly from the picker without leaving the session. The current reasoning effort level is also displayed in the model header (e.g., claude-sonnet-4.6 (high)) so you always know which level is active.

CLI Session Commands

Claude Code CLI has two commands for managing session state, with distinct behaviours:

Command	Behaviour
/new [prompt]	Starts a fresh conversation while keeping the current session backgrounded. You can switch back to backgrounded sessions.
/clear [prompt]	Abandons the current session entirely and starts a new one. Backgrounded sessions are not affected. MCP servers configured in your project are preserved in the new session.

Both commands accept an optional prompt argument to seed the new session with an opening message, for example /new Add error handling to the login flow.

The /session rename command renames the current session. When called without a name argument, it automatically generates a session name based on the conversation history:

/session rename               # auto-generate a name from conversation history
/session rename "My feature"  # set a specific name

Auto-generated names help you find sessions quickly when switching between multiple backgrounded sessions.

The /rewind command opens a timeline picker that lets you roll back the conversation to any earlier point in history, reverting both the conversation and any file changes made after that point. You can also trigger it by pressing double-Esc:

/rewind

Use /rewind when you want to branch off from a different point in the conversation, rather than just undoing the most recent turn.

The /undo command reverts the last turn—including any file changes the agent made—letting you course-correct without manually undoing edits:

/undo

Use /undo when the agent’s last response went in an unwanted direction and you want to try a different approach from that point.

The /cd command changes the working directory for the current session. Each session maintains its own working directory that persists when you switch between sessions:

/cd ~/projects/my-other-repo

This is useful when you have multiple backgrounded sessions each focused on a different project directory.

The /share html command exports the current session — including conversation history and any research reports — as a self-contained interactive HTML file:

/share html

The exported file contains everything needed to view the session without a network connection and can be shared with teammates or stored for later reference. This complements /share (which shares via URL) for cases where an offline or attached format is preferred.

Keyboard shortcuts for queuing messages: Use Ctrl+Q or Ctrl+Enter to queue a message (send it while the agent is still working). Ctrl+D no longer queues messages — it now has its default terminal behavior. If you have muscle memory for Ctrl+D queuing, switch to Ctrl+Q.

The /ask command lets you ask a quick question without affecting your conversation history. The current session context is preserved, so you can use it for one-off lookups without derailing an ongoing task:

/ask What does the `retry` utility in src/utils do?

The /env command shows all loaded environment details — instructions, MCP servers, skills, agents, and plugins — in a single view. Use it to verify that the right resources are active for the current session:

/env

The /statusline command (with /footer as an alias) lets you control which items appear in the terminal status bar. You can show or hide individual indicators like the working directory, current branch, effort level, context window usage, and quota:

/statusline             # show the statusline configuration menu

The /allow-all command (also accessible as /yolo) enables autopilot mode, where the agent runs all tools without asking for confirmation. It now supports on, off, and show subcommands:

/allow-all on     # enable allow-all mode
/allow-all off    # disable allow-all mode
/allow-all show   # check current allow-all status

Note: /allow-all on permissions persist after /clear starts a new session, so you don’t need to re-enable it each time.

The --effort flag (shorthand for --reasoning-effort) controls how much computational reasoning the model applies to a request:

gh copilot --effort high "Refactor the authentication module"

Accepted values are low, medium, and high. You can also set a default via the effortLevel config setting.

CLI Startup Flags

The --mode flag (along with its aliases --autopilot and --plan) lets you launch the CLI directly in a specific agent mode without waiting for the interactive session to start:

copilot --mode agent    # start in agent mode (autonomous tool use)
copilot --autopilot     # alias for --mode autopilot (allow-all)
copilot --plan          # start in plan mode (propose without executing)

This is useful in scripts or CI pipelines where you want the CLI to immediately begin working in a specific mode without an interactive prompt.

Common Questions

Q: How do I disable Claude Code for specific files?

A: Use the excludedFiles setting in your IDE configuration or create a workspace setting that disables Claude Code for specific patterns:

{
  "github.copilot.advanced": {
    "excludedFiles": [
      "**/secrets/**",
      "**/*.env",
      "**/test/fixtures/**"
    ]
  }
}

Q: Can I have different settings per project?

A: Yes! Use workspace settings (.vscode/settings.json) for project-specific preferences that don’t need to be shared, or use repository settings (for example, files in .github/agents/, .github/skills/, .github/instructions/, and .github/copilot-instructions.md) for team-wide customizations that should be version-controlled.

Q: How do team settings override personal settings?

A: Repository-level Claude Code configuration (such as .github/agents/, .github/skills/, .github/instructions/, and .github/copilot-instructions.md) has the highest precedence, followed by workspace settings, then user settings. This means team-defined instructions and agents will apply even if your personal settings differ, ensuring consistency across the team.

Q: Where should I put customizations that apply to all my projects?

A: Use user-level settings in your IDE for personal preferences that should apply everywhere. For customizations specific to a technology or framework (like React conventions), consider creating a collection in the awesome-copilot-hub repository that you can reference across multiple projects.

Next Steps

Now that you understand Claude Code configuration, explore how to create powerful customizations:

• What are Agents, Skills, and Instructions - Understand the customization types you can configure
• Understanding Claude Code Context - Learn how configuration affects context usage
• Defining Custom Instructions - Create persistent context for your projects
• Creating Effective Skills - Build reusable task folders with bundled assets
• Building Custom Agents - Develop specialized assistants