How do I install the Model Failover skill?

Run npx skillmds@latest add winsorllc/model-failover in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Model Failover safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Model Failover?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Model Failover free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Model Failover?

winsorllc (@winsorllc) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Model Failover by winsorllc — Agent Skill

Name: Model Failover
Author: winsorllc

File contents

Model Failover Skill

Automatically switch between LLM providers when one fails. Supports configurable fallback chains, rate limiting, and health monitoring. Inspired by OpenClaw's model failover system.

Setup

Configure your provider chain in environment variables:

# Comma-separated list of providers (in fallback order)
export LLM_PROVIDER_CHAIN="anthropic:claude-3-5-sonnet-20241022,openai:gpt-4o-mini,google:gemini-1.5-flash"

# API keys for each provider
export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."
export GOOGLE_API_KEY="..."

Usage

Chat with automatic failover

{baseDir}/model-failover.js chat "Your message here"

Add a new provider to the chain

{baseDir}/model-failover.js add-provider anthropic claude-3-5-sonnet-20241022

Remove a provider from the chain

{baseDir}/model-failover.js remove-provider openai

List providers in chain

{baseDir}/model-failover.js list

Check provider health

{baseDir}/model-failover.js health

Reset failure counts

{baseDir}/model-failover.js reset

Configuration

Environment Variable	Description	Default
`LLM_PROVIDER_CHAIN`	Comma-separated `provider:model` pairs	`anthropic:claude-3-5-sonnet-20241022`
`ANTHROPIC_API_KEY`	Anthropic API key	-
`OPENAI_API_KEY`	OpenAI API key	-
`GOOGLE_API_KEY`	Google API key	-
`CUSTOM_API_KEY`	Custom provider API key	-
`MAX_RETRIES`	Max retries per provider	2
`RETRY_DELAY_MS`	Delay between retries	1000

Provider Format

provider:model

Supported providers:

anthropic - Anthropic Claude models
openai - OpenAI GPT models
google - Google Gemini models
custom - Custom OpenAI-compatible endpoint (set OPENAI_BASE_URL)

How It Works

Try the first provider in the chain
If it fails (rate limit, error, timeout), wait and retry
If retries exhausted, move to next provider
Continue until success or all providers exhausted
Track failures per provider for health monitoring

---name: model-failoverdescription: Automatic LLM provider failover with fallback chains, inspired by OpenClaw/ZeroClaw model configuration.---# Model Failover SkillAutomatically switch between LLM providers when one fails. Supports configurable fallback chains, rate limiting, and health monitoring. Inspired by OpenClaw's model failover system.## SetupConfigure your provider chain in environment variables:```bash# Comma-separated list of providers (in fallback order)export LLM_PROVIDER_CHAIN="anthropic:claude-3-5-sonnet-20241022,openai:gpt-4o-mini,google:gemini-1.5-flash"# API keys for each providerexport ANTHROPIC_API_KEY="sk-ant-..."export OPENAI_API_KEY="sk-..."export GOOGLE_API_KEY="..."```## Usage### Chat with automatic failover```bash{baseDir}/model-failover.js chat "Your message here"```### Add a new provider to the chain```bash{baseDir}/model-failover.js add-provider anthropic claude-3-5-sonnet-20241022```### Remove a provider from the chain```bash{baseDir}/model-failover.js remove-provider openai```### List providers in chain```bash{baseDir}/model-failover.js list```### Check provider health```bash{baseDir}/model-failover.js health```### Reset failure counts```bash{baseDir}/model-failover.js reset```## Configuration| Environment Variable | Description | Default ||---------------------|-------------|---------|| `LLM_PROVIDER_CHAIN` | Comma-separated `provider:model` pairs | `anthropic:claude-3-5-sonnet-20241022` || `ANTHROPIC_API_KEY` | Anthropic API key | - || `OPENAI_API_KEY` | OpenAI API key | - || `GOOGLE_API_KEY` | Google API key | - || `CUSTOM_API_KEY` | Custom provider API key | - || `MAX_RETRIES` | Max retries per provider | 2 || `RETRY_DELAY_MS` | Delay between retries | 1000 |## Provider Format```provider:model```Supported providers:- `anthropic` - Anthropic Claude models- `openai` - OpenAI GPT models- `google` - Google Gemini models- `custom` - Custom OpenAI-compatible endpoint (set `OPENAI_BASE_URL`)## How It Works1. Try the first provider in the chain2. If it fails (rate limit, error, timeout), wait and retry3. If retries exhausted, move to next provider4. Continue until success or all providers exhausted5. Track failures per provider for health monitoring

Frequently asked questions

Model Failover