A sophisticated configuration skill for Openclaw Skills that optimizes the use of free AI models through intelligent fallback routing and provider diversification.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install freeride-opencode
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install freeride-opencode using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Freeride OpenCode?
Freeride OpenCode is designed to help developers leverage high-quality free AI models from both OpenCode Zen and OpenRouter while maintaining production-grade reliability. By implementing this skill within the Openclaw Skills ecosystem, users can significantly reduce API costs without sacrificing performance. It provides a robust framework for managing model availability, ensuring that your agents remain responsive even when specific providers encounter rate limits or service disruptions.
The core value of this skill lies in its ability to orchestrate multiple free-tier LLMs—such as MiniMax M2.1, Kimi K2.5, and Trinity Large—into a cohesive, resilient workflow. This allows for a "freeride" on powerful reasoning capabilities by utilizing smart routing for primary tasks, subtasks, and background heartbeat checks.
Freeride OpenCode Use Cases
- Reducing operational expenses by routing non-critical agent subtasks to free-tier models.
- Implementing resilient AI workflows that automatically switch between providers during API outages.
- Managing high-frequency heartbeat monitoring and cron jobs without consuming paid credits.
- Scaling developer agents across multiple providers to bypass individual rate limit constraints.
- Testing and prototyping agentic behaviors using a variety of high-performance free LLMs.
How Freeride OpenCode Works
- The user obtains and configures API keys for both OpenCode Zen and OpenRouter providers.
- A primary free model is selected for the main reasoning tasks within the agent configuration.
- A prioritized list of fallback models is defined, utilizing provider diversification to ensure maximum uptime.
- Specific, lower-latency models are assigned to secondary tasks like heartbeats or subagents for optimal resource allocation.
- The configuration is applied via the CLI, enabling the agent to dynamically route requests based on real-time availability and provider status.
Freeride OpenCode Setup
To integrate this configuration with Openclaw Skills, first ensure you have your OpenCode Zen and OpenRouter API keys. Then, apply the configuration using the following command:
openclaw config.patch --raw '{
"agents": {
"defaults": {
"model": {
"primary": "opencode/minimax-m2.1-free",
"fallbacks": [
"openrouter/arcee-ai/trinity-large-preview:free",
"opencode/kimi-k2.5-free"
]
},
"heartbeat": {
"model": "opencode/glm-4.7-free"
},
"subagents": {
"model": "opencode/kimi-k2.5-free"
}
}
}
}'
Freeride OpenCode Data Schema & Taxonomy
The skill organizes its logic within the standard JSON configuration used by Openclaw Skills, focusing on provider credentials and model routing logic.
| Section | Key Fields | Purpose |
|---|---|---|
| providers | api_key | Manages authentication for OpenCode and OpenRouter backends. |
| models | primary, fallbacks | Defines the hierarchical order of model usage to ensure reliability. |
| heartbeat | every, model | Configures the frequency and model choice for background status checks. |
| subagents | model | Assigns specific models to secondary agent tasks for cost balancing. |
Freeride OpenCode Advanced Features
- Provider Diversification: Minimizes downtime by alternating between different API infrastructures (OpenCode vs. OpenRouter).
- Intelligent Fallback Triggers: Automatically handles rate limits, authentication failures, and provider timeouts.
- Granular Task Assignment: Allows for specific model optimization based on task complexity (e.g., reasoning vs. status checks).
- Model Aliasing: Simplifies configuration by allowing human-readable names for complex model identifiers within Openclaw Skills.
- Cross-Provider Resilience: Ensures that if one provider's free tier is exhausted, the agent seamlessly transitions to an alternative service.
SKILL.md
Loading
Related Openclaw Skills
Feishu Automation
A powerful automation toolkit for the Feishu and Lark suite designed to handle batch document processing, data synchronization, and wiki management.
Tweet Monitor Pro
A professional scraping engine for X/Twitter and Chinese social platforms that requires no login or official API keys.
Feishu Messaging Configuration
A specialized configuration guide for optimizing how AI agents format and deliver messages within Feishu and Lark environments.
Feishu Chat Guide
A specialized guide for managing Feishu group chat interactions, ensuring stable message formatting and precise @ mentions.
OpenClaw Swarm Orchestration
A high-performance orchestration skill for spawning, coordinating, and sharing state across multiple AI subagents.
Speckit Swarm
An advanced agent orchestration system that enables parallel execution and task decomposition through specialized AI personas and ultrawork detection.
METADATA
Featured*
