How does Model Orchestration help me save on token costs?

This skill functions as a management layer for Claude Code, allowing you to route high-volume tasks like boilerplate generation or unit testing to lower-cost models while reserving your primary Claude limits for complex reasoning.

Which LLM providers and models are compatible with this worker plugin?

The plugin supports any Anthropic-compatible API, meaning you can easily connect it to providers like DeepSeek, LiteLLM, Ollama, Kimi, and z.ai GLM.

What is the installation process like for this orchestration skill?

Setup is straightforward: once installed via the marketplace, you simply provide your worker API keys and endpoints within your Claude Code configuration to start delegating tasks.

What exactly is included with my purchase?

You will receive the core orchestration plugin files, a configuration guide for various API providers, and access to all future version updates to ensure ongoing compatibility.

Can I customize which specific tasks are delegated to the cheaper agents?

Yes, you can define specific rules to determine which types of tasks are sent to headless workers and which remain with the primary Claude model to ensure optimal performance.

Claude Code Model Router: Delegate Work to Cheap Models |…

I will help you set up a DeepSeek worker. We'll use a dedicated configuration directory to ensure your OpenRouter credentials don't interfere with your primary Anthropic session.

DeepSeek Worker Setup

To initialize the worker, run the following commands in your terminal:


# 1. Create the worker using the OpenRouter preset
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" create deepseek --provider openrouter

# 2. Add your OpenRouter API key (this avoids leaking it in your shell history)
# Replace 'sk-or-...' with your actual key
printf 'sk-or-your-api-key' | "${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" set-key deepseek

# 3. Finalize the headless configuration
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" finalize deepseek

Once finalized, you can delegate tasks to this worker. The worker will operate in its own sandbox at ~/.claude-workers/deepseek/.

Example dispatch command:

~/.claude-workers/deepseek/run -p "Write standard CRUD boilerplate for the user_profile model in lib/models.go" --permission-mode acceptEdits

Next steps

Verify the connection by running ~/.claude-workers/deepseek/run to start an interactive test session.
Review ~/.claude-workers/deepseek/settings.json if you need to manually adjust model mappings (e.g., pointing Sonnet to deepseek/deepseek-chat).
Add the delegation rules from templates/delegation-rules.md to your CLAUDE.md to improve worker reliability.

Frequently Asked Questions

Claude Code Model Router: Delegate Work to Cheap Models