Before installing CCS, make sure you're logged into Claude CLI with your subscription account:

claude /login

macOS / Linux / Windows

npm install -g @kaitranntt/ccs

All major package managers are supported:

# yarn
yarn global add @kaitranntt/ccs

# pnpm (70% less disk space)
pnpm add -g @kaitranntt/ccs

# bun (30x faster)
bun add -g @kaitranntt/ccs

macOS / Linux

curl -fsSL ccs.kaitran.ca/install | bash

Windows PowerShell

irm ccs.kaitran.ca/install | iex

💡 Performance Tip: Traditional installs bypass Node.js routing for faster startup, but I prioritize npm updates due to easier deployment automation.

CCS automatically creates configuration during installation (via npm postinstall script).

~/.ccs/config.json:

{
  "profiles": {
    "glm": "~/.ccs/glm.settings.json",
    "glmt": "~/.ccs/glmt.settings.json",
    "kimi": "~/.ccs/kimi.settings.json",
    "default": "~/.claude/settings.json"
  }
}

If Claude CLI is installed in a non-standard location (D drive, custom directory), set CCS_CLAUDE_PATH:

export CCS_CLAUDE_PATH="/path/to/claude"              # Unix
$env:CCS_CLAUDE_PATH = "D:\Tools\Claude\claude.exe"   # Windows

See Troubleshooting Guide for detailed setup instructions.

Windows users: Enable Developer Mode for true symlinks (better performance, instant sync):

1. Open Settings → Privacy & Security → For developers
2. Enable Developer Mode
3. Reinstall CCS: npm install -g @kaitranntt/ccs

Without Developer Mode: CCS automatically falls back to copying directories (works but no instant sync across profiles).

⚠️ Important: Before using GLM/GLMT or Kimi profiles, update API keys in settings files:

• GLM: Edit ~/.ccs/glm.settings.json and add your GLM API key
• GLMT: Edit ~/.ccs/glmt.settings.json and add your Z.AI API key (requires coding plan)
• Kimi: Edit ~/.ccs/kimi.settings.json and add your Kimi API key

# Default Claude subscription
ccs "Plan microservices architecture"

# Switch to GLM (cost-optimized)
ccs glm "Create REST API"

# GLM with thinking mode
ccs glmt "Solve algorithmic problem"

# Kimi for coding
ccs kimi "Write integration tests"

Developers face multiple subscription scenarios daily:

1. Account Separation: Company Claude account vs personal Claude → you must manually switch contexts to keep work and personal separate
2. Rate Limits Hit: Claude stops mid-project → you manually edit ~/.claude/settings.json
3. Cost Management: 2-3 Pro subscriptions ($20/month each) vs Claude Max at 5x cost ($100/month) → Pro tier is the practical ceiling for most developers
4. Model Choice: Different tasks benefit from different model strengths → manual switching

Manual context switching breaks your workflow. CCS manages it seamlessly.

Settings-based: GLM, GLMT, Kimi, default

• Uses --settings flag pointing to config files
• GLMT: Embedded proxy for thinking mode support

Account-based: work, personal, team

• Uses CLAUDE_CONFIG_DIR for isolated instances
• Create with ccs auth create <profile>

Commands and skills symlinked from ~/.ccs/shared/ - no duplication across profiles.

~/.ccs/
├── shared/                  # Shared across all profiles
│   ├── agents/
│   ├── commands/
│   └── skills/
├── instances/               # Profile-specific data
│   └── work/
│       ├── agents@ → shared/agents/
│       ├── commands@ → shared/commands/
│       ├── skills@ → shared/skills/
│       ├── settings.json    # API keys, credentials
│       └── sessions/        # Conversation history
│       └── ...

Shared: commands/, skills/, agents/ Profile-specific: settings.json, sessions/, todolists/, logs/

[i] Windows: Copies dirs if symlinks unavailable (enable Developer Mode for true symlinks)

[!] Important: GLMT requires npm installation (npm install -g @kaitranntt/ccs). Not available in native shell versions (requires Node.js HTTP server).

GLMT now fully supports MCP tools and function calling:

• Bidirectional Transformation: Anthropic tools ↔ OpenAI function calling
• MCP Integration: MCP tools execute correctly (no XML tag output)
• Streaming Tool Calls: Real-time tool calls with input_json deltas
• Backward Compatible: Works seamlessly with existing thinking support
• No Configuration: Tool support works automatically

GLMT now supports real-time streaming with incremental reasoning content delivery.

• Default: Streaming enabled (TTFB <500ms)
• Disable: Set CCS_GLMT_STREAMING=disabled for buffered mode
• Force: Set CCS_GLMT_STREAMING=force to override client preferences
• Thinking parameter: Claude CLI thinking parameter support
  • Respects thinking.type and budget_tokens
  • Precedence: CLI parameter > message tags > default

Confirmed working: Z.AI (1498 reasoning chunks tested, tool calls verified)

1. CCS spawns embedded HTTP proxy on localhost
2. Proxy converts Anthropic format → OpenAI format (streaming or buffered)
3. Transforms Anthropic tools → OpenAI function calling format
4. Forwards to Z.AI with reasoning parameters and tools
5. Converts reasoning_content → thinking blocks (incremental or complete)
6. Converts OpenAI tool_calls → Anthropic tool_use blocks
7. Thinking and tool calls appear in Claude Code UI in real-time

• <Thinking:On|Off> - Enable/disable reasoning blocks (default: On)
• <Effort:Low|Medium|High> - Control reasoning depth (deprecated - Z.AI only supports binary thinking)

GLMT-specific:

• CCS_GLMT_FORCE_ENGLISH=true - Force English output (default: true)
• CCS_GLMT_THINKING_BUDGET=8192 - Control thinking on/off based on task type
  • 0 or "unlimited": Always enable thinking
  • 1-2048: Disable thinking (fast execution)
  • 2049-8192: Enable for reasoning tasks only (default)

  • 8192: Always enable thinking

• CCS_GLMT_STREAMING=disabled - Force buffered mode
• CCS_GLMT_STREAMING=force - Force streaming (override client)

General:

• CCS_DEBUG_LOG=1 - Enable debug file logging
• CCS_CLAUDE_PATH=/path/to/claude - Custom Claude CLI path

# Edit GLMT settings
nano ~/.ccs/glmt.settings.json

# Set Z.AI API key (requires coding plan)
{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "your-z-ai-api-key"
  }
}

DoS protection (v3.4):

• SSE buffer: 1MB max per event
• Content buffer: 10MB max per block (thinking/text)
• Content blocks: 100 max per message
• Request timeout: 120s (both streaming and buffered)

Enable verbose logging:

ccs glmt --verbose "your prompt"

Enable debug file logging:

export CCS_DEBUG_LOG=1
ccs glmt --verbose "your prompt"
# Logs: ~/.ccs/logs/

Check streaming mode:

# Disable streaming for debugging
CCS_GLMT_STREAMING=disabled ccs glmt "test"

Check reasoning content:

cat ~/.ccs/logs/*response-openai.json | jq '.choices[0].message.reasoning_content'

If absent: Z.AI API issue (verify key, account status) If present: Transformation issue (check response-anthropic.json)

ccs              # Claude subscription (default)
ccs glm          # GLM (no thinking)
ccs glmt         # GLM with thinking
ccs kimi         # Kimi for Coding
ccs --version    # Show version

# Create accounts
ccs auth create work
ccs auth create personal

# Terminal 1
ccs work "implement feature"

# Terminal 2 (concurrent)
ccs personal "review code"

Non-standard installation location:

export CCS_CLAUDE_PATH="/path/to/claude"              # Unix
$env:CCS_CLAUDE_PATH = "D:\Tools\Claude\claude.exe"   # Windows

See Troubleshooting Guide

Auto-created during installation via npm postinstall script.

~/.ccs/config.json:

{
  "profiles": {
    "glm": "~/.ccs/glm.settings.json",
    "glmt": "~/.ccs/glmt.settings.json",
    "kimi": "~/.ccs/kimi.settings.json",
    "default": "~/.claude/settings.json"
  }
}

Complete guide: docs/en/configuration.md

Package Managers

npm uninstall -g @kaitranntt/ccs
yarn global remove @kaitranntt/ccs
pnpm remove -g @kaitranntt/ccs
bun remove -g @kaitranntt/ccs

Official Uninstaller

# macOS / Linux
curl -fsSL ccs.kaitran.ca/uninstall | bash

# Windows
irm ccs.kaitran.ca/uninstall | iex

• YAGNI: No features "just in case"
• KISS: Simple bash, no complexity
• DRY: One source of truth (config)

Complete documentation in docs/:

• Installation Guide
• Configuration
• Usage Examples
• System Architecture
• GLMT Control Mechanisms
• Troubleshooting
• Contributing

We welcome contributions! Please see our Contributing Guide for details.

CCS is licensed under the MIT License.