My Claude Code Project's Starter Settings

Threads - https://www.threads.com/@george_sl_liu
BlueSky - https://bsky.app/profile/georgesl.bsky.social

My Claude Code Project's Starter Settings

My Claude Code project's starter settings and Claude Code hooks and slash commands are provided in this repository for users to try out. The CLAUDE.md is setup as set of memory bank files to better retain context over many chat sessions. Be sure to read the official Claude Code docs first at https://docs.anthropic.com/en/docs/claude-code/overview and sign up for a paid Claude AI account to use Claude Code. You can pay for Claude Pro $20/month, Claude Max $100/month or Claude Max $200/month. The paid Claude tier plans will include varying quotas for usage and rate limits outlined here.

Copy the files in this Github repo to your project directory (where you intended codebase will be).
Modify the template files and CLAUDE.mdto your liking. .claude/settings.jsonneeds to install Terminal-Notifier for macOS https://github.com/centminmod/terminal-notifier-setup. If you're not using macOS, you can remove.claude/settings.json`.
After launching Claude Code for the first time within your project directory, run /init so that Claude Code analyses your code base and then populates your memory bank system files as per CLAUDE.md` instructions.
Optional step highly recommended: Install Visual Studio Code (beginners YouTube video guide and here) and Claude Code VSC Extension.
Optional step highly recommended: Sign up for Github.com account and install Git for Visual Studio Code. Checkout YouTube guides here and here.
CLAUDE.md updated to instruct models to use faster tools so for macOS: brew install ripgrep fd jq
Optional step to setup Claude Code, Codex GPT-5, Gemini CLI, OpenCode, Vercel CLI, Cloudflare Wrangler, Amazon AWS CLI, all in a single isolated Visual Studio Code dev container running Debian 12. Allowing you to run YOLO modes for Claude Code with dangerously_skip_permissions enabled and Codex CLI with sandbox_mode = danger-full-access etc.
Claude Code via Claude Desktop apps use Git Worktrees. You may need to create a .worktreeinclude file as outlined here.
If you use Cloudflare and ClerkOS platforms in your apps, you can keep either CLAUDE-cloudflare.md or CLAUDE-cloudflare-mini.md supplementary reference docs and update CLAUDE.md referencing either file to help AI understand Cloudflare and ClerkOS platforum documentation and products. Edit documentation templates as needed i.e. if you do not use ClerkOS platform, you can remove those sections.
If you use Convex database in your apps, you can use CLAUDE-convex.md supplementary reference docs for building Next.js and React apps with Convex backend deployed on Cloudflare Pages.
Useful read Advent of Claude: 31 Days of Claude Code by Ado Kukic from Anthropic.
Useful Claude Code with Claude Opus 4.5 YouTube video by Alex Finn and Claude Code YouTube video by Matt Maher.

CLAUDE.md Memory Bank system

CLAUDE.md uses a memory bank system of files for Claude Code to better retain context over many chat sessions. Example of Claude Code thinking output when I ask it to update memory bank after a successful task completion and git commit:

> update memory bank

∴ Thinking…

  The user wants me to update the memory bank files. I should update the relevant CLAUDE-*.md files to reflect the v0.1.6 changes and current state. Let me check
   which memory bank files exist and update them.

∴ Thinking…

  I need to continue updating the memory bank files. I'll update:
  1. CLAUDE-patterns.md - Add export path handling pattern (Pattern 22)
  2. CLAUDE-decisions.md - Add ADR-017 for Phoneme API migration and ADR-018 for export path handling
  3. CLAUDE-troubleshooting.md - Add new issues and solutions for v0.1.6

∴ Thinking…

  The memory bank files have been modified but not committed. The v0.1.6 release was already committed and tagged, but the memory bank documentation updates are
  still uncommitted. Let me provide a summary of the completed work and offer to commit these documentation changes.

⏺ Summary: v0.1.6 Release Complete ✅

  Memory Bank Updates Complete:
  - CLAUDE-activeContext.md - v0.1.6 session context
  - CLAUDE-patterns.md - Added patterns 22-24 (Export Path, Format Detection, API Migration)
  - CLAUDE-decisions.md - Added ADR-017 & ADR-018
  - CLAUDE-troubleshooting.md - Added 4 new issue/fix entries

  v0.1.6 Fixes Applied:
  1. Export to absolute paths (e.g., --export /tmp/test.wav)
  2. Format detection from filename extension (prevents .mp3.wav)
  3. Phoneme API migrated to /dev/phonemize
  4. Test scripts updated for --export "" syntax

  Test Results: All 29 tests passing

  The memory bank documentation updates are ready to commit. Would you like me to commit them

MCP Servers

I also install the following MCP servers (install commands):

Claude Code Plugin Marketplace

Browser and install Claude Code plugins from official marketplace https://code.claude.com/docs/en/discover-plugins.

/plugin install plugin-name@claude-plugins-official

Install frontend design plugin.

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics.

/plugin install frontend-design@claude-code-plugins

Install feature dev plugin.

The Feature Development Plugin provides a systematic 7-phase approach to building new features. Instead of jumping straight into code, it guides you through understanding the codebase, asking clarifying questions, designing architecture, and ensuring quality—resulting in better-designed features that integrate seamlessly with your existing code.

/plugin install feature-dev@claude-code-plugins

Install Ralph Wiggum plugin. Details https://paddo.dev/blog/ralph-wiggum-autonomous-loops/. Update: currently seems broken on some systems.

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.

/plugin install ralph-wiggum@claude-code-plugins

Claude Code 3rd Party Marketplaces

Claude Code Safety Net plugin https://github.com/kenryu42/claude-code-safety-net to prevent destructive commands being run by Claude Code i.e. https://www.reddit.com/r/ClaudeAI/comments/1pgxckk/claude_cli_deleted_my_entire_home_directory_wiped/

A Claude Code plugin that acts as a safety net, catching destructive git and filesystem commands before they execute.

/plugin marketplace add kenryu42/cc-marketplace
/plugin install safety-net@cc-marketplace

Claude Code Statuslines

~/.claude/statuslines/statusline.sh configured in ~/.claude/settings.json.

for ~/.claude/settings.json

  "statusLine": {
    "type": "command",
    "command": "~/.claude/statuslines/statusline.sh",
    "padding": 0
  },

for ~/.claude/statuslines/statusline.sh

#!/bin/bash
# Read JSON input from stdin
input=$(cat)

# Extract model and workspace values
MODEL_DISPLAY=$(echo "$input" | jq -r '.model.display_name')
CURRENT_DIR=$(echo "$input" | jq -r '.workspace.current_dir')

# Extract context window metrics
INPUT_TOKENS=$(echo "$input" | jq -r '.context_window.total_input_tokens')
OUTPUT_TOKENS=$(echo "$input" | jq -r '.context_window.total_output_tokens')
CONTEXT_SIZE=$(echo "$input" | jq -r '.context_window.context_window_size')

# Extract cost metrics
COST_USD=$(echo "$input" | jq -r '.cost.total_cost_usd')
LINES_ADDED=$(echo "$input" | jq -r '.cost.total_lines_added')
LINES_REMOVED=$(echo "$input" | jq -r '.cost.total_lines_removed')

# Format tokens as Xk
format_tokens() {
    local num="$1"
    if [ "$num" -ge 1000 ]; then
        echo "$((num / 1000))k"
    else
        echo "$num"
    fi
}

# Calculate total
TOTAL_TOKENS=$((INPUT_TOKENS + OUTPUT_TOKENS))

# Show git branch if in a git repo
GIT_BRANCH=""
if git rev-parse --git-dir > /dev/null 2>&1; then
    BRANCH=$(git branch --show-current 2>/dev/null)
    if [ -n "$BRANCH" ]; then
        GIT_BRANCH=" | 🌿 $BRANCH"
    fi
fi

echo "[$MODEL_DISPLAY] 📁 ${CURRENT_DIR##*/}${GIT_BRANCH}
Tokens: $(format_tokens "$TOTAL_TOKENS") (in:$(format_tokens "$INPUT_TOKENS")+out:$(format_tokens "$OUTPUT_TOKENS")) | Ctx:$(format_tokens "$CONTEXT_SIZE")
Cost: \$${COST_USD} | +${LINES_ADDED} -${LINES_REMOVED} lines"

Git Worktrees for AI Coding Sessions

Git worktrees allow you to run parallel Claude Code and Codex CLI sessions with complete code isolation. Each worktree has its own isolated working directory while sharing the same Git history and remote connections. This prevents AI instances from interfering with each other when working on multiple tasks simultaneously.

Benefits:

Run multiple AI coding sessions in parallel
Each worktree has independent file state
Changes in one worktree won't affect others
Ideal for experimental features or YOLO mode usage

Official Documentation: Run parallel Claude Code sessions with git worktrees

macOS / Linux (Bash/Zsh)

Add these functions to ~/.bashrc, ~/.zshrc, or ~/.bash_aliases:

# Codex CLI worktree launcher
cx() {
    local branch_name
    if [ -z "$1" ]; then
        branch_name="worktree-$(date +%Y%m%d-%H%M%S)"
    else
        branch_name="$1"
    fi
    git worktree add "../$branch_name" -b "$branch_name" && \
    cd "../$branch_name" || return 1
    codex -m gpt-5-codex --config model_reasoning_effort='xhigh'
}

# Claude Code worktree launcher
clx() {
    local branch_name
    if [ -z "$1" ]; then
        branch_name="worktree-$(date +%Y%m%d-%H%M%S)"
    else
        branch_name="$1"
    fi
    git worktree add "../$branch_name" -b "$branch_name" && \
    cd "../$branch_name" || return 1
    claude --model opusplan --permission-mode plan
}

After adding, reload your shell: source ~/.bashrc or source ~/.zshrc

Windows (PowerShell)

Add these functions to your PowerShell profile. Open it with notepad $PROFILE:

# Codex CLI worktree launcher
function cx {
    param([string]$BranchName)
    if (-not $BranchName) {
        $BranchName = "worktree-$(Get-Date -Format 'yyyyMMdd-HHmmss')"
    }
    git worktree add "../$BranchName" -b $BranchName
    if ($LASTEXITCODE -eq 0) {
        Set-Location "../$BranchName"
        codex -m gpt-5-codex --config model_reasoning_effort='xhigh'
    }
}

# Claude Code worktree launcher
function clx {
    param([string]$BranchName)
    if (-not $BranchName) {
        $BranchName = "worktree-$(Get-Date -Format 'yyyyMMdd-HHmmss')"
    }
    git worktree add "../$BranchName" -b $BranchName
    if ($LASTEXITCODE -eq 0) {
        Set-Location "../$BranchName"
        claude --model opusplan --permission-mode plan
    }
}

After adding, reload PowerShell or run: . $PROFILE

Windows (CMD Batch Files)

Create these batch files in a directory in your PATH (e.g., C:\Users\YourName\bin\):

cx.bat - Codex CLI launcher:

@echo off
setlocal enabledelayedexpansion
if "%~1"=="" (
    for /f "tokens=2 delims==" %%I in ('wmic os get localdatetime /value') do set datetime=%%I
    set branch_name=worktree-!datetime:~0,8!-!datetime:~8,6!
) else (
    set branch_name=%~1
)
git worktree add "../%branch_name%" -b "%branch_name%"
if %errorlevel% equ 0 (
    cd "../%branch_name%"
    codex -m gpt-5-codex --config model_reasoning_effort='xhigh'
)
endlocal

clx.bat - Claude Code launcher:

@echo off
setlocal enabledelayedexpansion
if "%~1"=="" (
    for /f "tokens=2 delims==" %%I in ('wmic os get localdatetime /value') do set datetime=%%I
    set branch_name=worktree-!datetime:~0,8!-!datetime:~8,6!
) else (
    set branch_name=%~1
)
git worktree add "../%branch_name%" -b "%branch_name%"
if %errorlevel% equ 0 (
    cd "../%branch_name%"
    claude --model opusplan --permission-mode plan
)
endlocal

Usage

# Create worktree with custom name
clx feature-auth
cx bugfix-123

# Create worktree with auto-generated timestamp name
clx
cx

Worktree Management

# List all worktrees
git worktree list

# Remove a worktree when done
git worktree remove ../worktree-name

# Clean up stale worktree references
git worktree prune

Environment Setup

Each new worktree needs its own development environment:

JavaScript/Node.js: Run npm install or yarn
Python: Create virtual environment or run pip install -r requirements.txt
Other languages: Follow your project's standard setup process

The `.worktreeinclude` File

When Claude Code creates a worktree, files ignored via .gitignore aren't automatically available. The .worktreeinclude file specifies which ignored files should be copied to new worktrees.

How It Works:

Uses .gitignore-style patterns
Only files matched by both .worktreeinclude AND .gitignore are copied
This prevents accidentally duplicating tracked files

Create a .worktreeinclude file in your repository root:

# Environment files
.env
.env.local
.env.*

# Claude Code local settings
**/.claude/settings.local.json

Common Use Cases:

.env files with API keys and secrets
.env.local for local development overrides
.claude/settings.local.json for personal Claude Code settings

Claude Desktop Worktree Location

When using Claude Code via the Claude Desktop app:

Default worktree location: ~/.claude-worktrees
Configurable through Claude Desktop app settings
Repository must be Git initialized for worktree sessions to work

Official Documentation: Claude Code on Desktop

Local Ignores Without `.gitignore`

To ignore files locally without modifying the shared .gitignore, use .git/info/exclude:

# Edit the local exclude file
nano .git/info/exclude
# or
code .git/info/exclude

Add patterns using the same syntax as .gitignore:

# Local IDE settings
.idea/
*.swp

# Personal scripts
my-local-scripts/

# Local test files
test-local.sh

Key Differences:

File	Scope	Committed to Git
`.gitignore`	Shared with team	Yes
`.git/info/exclude`	Local only	No
`~/.config/git/ignore`	Global (all repos)	No

When to Use .git/info/exclude:

Personal IDE or editor files
Local testing scripts
Machine-specific configurations
Files you don't want to clutter the shared .gitignore

Note: Files in .git/info/exclude work with .worktreeinclude the same way as .gitignore - patterns must appear in both files for copying to worktrees.

Claude Code Skills

Claude Code now supports Agent Skills.

claude-docs-consultant

Purpose: A specialized Claude skill which will selectively consult the official Claude Code documentation from docs.claude.com using selective fetching. This skill will invoke only when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront

Claude Code Hooks

The Claude Code hook is for STOP which uses Terminal-Notifier to show macOS desktop notifications whenever Claude Code stops and finishes it's response https://github.com/centminmod/terminal-notifier-setup.

Claude Code Subagents

Claude Code subagents are specialized tools designed to handle complex, multi-step tasks autonomously. A key benefit of Claude Code subagents is that uses its own context window separate from the main conversation and can use it's own custom prompt. Learn more about subagents in the official documentation.

memory-bank-synchronizer

Purpose: Synchronizes memory bank documentation with actual codebase state, ensuring architectural patterns in memory files match implementation reality
Location: .claude/agents/memory-bank-synchronizer.md
Key Responsibilities:
- Pattern documentation synchronization
- Architecture decision updates
- Technical specification alignment
- Implementation status tracking
- Code example freshness validation
- Cross-reference validation
Usage: Proactively maintains consistency between CLAUDE-*.md files and source code to ensure documentation remains accurate and trustworthy

code-searcher

Purpose: A specialized agent for efficiently searching the codebase, finding relevant files, and summarizing code. Supports both standard detailed analysis and optional Chain of Draft (CoD) ultra-concise mode when explicitly requested for 80% token reduction
Location: .claude/agents/code-searcher.md
Key Responsibilities:
- Efficient codebase navigation and search
- Function and class location
- Code pattern identification
- Bug source location assistance
- Feature implementation analysis
- Integration point discovery
- Chain of Draft (CoD) mode for ultra-concise reasoning with minimal tokens
Usage: Use when you need to locate specific functions, classes, or logic within the codebase. Request "use CoD", "chain of draft", or "draft mode" for ultra-concise responses with ~80% fewer tokens
- Standard mode: "Find the payment processing code" → Full detailed analysis
- CoD mode: "Find the payment processing code using CoD" → "Payment→glob:payment→found:payment.service.ts:45"

get-current-datetime

Purpose: Simple DateTime utility for accurate Brisbane, Australia (GMT+10) timezone values. Executes bash date commands and returns only the raw output without formatting or explanations
Location: .claude/agents/get-current-datetime.md
Key Responsibilities:
- Execute TZ='Australia/Brisbane' date commands
- Provide accurate Brisbane timezone timestamps
- Support multiple format options (default, filename, readable, ISO)
- Eliminate timezone confusion and month errors
- Return raw command output without additional processing
Usage: Use when creating files with timestamps, generating reports with dates, or needing accurate Australian timezone values for any purpose

ux-design-expert

Purpose: Comprehensive UX/UI design guidance specialist combining user experience optimization, premium interface design, and scalable design systems with Tailwind CSS and Highcharts data visualization
Location: .claude/agents/ux-design-expert.md
Key Responsibilities:
- UX flow optimization and friction reduction
- Premium UI design with sophisticated visual hierarchies
- Scalable design systems architecture using Tailwind CSS
- Data visualization strategy with Highcharts implementations
- Accessibility compliance and performance optimization
- Component library design with atomic methodology
Usage: Use for dashboard UX improvements, premium component libraries, complex user flow optimization, design system creation, or any comprehensive UX/UI design guidance needs

Claude Code Slash Commands

`/anthropic` Commands

/apply-thinking-to - Expert prompt engineering specialist that applies Anthropic's extended thinking patterns to enhance prompts with advanced reasoning frameworks
- Transforms prompts using progressive reasoning structure (open-ended → systematic)
- Applies sequential analytical frameworks and systematic verification with test cases
- Includes constraint optimization, bias detection, and extended thinking budget management
- Usage: /apply-thinking-to @/path/to/prompt-file.md
/convert-to-todowrite-tasklist-prompt - Converts complex, context-heavy prompts into efficient TodoWrite tasklist-based methods with parallel subagent execution
- Achieves 60-70% speed improvements through parallel processing
- Transforms verbose workflows into specialized task delegation
- Prevents context overflow through strategic file selection (max 5 files per task)
- Usage: /convert-to-todowrite-tasklist-prompt @/path/to/original-slash-command.md
/update-memory-bank - Simple command to update CLAUDE.md and memory bank files
- Usage: /update-memory-bank

`/ccusage` Commands

/ccusage-daily - Generates comprehensive Claude Code usage cost analysis and statistics
- Runs ccusage daily command and parses output into structured markdown
- Provides executive summary with total costs, peak usage days, and cache efficiency
- Creates detailed tables showing daily costs, token usage, and model statistics
- Includes usage insights, recommendations, and cost management analysis
- Usage: /ccusage-daily

`/cleanup` Commands

/cleanup-context - Memory bank optimization specialist for reducing token usage in documentation
- Removes duplicate content and eliminates obsolete files
- Consolidates overlapping documentation while preserving essential information
- Implements archive strategies for historical documentation
- Achieves 15-25% token reduction through systematic optimization
- Usage: /cleanup-context

`/documentation` Commands

/create-readme-section - Generate specific sections for README files with professional formatting
- Creates well-structured sections like Installation, Usage, API Reference, Contributing, etc.
- Follows markdown best practices with proper headings, code blocks, and formatting
- Analyzes project context to provide relevant content
- Matches existing README style and tone
- Usage: /create-readme-section "Create an installation section for my Python project"
/create-release-note - Generate comprehensive release documentation from recent commits with dual output formats
- Interactive workflow with two modes: by commit count or by commit hash range (last 24/48/72 hours)
- Produces customer-facing release note (value-focused, no technical jargon) and technical engineering note (SHA references, file paths)
- Comprehensive commit analysis with grouping by subsystem and traceability to specific SHAs
- Supports direct arguments for quick generation or interactive selection for precise control
- Usage: /create-release-note (interactive), /create-release-note 20 (last 20 commits), or select commit hash after viewing recent commits

`/security` Commands

/security-audit - Perform comprehensive security audit of the codebase
- Identifies potential vulnerabilities using OWASP guidelines
- Checks authentication, input validation, data protection, and API security
- Categorizes issues by severity (Critical, High, Medium, Low)
- Provides specific remediation steps with code examples
- Usage: /security-audit
/check-best-practices - Analyze code against language-specific best practices
- Detects languages and frameworks to apply relevant standards
- Checks naming conventions, code organization, error handling, and performance
- Provides actionable feedback with before/after code examples
- Prioritizes impactful improvements over nitpicks
- Usage: /check-best-practices
/secure-prompts - Enterprise-grade security analyzer for detecting prompt injection attacks and malicious instructions
- Detects prompt injection attacks, hidden content, and malicious instructions using advanced AI-specific detection patterns
- Provides comprehensive threat analysis with automated timestamped report generation
- Saves reports to reports/secure-prompts/ directory for audit trails
- Analyzes both file content and direct text input for security threats
- Usage: /secure-prompts @suspicious_file.txt or /secure-prompts "content to analyze"
- Example prompt injection prompts at .claude/commands/security/test-examples that you can run /secure-prompts against.
- Example generated report for /secure-prompts .claude/commands/security/test-examples/test-encoding-attacks.md here

`/architecture` Commands

/explain-architecture-pattern - Identify and explain architectural patterns in the codebase
- Analyzes project structure and identifies design patterns
- Explains rationale behind architectural decisions
- Provides visual representations with diagrams
- Shows concrete implementation examples
- Usage: /explain-architecture-pattern

`/promptengineering` Commands

/convert-to-test-driven-prompt - Transform requests into Test-Driven Development style prompts
- Defines explicit test cases with Given/When/Then format
- Includes success criteria and edge cases
- Structures prompts for red-green-refactor cycle
- Creates measurable, specific test scenarios
- Usage: /convert-to-test-driven-prompt "Add user authentication feature"
/batch-operations-prompt - Optimize prompts for multiple file operations and parallel processing
- Identifies parallelizable tasks to maximize efficiency
- Groups operations by conflict potential
- Integrates with TodoWrite for task management
- Includes validation steps between batch operations
- Usage: /batch-operations-prompt "Update all API calls to use new auth header"

`/refactor` Commands

/refactor-code - Analysis-only refactoring specialist that creates comprehensive refactoring plans without modifying code
- Analyzes code complexity, test coverage, and architectural patterns
- Identifies safe extraction points and refactoring opportunities
- Creates detailed step-by-step refactoring plans with risk assessment
- Generates timestamped reports in reports/refactor/ directory
- Focuses on safety, incremental progress, and maintainability
- Usage: /refactor-code

Claude Code Plan Weekly Rate Limits

If you are using Claude monthly subscription plans for Claude Code, new weekly rate limits will apply from August 28, 2025 in addition to max 50x 5hr session limits per month:

Plan	Sonnet 4 (hrs/week)	Opus 4 (hrs/week)
Pro	40–80	–
Max ($100 /mo)	140–280	15–35
Max ($200 /mo)	240–480	24–40

Claude Code settings

Configure Claude Code with global and project-level settings, and environment variables.

Claude Code offers a variety of settings to configure its behavior to meet your needs. You can configure Claude Code by running the /config command when using the interactive REPL.

Settings files

The settings.json file is our official mechanism for configuring Claude Code through hierarchical settings:

User settings are defined in ~/.claude/settings.json and apply to all projects.
Project settings are saved in your project directory:
- .claude/settings.json for settings that are checked into source control and shared with your team
- .claude/settings.local.json for settings that are not checked in, useful for personal preferences and experimentation. Claude Code will configure git to ignore .claude/settings.local.json when it is created.

Available settings

settings.json supports a number of options:

Key	Description	Example
`apiKeyHelper`	Custom script, to be executed in `/bin/sh`, to generate an auth value. This value will generally be sent as `X-Api-Key`, `Authorization: Bearer`, and `Proxy-Authorization: Bearer` headers for model requests	`/bin/generate_temp_api_key.sh`
`cleanupPeriodDays`	How long to locally retain chat transcripts (default: 30 days)	`20`
`env`	Environment variables that will be applied to every session	`{"FOO": "bar"}`
`includeCoAuthoredBy`	Whether to include the `co-authored-by Claude` byline in git commits and pull requests (default: `true`)	`false`
`permissions`	See table below for structure of permissions.

Permission settings

Keys	Description	Example
`allow`	Array of permission rules to allow tool use	`[ "Bash(git diff:*)" ]`
`deny`	Array of permission rules to deny tool use	`[ "WebFetch", "Bash(curl:*)" ]`
`additionalDirectories`	Additional working directories that Claude has access to	`[ "../docs/" ]`
`defaultMode`	Default permission mode when opening Claude Code	`"acceptEdits"`
`disableBypassPermissionsMode`	Set to `"disable"` to prevent `bypassPermissions` mode from being activated. See managed policy settings	`"disable"`

Settings precedence

Settings are applied in order of precedence:

Enterprise policies (see IAM documentation)
Command line arguments
Local project settings
Shared project settings
User settings

Environment variables

Claude Code supports the following environment variables to control its behavior:

All environment variables can also be configured in [`settings.json`](#available-settings). This is useful as a way to automatically set environment variables for each session, or to roll out a set of environment variables for your whole team or organization.

Variable	Purpose
`ANTHROPIC_API_KEY`	API key sent as `X-Api-Key` header, typically for the Claude SDK (for interactive usage, run `/login`)
`ANTHROPIC_AUTH_TOKEN`	Custom value for the `Authorization` and `Proxy-Authorization` headers (the value you set here will be prefixed with `Bearer` )
`ANTHROPIC_CUSTOM_HEADERS`	Custom headers you want to add to the request (in `Name: Value` format)
`ANTHROPIC_MODEL`	Name of custom model to use (see Model Configuration)
`ANTHROPIC_SMALL_FAST_MODEL`	Name of Haiku-class model for background tasks
`ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION`	Override AWS region for the small/fast model when using Bedrock
`BASH_DEFAULT_TIMEOUT_MS`	Default timeout for long-running bash commands
`BASH_MAX_TIMEOUT_MS`	Maximum timeout the model can set for long-running bash commands
`BASH_MAX_OUTPUT_LENGTH`	Maximum number of characters in bash outputs before they are middle-truncated
`CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR`	Return to the original working directory after each Bash command
`CLAUDE_CODE_API_KEY_HELPER_TTL_MS`	Interval in milliseconds at which credentials should be refreshed (when using `apiKeyHelper`)
`CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL`	Skip auto-installation of IDE extensions (defaults to false)
`CLAUDE_CODE_MAX_OUTPUT_TOKENS`	Set the maximum number of output tokens for most requests
`CLAUDE_CODE_USE_BEDROCK`	Use Bedrock
`CLAUDE_CODE_USE_VERTEX`	Use Vertex
`CLAUDE_CODE_SKIP_BEDROCK_AUTH`	Skip AWS authentication for Bedrock (e.g. when using an LLM gateway)
`CLAUDE_CODE_SKIP_VERTEX_AUTH`	Skip Google authentication for Vertex (e.g. when using an LLM gateway)
`CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`	Equivalent of setting `DISABLE_AUTOUPDATER`, `DISABLE_BUG_COMMAND`, `DISABLE_ERROR_REPORTING`, and `DISABLE_TELEMETRY`
`DISABLE_AUTOUPDATER`	Set to `1` to disable automatic updates. This takes precedence over the `autoUpdates` configuration setting.
`DISABLE_BUG_COMMAND`	Set to `1` to disable the `/bug` command
`DISABLE_COST_WARNINGS`	Set to `1` to disable cost warning messages
`DISABLE_ERROR_REPORTING`	Set to `1` to opt out of Sentry error reporting
`DISABLE_NON_ESSENTIAL_MODEL_CALLS`	Set to `1` to disable model calls for non-critical paths like flavor text
`DISABLE_TELEMETRY`	Set to `1` to opt out of Statsig telemetry (note that Statsig events do not include user data like code, file paths, or bash commands)
`HTTP_PROXY`	Specify HTTP proxy server for network connections
`HTTPS_PROXY`	Specify HTTPS proxy server for network connections
`MAX_THINKING_TOKENS`	Force a thinking for the model budget
`MCP_TIMEOUT`	Timeout in milliseconds for MCP server startup
`MCP_TOOL_TIMEOUT`	Timeout in milliseconds for MCP tool execution
`MAX_MCP_OUTPUT_TOKENS`	Maximum number of tokens allowed in MCP tool responses (default: 25000)
`VERTEX_REGION_CLAUDE_3_5_HAIKU`	Override region for Claude 3.5 Haiku when using Vertex AI
`VERTEX_REGION_CLAUDE_3_5_SONNET`	Override region for Claude 3.5 Sonnet when using Vertex AI
`VERTEX_REGION_CLAUDE_3_7_SONNET`	Override region for Claude 3.7 Sonnet when using Vertex AI
`VERTEX_REGION_CLAUDE_4_0_OPUS`	Override region for Claude 4.0 Opus when using Vertex AI
`VERTEX_REGION_CLAUDE_4_0_SONNET`	Override region for Claude 4.0 Sonnet when using Vertex AI

Configuration options

We are in the process of migrating global configuration to settings.json.

claude config will be deprecated in place of settings.json

To manage your configurations, use the following commands:

List settings: claude config list
See a setting: claude config get <key>
Change a setting: claude config set <key> <value>
Push to a setting (for lists): claude config add <key> <value>
Remove from a setting (for lists): claude config remove <key> <value>

By default config changes your project configuration. To manage your global configuration, use the --global (or -g) flag.

Global configuration

To set a global configuration, use claude config set -g <key> <value>:

Key	Description	Example
`autoUpdates`	Whether to enable automatic updates (default: `true`). When enabled, Claude Code automatically downloads and installs updates in the background. Updates are applied when you restart Claude Code.	`false`
`preferredNotifChannel`	Where you want to receive notifications (default: `iterm2`)	`iterm2`, `iterm2_with_bell`, `terminal_bell`, or `notifications_disabled`
`theme`	Color theme	`dark`, `light`, `light-daltonized`, or `dark-daltonized`
`verbose`	Whether to show full bash and command outputs (default: `false`)	`true`

Tools available to Claude

Claude Code has access to a set of powerful tools that help it understand and modify your codebase:

Tool	Description	Permission Required
Agent	Runs a sub-agent to handle complex, multi-step tasks	No
Bash	Executes shell commands in your environment	Yes
Edit	Makes targeted edits to specific files	Yes
Glob	Finds files based on pattern matching	No
Grep	Searches for patterns in file contents	No
LS	Lists files and directories	No
MultiEdit	Performs multiple edits on a single file atomically	Yes
NotebookEdit	Modifies Jupyter notebook cells	Yes
NotebookRead	Reads and displays Jupyter notebook contents	No
Read	Reads the contents of files	No
TodoRead	Reads the current session's task list	No
TodoWrite	Creates and manages structured task lists	No
WebFetch	Fetches content from a specified URL	Yes
WebSearch	Performs web searches with domain filtering	Yes
Write	Creates or overwrites files	Yes

Permission rules can be configured using /allowed-tools or in permission settings.

Extending tools with hooks

You can run custom commands before or after any tool executes using Claude Code hooks.

For example, you could automatically run a Python formatter after Claude modifies Python files, or prevent modifications to production configuration files by blocking Write operations to certain paths

Claude Code MCP Servers

Claude Code Usage Metrics MCP

claude mcp add --transport stdio metrics -s user -- uv run --directory /path/to/your/mcp-server metrics-server

claude mcp list
Checking MCP server health...

context7: https://mcp.context7.com/sse (SSE) - ✓ Connected
cf-docs: https://docs.mcp.cloudflare.com/sse (SSE) - ✓ Connected
metrics: uv run --directory /path/to/your/mcp-server metrics-server - ✓ Connected

MCP tool call get_current_cost. Returns today's total USD cost from Prometheus.

{
  "metric": "Total Cost Today",
  "value": 27.149809833783127,
  "formatted": "$27.1498",
  "unit": "currencyUSD"
}

Gemini CLI MCP Server

Gemini CLI MCP

claude mcp add gemini-cli /pato/to/.venv/bin/python /pato/to//mcp_server.py -s user -e GEMINI_API_KEY='GEMINI_API_KEY' -e OPENROUTER_API_KEY='OPENROUTER_API_KEY'

Cloudflare MCP Documentation

Cloudflare Documentation MCP

claude mcp add --transport sse cf-docs https://docs.mcp.cloudflare.com/sse -s user

Context 7 MCP Server

Context 7 MCP

with API key

claude mcp add --transport http context7 https://mcp.context7.com/mcp --header "CONTEXT7_API_KEY: YOUR_API_KEY" -s user

Notion MCP Server

Notion MCP

claude mcp add-json notionApi '{"type":"stdio","command":"npx","args":["-y","@notionhq/notion-mcp-server"],"env":{"OPENAPI_MCP_HEADERS":"{\"Authorization\": \"Bearer ntn_API_KEY\", \"Notion-Version\": \"2022-06-28\"}"}}' -s user

Chrome Devtools MCP sever

Chrome Devtools MCP

This MCP server can take up to 17K of Claude's context window so I only install it when project needs it via --mcp-config parameter when running Claude client:

claude --mcp-config .claude/mcp/chrome-devtools.json

Where .claude/mcp/chrome-devtools.json

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "chrome-devtools-mcp@latest"
      ]
    }
  }
}

Chrome Devtool MCP server takes up ~16,977 tokens across 26 MCP tools

     mcp__chrome-devtools__list_console_messages (chrome-devtools): 584 tokens
     mcp__chrome-devtools__emulate_cpu (chrome-devtools): 651 tokens
     mcp__chrome-devtools__emulate_network (chrome-devtools): 694 tokens
     mcp__chrome-devtools__click (chrome-devtools): 636 tokens
     mcp__chrome-devtools__drag (chrome-devtools): 638 tokens
     mcp__chrome-devtools__fill (chrome-devtools): 644 tokens
     mcp__chrome-devtools__fill_form (chrome-devtools): 676 tokens
     mcp__chrome-devtools__hover (chrome-devtools): 609 tokens
     mcp__chrome-devtools__upload_file (chrome-devtools): 651 tokens
     mcp__chrome-devtools__get_network_request (chrome-devtools): 618 tokens
     mcp__chrome-devtools__list_network_requests (chrome-devtools): 783 tokens
     mcp__chrome-devtools__close_page (chrome-devtools): 624 tokens
     mcp__chrome-devtools__handle_dialog (chrome-devtools): 645 tokens
     mcp__chrome-devtools__list_pages (chrome-devtools): 582 tokens
     mcp__chrome-devtools__navigate_page (chrome-devtools): 642 tokens
     mcp__chrome-devtools__navigate_page_history (chrome-devtools): 656 tokens
     mcp__chrome-devtools__new_page (chrome-devtools): 637 tokens
     mcp__chrome-devtools__resize_page (chrome-devtools): 629 tokens
     mcp__chrome-devtools__select_page (chrome-devtools): 619 tokens
     mcp__chrome-devtools__performance_analyze_insight (chrome-devtools): 649 tokens
     mcp__chrome-devtools__performance_start_trace (chrome-devtools): 689 tokens
     mcp__chrome-devtools__performance_stop_trace (chrome-devtools): 586 tokens
     mcp__chrome-devtools__take_screenshot (chrome-devtools): 803 tokens
     mcp__chrome-devtools__evaluate_script (chrome-devtools): 775 tokens
     mcp__chrome-devtools__take_snapshot (chrome-devtools): 614 tokens
     mcp__chrome-devtools__wait_for (chrome-devtools): 643 tokens

Name		Name	Last commit message	Last commit date
Latest commit History 91 Commits
.claude		.claude
reports/secure-prompts		reports/secure-prompts
.clinerules		.clinerules
.dockerignore		.dockerignore
.worktreeinclude		.worktreeinclude
AGENTS.md		AGENTS.md
CLAUDE-cloudflare-mini.md		CLAUDE-cloudflare-mini.md
CLAUDE-cloudflare.md		CLAUDE-cloudflare.md
CLAUDE-convex.md		CLAUDE-convex.md
CLAUDE.md		CLAUDE.md
GEMINI.md		GEMINI.md
LICENSE		LICENSE
README.md		README.md

License

centminmod/my-claude-code-setup

Folders and files

Latest commit

History

Repository files navigation

My Claude Code Project's Starter Settings

CLAUDE.md Memory Bank system

MCP Servers

Claude Code Plugin Marketplace

Claude Code 3rd Party Marketplaces

Claude Code Statuslines

Git Worktrees for AI Coding Sessions

macOS / Linux (Bash/Zsh)

Windows (PowerShell)

Windows (CMD Batch Files)

Usage

Worktree Management

Environment Setup

The .worktreeinclude File

Claude Desktop Worktree Location

Local Ignores Without .gitignore

Claude Code Skills

claude-docs-consultant

Claude Code Hooks

Claude Code Subagents

memory-bank-synchronizer

code-searcher

get-current-datetime

ux-design-expert

Claude Code Slash Commands

/anthropic Commands

/ccusage Commands

/cleanup Commands

/documentation Commands

/security Commands

/architecture Commands

/promptengineering Commands

/refactor Commands

Claude Code Plan Weekly Rate Limits

Claude Code settings

Settings files

Available settings

Permission settings

Settings precedence

Environment variables

Configuration options

Global configuration

Tools available to Claude

Extending tools with hooks

Claude Code MCP Servers

Gemini CLI MCP Server

Cloudflare MCP Documentation

Context 7 MCP Server

Notion MCP Server

Chrome Devtools MCP sever

Star History

Stats

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Contributors 2

Uh oh!

The `.worktreeinclude` File

Local Ignores Without `.gitignore`

`/anthropic` Commands

`/ccusage` Commands

`/cleanup` Commands

`/documentation` Commands

`/security` Commands

`/architecture` Commands

`/promptengineering` Commands

`/refactor` Commands

Packages