May 4, 2026 — CLAUDE.md template updated. The CLAUDE.md template has been modernized with 3 new variants (CLAUDE-template-1.md, CLAUDE-template-2.md, CLAUDE-template-3.md) following official Anthropic best practices — including dual-memory architecture, progressive disclosure, and standalone behavioral rules. Existing users: use CLAUDE-migrate-to-new-template.md as an AI prompt to migrate your current CLAUDE.md to any of the new templates while preserving all your project-specific content. See Choosing a CLAUDE.md Template for details.

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

My Claude Code Setup

What This Repository Provides

Starter Settings for Claude Code projects with optimized configurations
Memory Bank System for context retention across chat sessions
Pre-configured Hooks, Skills, and Subagents for enhanced productivity
MCP Server Recommendations for extending Claude Code capabilities

Quick Navigation

What do you want to do?	Jump to
Install & get started	Getting Started
Set up persistent memory	Memory Bank System
Add plugins to Claude Code	Plugins
Connect external tools	MCP Servers
Run parallel AI sessions	Git Worktrees
Customize Claude's behavior	Customization
Use Z.AI for higher quotas	Z.AI Integration
Monitor costs and usage	Costs & Usage
Look up settings/config	Configuration Reference

Getting Started

Prerequisites

Requirement	Notes
Claude AI Account	Pro ($20/mo), Max ($100/mo), or Max ($200/mo)
Node.js 18+	Runtime environment
Git	Version control
ripgrep, fd, jq	Fast tools (macOS: `brew install ripgrep fd jq`)

Installation Options

Choose the approach that works best for you:

Option A: Clone Entire Repository (New Projects)

# 1. Clone this repository as your new project
git clone https://github.com/centminmod/my-claude-code-setup.git my-project
cd my-project

# 2. Remove template README files (create your own)
rm README.md README-v2.md README-v3.md README-v4.md

# 3. Reinitialize git for your own project (optional)
rm -rf .git
git init

# 4. Launch Claude Code and initialize
claude
# Then run: /init

Option B: Selective Copy (Existing Projects)

Copy only what you need into your existing project:

# Core files (recommended)
cp /path/to/my-claude-code-setup/CLAUDE.md your-project/
cp -r /path/to/my-claude-code-setup/.claude your-project/

# Or pick specific components:
cp -r /path/to/my-claude-code-setup/.claude/commands your-project/.claude/
cp -r /path/to/my-claude-code-setup/.claude/skills your-project/.claude/
cp -r /path/to/my-claude-code-setup/.claude/agents your-project/.claude/
cp -r /path/to/my-claude-code-setup/.claude/hooks your-project/.claude/

Option C: Download from GitHub

Browse the repository and download individual files:

CLAUDE.md - Memory bank main file (uses Template 3 format)
CLAUDE-template-1.md - Compact self-contained template
CLAUDE-template-2.md - Memory bank system template
CLAUDE-template-3.md - Progressive disclosure template
CLAUDE-migrate-to-new-template.md - Template migration guide
.claude/settings.json - Settings template
.claude/rules/core-rules.md - Behavioral rules (required by Template 3)
.claude/commands/ - Slash commands
.claude/skills/ - Skills
.claude/agents/ - Subagents

What Happens Next?

Claude Code analyzes your codebase
Memory bank files are populated based on your project
You're ready to start coding with persistent context!

Optional Enhancements

VS Code Integration: Install Claude Code Extension
GitHub Setup: Configure Git for VS Code (guide)
Dev Container: Use the isolated dev environment for YOLO mode
Platform Docs: Add CLAUDE-cloudflare.md for Cloudflare/ClerkOS or CLAUDE-convex.md for Convex

Learning Resources

Advent of Claude: 31 Days by Ado Kukic (Anthropic)
Claude Code with Opus 4.5 by Alex Finn
Claude Code Overview by Matt Maher

I want to set up the memory bank system

What is Memory Bank?

The Memory Bank System helps Claude Code remember context across chat sessions. Instead of starting fresh each time, Claude reads structured markdown files to understand your project's patterns, decisions, and current state.

Core Context Files

File	What it stores
`CLAUDE.md`	Main entry point with project overview and AI guidance
`CLAUDE-activeContext.md`	Current session state, goals, and progress
`CLAUDE-patterns.md`	Established code patterns and conventions
`CLAUDE-decisions.md`	Architecture decisions and rationale (ADRs)
`CLAUDE-troubleshooting.md`	Common issues and proven solutions
`CLAUDE-config-variables.md`	Configuration variables reference
`CLAUDE-temp.md`	Temporary scratch pad (only read when referenced)

Token-Free Notes

HTML comments () in CLAUDE.md are stripped from context at runtime and cost zero tokens. The templates use them for guidance notes — you can add your own without impacting Claude's context window.

Initial Setup

Copy template files from this repository to your project root
Run /init in Claude Code
Claude analyzes your codebase and populates the memory bank

Updating Memory Bank

After completing significant work:

update memory bank

Claude Code will update all relevant CLAUDE-*.md files with your latest changes.

Example Output

> update memory bank

∴ Thinking…
  I'll update the memory bank files to reflect the v0.1.6 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
  - CLAUDE-decisions.md - Added ADR-017 & ADR-018
  - CLAUDE-troubleshooting.md - Added 4 new issue/fix entries

  Test Results: All 29 tests passing

See also: Customization for creating custom subagents that sync memory bank with code

Choosing a CLAUDE.md Template

This repo provides 3 modernized templates following official Anthropic best practices:

Template	Lines	Best For
`CLAUDE-template-1.md`	~101	Quick starts — compact, self-contained, all rules inline
`CLAUDE-template-2.md`	~153	Existing memory bank users — full workflow, dual-memory comparison
`CLAUDE-template-3.md`	~105	Teams — progressive disclosure, rules externalized to `.claude/rules/`

All templates include dual-memory architecture and progressive disclosure. The current CLAUDE.md uses Template 3 format.

Already have a CLAUDE.md? Use CLAUDE-migrate-to-new-template.md as a prompt — Claude Code will migrate your existing content to your chosen template while preserving all project-specific information.

I want to extend Claude Code with plugins

Official Anthropic Marketplace

Browse plugins at the official marketplace.

# Install a plugin
/plugin install plugin-name@claude-plugins-official

# Update marketplace
/plugin marketplace update claude-plugins-official

Recommended Plugins

Plugin	What it does	Install
code-simplifier	Simplifies code for clarity and maintainability	`/plugin install code-simplifier`
frontend-design	Creates production-grade frontend interfaces	`/plugin install frontend-design@claude-code-plugins`
feature-dev	7-phase approach to building features	`/plugin install feature-dev@claude-code-plugins`
ralph-wiggum	Iterative AI loops for development	`/plugin install ralph-wiggum@claude-code-plugins`

Note: Ralph Wiggum has issues on some systems (#16398, #16389). Usage video

Third-Party Plugins

Safety Net - Catches destructive commands before execution:

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

Z.AI Usage Query - Query Z.AI usage statistics:

/plugin marketplace add zai/zai-coding-plugins
/plugin install glm-plan-usage@zai-coding-plugins

Cloudflare Skills - Cloudflare platform development (Workers, Agents SDK):

/plugin marketplace add cloudflare/skills

See also: MCP Servers for connecting external tools

I want to connect external tools (MCP)

What is MCP?

MCP (Model Context Protocol) servers extend Claude Code by connecting to external tools, documentation, and services.

Recommended MCP Servers

Server	What it does	Install
Context7	Look up docs for any library	`claude mcp add --transport http context7 https://mcp.context7.com/mcp --header "CONTEXT7_API_KEY: YOUR_KEY" -s user`
Cloudflare Docs	Cloudflare documentation	`claude mcp add --transport sse cf-docs https://docs.mcp.cloudflare.com/sse -s user`
Usage Metrics	Track Claude Code costs	`claude mcp add --transport stdio metrics -s user -- uv run --directory /path/to/mcp-server metrics-server`
Gemini CLI	Access Gemini models	`claude mcp add gemini-cli /path/to/.venv/bin/python /path/to/mcp_server.py -s user -e GEMINI_API_KEY='KEY'`
Notion	Notion workspace integration	See below

Installing 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 (On-Demand)

Due to ~17K token overhead, install only when needed:

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

Create .claude/mcp/chrome-devtools.json:

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

Verify Installation

claude mcp list
# context7: ✓ Connected
# cf-docs: ✓ Connected
# metrics: ✓ Connected

Example: Cost Tracking

The get_current_cost tool returns:

{
  "metric": "Total Cost Today",
  "formatted": "$27.15",
  "unit": "currencyUSD"
}

See also: Plugins for the official plugin system

I want to run parallel AI coding sessions

Why Git Worktrees?

Git worktrees let you run multiple Claude Code sessions with complete code isolation. Each worktree has its own working directory while sharing Git history.

Benefits:

Run parallel AI sessions simultaneously
Each worktree has independent file state
Changes won't interfere between sessions
Perfect for experimental features or YOLO mode

Setup Shell Functions

macOS / Linux - Add to ~/.bashrc or ~/.zshrc:

# 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
}

# 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'
}

Reload: source ~/.bashrc or source ~/.zshrc

Windows PowerShell

Add to PowerShell profile (notepad $PROFILE):

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
    }
}

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'
    }
}

Reload: . $PROFILE

Windows CMD Batch

Create clx.bat in a PATH directory:

@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

Create cx.bat similarly for Codex CLI.

Usage

# Named worktree
clx feature-auth
cx bugfix-123

# Auto-generated timestamp name
clx
cx

Managing Worktrees

git worktree list          # List all worktrees
git worktree remove ../name # Remove a worktree
git worktree prune         # Clean up stale references

Environment Setup

Each worktree needs its own dependencies:

Node.js: npm install or yarn
Python: pip install -r requirements.txt

The .worktreeinclude File

Specify which .gitignored files to copy to new worktrees:

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

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

Claude Desktop Worktree Location

Default: ~/.claude-worktrees
Configurable in Claude Desktop settings
Repository must be Git initialized

Local Ignores Without .gitignore

Use .git/info/exclude for local-only ignores:

.idea/
my-local-scripts/

File	Scope	Shared
`.gitignore`	Team	Yes
`.git/info/exclude`	Local	No
`~/.config/git/ignore`	Global	No

See also: Z.AI + Worktrees for combining Z.AI with worktrees

I want to customize Claude's behavior

Custom Slash Commands

`/anthropic` Commands

Command	What it does
`/apply-thinking-to`	Enhances prompts with Anthropic's extended thinking patterns
`/convert-to-todowrite-tasklist-prompt`	Converts prompts to parallel task execution (60-70% faster)
`/update-memory-bank`	Updates CLAUDE.md and memory bank files

`/ccusage` Commands

Command	What it does
`/ccusage-daily`	Comprehensive usage cost analysis with daily breakdowns

`/cleanup` Commands

Command	What it does
`/cleanup-context`	Memory bank optimization (15-25% token reduction)

`/documentation` Commands

Command	What it does
`/create-readme-section`	Generates README sections with professional formatting
`/create-release-note`	Creates dual release notes (customer-facing + technical)

`/security` Commands

Command	What it does
`/security-audit`	OWASP-based security audit
`/check-best-practices`	Language-specific best practices analysis
`/secure-prompts`	Detects prompt injection attacks

Test prompts available at .claude/commands/security/test-examples/

`/architecture` Commands

Command	What it does
`/explain-architecture-pattern`	Identifies and explains architectural patterns

`/promptengineering` Commands

Command	What it does
`/convert-to-test-driven-prompt`	Transforms requests into TDD-style prompts
`/batch-operations-prompt`	Optimizes for parallel file operations

`/refactor` Commands

Command	What it does
`/refactor-code`	Creates detailed refactoring plans with risk assessment

Custom Skills

Skills provide specialized capabilities. See official docs.

Skill	What it does
claude-code-guide (built-in)	Natively built-in subagent for Claude Code CLI features, hooks, MCP servers, settings, Agent SDK, and API usage
consult-zai	Dual-AI consultation comparing z.ai GLM 4.7 and code-searcher responses
consult-codex	Dual-AI consultation comparing Codex GPT-5.2 and code-searcher responses
ai-image-creator	Generate PNG images using AI (Gemini, FLUX.2, Riverflow, SeedDream, GPT-5, GPT-5.4 Image 2) with configurable aspect ratios and resolutions. Supports transparent backgrounds (`-t`), reference image editing (`-r`), image analysis/description (`--analyze`), cost tracking (`--costs`), prompt enhancement patterns, and composite banner generation for multi-size logo banners. Requires setup
session-metrics	Parse Claude Code JSONL logs into per-turn token/cost/cache breakdowns. Multi-format export (text/JSON/CSV/MD/HTML), 5-hour session blocks with 7/14/30-day counters, weekly roll-up with percentage deltas, session duration + burn rate, hour-of-day + weekday punchcard, and pluggable chart libraries via `--chart-lib {highcharts,uplot,chartjs,none}`. Instance-wide dashboard (`--all-projects`, v1.14.0+) aggregates every project under `~/.claude/projects/` with per-project HTML drilldowns. Stdlib-only Python, zero network at runtime. Also installable via `/plugin install session-metrics@centminmod`.

Custom Subagents

Subagents handle complex tasks autonomously with their own context window. See official docs.

Agent	What it does
memory-bank-synchronizer	Keeps memory bank in sync with codebase
code-searcher	Efficient codebase search with optional CoD mode (80% fewer tokens)
get-current-datetime	Accurate Brisbane timezone (GMT+10) timestamps
ux-design-expert	Comprehensive UX/UI guidance with Tailwind CSS & Highcharts
zai-cli	CLI wrapper for z.ai GLM 4.7 (used by consult-zai skill)
codex-cli	CLI wrapper for Codex GPT-5.2 (used by consult-codex skill)

Hooks

Hooks run custom commands before/after tool execution.

Included Hook: STOP notification using Terminal-Notifier for macOS desktop notifications. Setup: Terminal-Notifier

See also: Configuration Reference for all settings options

I want to use Z.AI for higher quotas

What is Z.AI?

Z.AI's GLM Coding Plan provides cost-effective access to high-performance GLM models optimized for coding, with significantly higher quotas than standard Claude plans.

10% Discount: Use invite code WWB8IFLROM

Pricing & Plans

Plan	Prompts/5hrs	Monthly Cost	vs Claude
Lite	~120	~$3	3× Claude Pro quota
Pro	~600	Higher	3× Claude Max 5x quota
Max	~2,400	Higher	3× Claude Max 20x quota

Each prompt allows 15–20 model calls = billions of tokens monthly at ~1% of API pricing.

Privacy

Data Location: Singapore
Privacy Guarantee: Z.AI does not store any content you provide
Privacy Policy

Prerequisites

Node.js 18+
Z.AI API key from dashboard
Official docs

Setup Options

Option 1: Automated (macOS/Linux only)

curl -O "https://cdn.bigmodel.cn/install/claude_code_zai_env.sh" && bash ./claude_code_zai_env.sh

Option 2: Manual - Edit ~/.claude/settings.json:

{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "your-zai-api-key",
    "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic",
    "API_TIMEOUT_MS": "3000000"
  }
}

Shell Function Launcher (Recommended)

Use Z.AI without affecting your existing Claude Code setup.

macOS / Linux - Add to ~/.bashrc or ~/.zshrc:

zai() {
    export ANTHROPIC_AUTH_TOKEN="your-zai-api-key"
    export ANTHROPIC_BASE_URL="https://api.z.ai/api/anthropic"
    export API_TIMEOUT_MS="3000000"
    claude "$@"
}

Windows PowerShell

function zai {
    $env:ANTHROPIC_AUTH_TOKEN = "your-zai-api-key"
    $env:ANTHROPIC_BASE_URL = "https://api.z.ai/api/anthropic"
    $env:API_TIMEOUT_MS = "3000000"
    claude $args
}

Windows CMD Batch

Create zai.bat:

@echo off
set ANTHROPIC_AUTH_TOKEN=your-zai-api-key
set ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic
set API_TIMEOUT_MS=3000000
claude %*

Model Mapping

Claude Model	GLM Model
Opus	GLM-4.7
Sonnet	GLM-4.7
Haiku	GLM-4.5-Air

Customize mappings (optional) by adding to your shell function:

export ANTHROPIC_DEFAULT_OPUS_MODEL="GLM-4.7"
export ANTHROPIC_DEFAULT_SONNET_MODEL="GLM-4.5"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="GLM-4.5-Air"

Windows PowerShell Custom Mapping

function zai {
    $env:ANTHROPIC_AUTH_TOKEN = "your-zai-api-key"
    $env:ANTHROPIC_BASE_URL = "https://api.z.ai/api/anthropic"
    $env:API_TIMEOUT_MS = "3000000"
    $env:ANTHROPIC_DEFAULT_OPUS_MODEL = "GLM-4.7"
    $env:ANTHROPIC_DEFAULT_SONNET_MODEL = "GLM-4.5"
    $env:ANTHROPIC_DEFAULT_HAIKU_MODEL = "GLM-4.5-Air"
    claude $args
}

Windows CMD Custom Mapping

@echo off
set ANTHROPIC_AUTH_TOKEN=your-zai-api-key
set ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic
set API_TIMEOUT_MS=3000000
set ANTHROPIC_DEFAULT_OPUS_MODEL=GLM-4.7
set ANTHROPIC_DEFAULT_SONNET_MODEL=GLM-4.5
set ANTHROPIC_DEFAULT_HAIKU_MODEL=GLM-4.5-Air
claude %*

Usage

zai                              # Launch Z.AI
zai --model sonnet               # Specific model
zai --model opus --permission-mode plan

Z.AI + Git Worktree Integration

Combine Z.AI with worktrees for isolated parallel sessions:

macOS / Linux:

zaix() {
    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

    export ANTHROPIC_AUTH_TOKEN="your-zai-api-key"
    export ANTHROPIC_BASE_URL="https://api.z.ai/api/anthropic"
    export API_TIMEOUT_MS="3000000"
    claude --model sonnet --permission-mode plan
}

Windows PowerShell Z.AI + Worktree

function zaix {
    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"
        $env:ANTHROPIC_AUTH_TOKEN = "your-zai-api-key"
        $env:ANTHROPIC_BASE_URL = "https://api.z.ai/api/anthropic"
        $env:API_TIMEOUT_MS = "3000000"
        claude --model sonnet --permission-mode plan
    }
}

Windows CMD Z.AI + Worktree

Create zaix.bat:

@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%"
    set ANTHROPIC_AUTH_TOKEN=your-zai-api-key
    set ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic
    set API_TIMEOUT_MS=3000000
    claude --model sonnet --permission-mode plan
)
endlocal

Usage:

zaix feature-auth  # Named worktree
zaix               # Auto-generated name

See also: Parallel Sessions for more worktree details

Claude Code GitHub Actions

Automate AI-powered workflows in your repository with @claude mentions.

Key capabilities:

Respond to @claude mentions in issues and pull requests
Create and modify code through pull requests
Follow project-specific guidelines from CLAUDE.md

Reference: Claude Code GitHub Actions Documentation

Z.AI Integration Example

Create .github/workflows/claude.yml:

name: Claude Code

on:
  issue_comment:
    types: [created]
  pull_request_review_comment:
    types: [created]
  issues:
    types: [opened, assigned]
  pull_request_review:
    types: [submitted]

jobs:
  claude:
    if: |
      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
    runs-on: ubuntu-latest
    permissions:
      contents: write
      pull-requests: write
      issues: write
      id-token: write
      actions: read
    steps:
      - name: Checkout repository
        uses: actions/checkout@v5
        with:
          fetch-depth: 1

      - name: Run Claude Code
        id: claude
        uses: anthropics/claude-code-action@v1
        env:
          ANTHROPIC_BASE_URL: https://api.z.ai/api/anthropic
          API_TIMEOUT_MS: 3000000
        with:
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          claude_args: |
            --model claude-opus
            --max-turns 100

Component	Purpose
ANTHROPIC_BASE_URL	Routes API calls through Z.AI endpoint
API_TIMEOUT_MS	Extended timeout (50 minutes)
claude_args	Uses `claude-opus` with up to 100 turns

Setup: Add ANTHROPIC_API_KEY secret in repository settings, create workflow file, then mention @claude in issues/PRs.

I want to monitor costs and usage

Claude Plan Rate Limits

From August 28, 2025, weekly limits apply (plus monthly 50x 5hr session limit):

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

Status Lines

Display real-time usage in Claude Code.

Add to ~/.claude/settings.json:

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

Create ~/.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')

# Extract percentage metrics
USED_PERCENTAGE=$(echo "$input" | jq -r '.context_window.used_percentage')
REMAINING_PERCENTAGE=$(echo "$input" | jq -r '.context_window.remaining_percentage')

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

# Generate progress bar for context usage
generate_progress_bar() {
    local percentage=$1
    local bar_width=20
    local filled=$(awk "BEGIN {printf \"%.0f\", ($percentage / 100) * $bar_width}")
    local empty=$((bar_width - filled))
    local bar=""
    for ((i=0; i<filled; i++)); do bar+="█"; done
    for ((i=0; i<empty; i++)); do bar+="░"; done
    echo "$bar"
}

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

# Generate progress bar
PROGRESS_BAR=$(generate_progress_bar "$USED_PERCENTAGE")

# Show git branch if in a git repo
GIT_BRANCH=""
if git -C "$CURRENT_DIR" rev-parse --git-dir > /dev/null 2>&1; then
    BRANCH=$(git -C "$CURRENT_DIR" branch --show-current 2>/dev/null)
    if [ -n "$BRANCH" ]; then
        # Worktree detection
        GIT_DIR=$(git -C "$CURRENT_DIR" rev-parse --git-dir 2>/dev/null)
        WORKTREE=""
        if [[ "$GIT_DIR" == *".git/worktrees/"* ]] || [[ -f "$GIT_DIR/gitdir" ]]; then
            WORKTREE=" 🌳"
        fi
        # Ahead/behind detection
        AHEAD_BEHIND=""
        UPSTREAM=$(git -C "$CURRENT_DIR" rev-parse --abbrev-ref '@{u}' 2>/dev/null)
        if [ -n "$UPSTREAM" ]; then
            AHEAD=$(git -C "$CURRENT_DIR" rev-list --count '@{u}..HEAD' 2>/dev/null || echo 0)
            BEHIND=$(git -C "$CURRENT_DIR" rev-list --count 'HEAD..@{u}' 2>/dev/null || echo 0)
            if [ "$AHEAD" -gt 0 ] && [ "$BEHIND" -gt 0 ]; then
                AHEAD_BEHIND=" ↕${AHEAD}/${BEHIND}"
            elif [ "$AHEAD" -gt 0 ]; then
                AHEAD_BEHIND=" ↑${AHEAD}"
            elif [ "$BEHIND" -gt 0 ]; then
                AHEAD_BEHIND=" ↓${BEHIND}"
            fi
        fi
        GIT_BRANCH=" | 🌿 $BRANCH${WORKTREE}${AHEAD_BEHIND}"
    fi
fi

echo "[$MODEL_DISPLAY] 📁 ${CURRENT_DIR##*/}${GIT_BRANCH}
Context: [$PROGRESS_BAR] ${USED_PERCENTAGE}%
Cost: \$${COST_USD} | +${LINES_ADDED} -${LINES_REMOVED} lines"

Cost Tracking MCP

Install the Usage Metrics MCP:

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

Cost Analysis Command

Use /ccusage-daily for detailed cost analysis with daily breakdowns, model statistics, and recommendations.

Optimization Tips

Use Z.AI for 3× higher quotas at lower cost
Use CoD mode in code-searcher for 80% token reduction
Use git worktrees for parallel sessions without duplicating quota
Monitor status lines to track real-time usage

See also: Z.AI for higher quota options

Configuration Reference

Settings Scopes

Scope	Location	Who it affects
Managed	System directories	All users (IT-controlled)
User	`~/.claude/settings.json`	You (all projects)
Project	`.claude/settings.json`	All collaborators
Local	`.claude/settings.local.json`	You (this project only)

Precedence: Enterprise > CLI args > Local > Project > User

settings.json Options

Key	What it does	Example
`apiKeyHelper`	Script to generate auth	`/bin/generate_key.sh`
`cleanupPeriodDays`	Days to keep transcripts	`20`
`env`	Environment variables	`{"FOO": "bar"}`
`includeCoAuthoredBy`	Add Claude byline to commits	`false`

Permission Settings

Key	What it does	Example
`allow`	Allowed tool rules	`["Bash(git diff:*)"]`
`deny`	Denied tool rules	`["WebFetch"]`
`additionalDirectories`	Extra working dirs	`["../docs/"]`
`defaultMode`	Default permission mode	`"acceptEdits"`

Environment Variables

Variable	Purpose
`ANTHROPIC_API_KEY`	API key for Claude SDK
`ANTHROPIC_AUTH_TOKEN`	Custom auth header
`ANTHROPIC_BASE_URL`	Custom API endpoint
`ANTHROPIC_MODEL`	Custom model name
`BASH_DEFAULT_TIMEOUT_MS`	Default bash timeout
`CLAUDE_CODE_MAX_OUTPUT_TOKENS`	Max output tokens
`CLAUDE_CODE_USE_BEDROCK`	Use Amazon Bedrock
`CLAUDE_CODE_USE_VERTEX`	Use Google Vertex AI
`DISABLE_AUTOUPDATER`	Disable updates
`DISABLE_TELEMETRY`	Opt out of telemetry
`MCP_TIMEOUT`	MCP startup timeout
`MCP_TOOL_TIMEOUT`	MCP tool timeout
`MAX_MCP_OUTPUT_TOKENS`	Max MCP tokens (default: 25000)

File Locations

File	macOS/Linux	Windows
User settings	`~/.claude/settings.json`	`%USERPROFILE%\.claude\settings.json`
Project settings	`.claude/settings.json`	`.claude\settings.json`
Local settings	`.claude/settings.local.json`	`.claude\settings.local.json`

Tools Available to Claude

Tool	What it does	Permission
Agent	Runs sub-agents	No
Bash	Shell commands	Yes
Edit	File edits	Yes
Glob	Find files by pattern	No
Grep	Search file contents	No
LS	List files	No
MultiEdit	Multiple atomic edits	Yes
NotebookEdit	Jupyter cell edits	Yes
NotebookRead	Read Jupyter notebooks	No
Read	Read files	No
TodoRead/TodoWrite	Task management	No
WebFetch	Fetch URLs	Yes
WebSearch	Web searches	Yes
Write	Create/overwrite files	Yes

Config Commands

claude config list              # List settings
claude config get <key>         # Get setting
claude config set <key> <value> # Set setting
claude config set -g <key> <value> # Global setting

Resources

Official Documentation

YouTube Guides

Claude Code with Opus 4.5 - Alex Finn
How To Master Claude Code (Anthropic's Official 7-Hour Course) - Anthropic Official
Claude Code Overview - Matt Maher
VS Code Beginner Guide
Ralph Wiggum Tutorial - Greg Isenberg & Ryan Carson

Other Resources

Advent of Claude: 31 Days - Ado Kukic
40+ Claude Code Tips
OpenClaw: Security, Deployment & Cost Guide - For using Claude LLM models with OpenClaw

FilesExpand file tree

README-v3.md

Latest commit

History

README-v3.md

File metadata and controls

My Claude Code Setup

What This Repository Provides

Quick Navigation

Getting Started

Prerequisites

Installation Options

Option A: Clone Entire Repository (New Projects)

Option B: Selective Copy (Existing Projects)

Option C: Download from GitHub

What Happens Next?

Optional Enhancements

Learning Resources

I want to set up the memory bank system

What is Memory Bank?

Core Context Files

Token-Free Notes

Initial Setup

Updating Memory Bank

Example Output

Choosing a CLAUDE.md Template

I want to extend Claude Code with plugins

Official Anthropic Marketplace

Recommended Plugins

Third-Party Plugins

I want to connect external tools (MCP)

What is MCP?

Recommended MCP Servers

Installing Notion MCP

Chrome DevTools MCP (On-Demand)

Verify Installation

Example: Cost Tracking

I want to run parallel AI coding sessions

Why Git Worktrees?

Setup Shell Functions

Usage

Managing Worktrees

Environment Setup

The .worktreeinclude File

Claude Desktop Worktree Location

Local Ignores Without .gitignore

I want to customize Claude's behavior

Custom Slash Commands

/anthropic Commands

/ccusage Commands

/cleanup Commands

/documentation Commands

/security Commands

/architecture Commands

/promptengineering Commands

/refactor Commands

Custom Skills

Custom Subagents

Hooks

I want to use Z.AI for higher quotas

What is Z.AI?

Pricing & Plans

Privacy

Prerequisites

Setup Options

Shell Function Launcher (Recommended)

Model Mapping

Usage

Z.AI + Git Worktree Integration

Claude Code GitHub Actions

I want to monitor costs and usage

Claude Plan Rate Limits

Status Lines

Cost Tracking MCP

Cost Analysis Command

Optimization Tips

Configuration Reference

Settings Scopes

settings.json Options

Permission Settings

`/anthropic` Commands

`/ccusage` Commands

`/cleanup` Commands

`/documentation` Commands

`/security` Commands

`/architecture` Commands

`/promptengineering` Commands

`/refactor` Commands