A configuration skill for integrating NewCLI as a multi-model provider for OpenClaw, featuring high-efficiency AWS routes for Claude models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install add-newcli-provider
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 add-newcli-provider 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 NewCLI Model Provider Configuration?
This skill enables developers to connect OpenClaw to the NewCLI (FoxCode) model proxy service. By integrating this, users gain access to a broad spectrum of large language models, including the Claude series, GPT-5 Codex series, and Gemini 3 Pro. This configuration is a powerful addition to your collection of Openclaw Skills because it organizes access across four distinct provider types based on API protocol and cost optimization routes.
The integration is particularly valuable for its support of the newcli-aws provider, which offers Claude models at a fraction of the standard cost (1/24th consumption rate). This allows for high-frequency agent operations without exhausting API quotas, making it an essential configuration for heavy development workloads.
NewCLI Model Provider Configuration Use Cases
- Adding Claude or GPT models to an OpenClaw agent for advanced coding and reasoning tasks.
- Implementing cost-efficient LLM workflows by utilizing the specialized newcli-aws special route.
- Setting up multi-model fallback chains to ensure high availability and reliability for automated agents.
- Accessing Gemini image generation models with specific aspect ratios directly through a unified configuration.
How NewCLI Model Provider Configuration Works
- Connectivity Testing: The skill uses targeted curl commands to verify the availability of specific model endpoints (Claude, GPT, or Gemini) using your specific API key.
- Provider Registration: It defines four specific provider blocks (newcli, newcli-aws, newcli-codex, and newcli-gemini) in the OpenClaw configuration file with matching base URLs and protocols.
- Model Mapping: Users manually add verified model IDs to the provider definitions, ensuring only accessible models are utilized by the agent.
- Alias Creation: Short, easy-to-remember aliases are mapped to long model IDs to streamline chat commands and agent configuration.
- Fallback Integration: The configured models are added to the automated fallback chain to provide a robust failover mechanism during service interruptions.
- System Validation: The skill uses the openclaw doctor command to validate JSON schema before restarting the gateway service.
NewCLI Model Provider Configuration Setup
First, obtain your API Key from the NewCLI service. Then, follow these steps to enhance your Openclaw Skills setup:
- Test the endpoint for the Claude AWS route:
curl -s https://code.newcli.com/claude/aws/v1/messages \
-H "x-api-key: <YOUR_API_KEY>" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-4-6","messages":[{"role":"user","content":"hi"}],"max_tokens":10}'
Add the provider block to
~/.openclaw/openclaw.jsonundermodels.providers.Validate the configuration and restart the gateway:
# Run schema check
openclaw doctor
# Restart on macOS
launchctl kickstart -k gui/$(id -u)/ai.openclaw.gateway
NewCLI Model Provider Configuration Data Schema & Taxonomy
The skill organizes data within the main OpenClaw configuration file using the following structure:
| Section | Field | Purpose |
|---|---|---|
| models.providers | baseUrl | The specific proxy endpoint (e.g., /claude/aws) |
| models.providers | api | The protocol type: anthropic-messages, openai-completions, or google-generative-ai |
| agents.defaults.models | alias | User-friendly names for model switching (e.g., 'gpt53') |
| agents.defaults.model.fallbacks | Array | Priority sequence for automatic model failover |
NewCLI Model Provider Configuration Advanced Features
- Cost Optimization: Specifically leverage the newcli-aws provider for 24x more usage compared to standard Claude routes.
- Image Generation: Support for Gemini-3-pro-image models with specific resolution and aspect ratio parameters (e.g., 16x9, 2k, 4k).
- Protocol Diversity: Manage three distinct API protocols within a single provider account through these Openclaw Skills.
- WAF-Aware Fallbacks: Strategic placement of Codex models outside of automatic fallback chains to avoid Cloudflare WAF 403 blocks during large context requests.
- Reasoning Model Support: Explicit configuration of reasoning capabilities for Gemini and Claude models within the model definition schema.
SKILL.md
Loading
Related Openclaw Skills
MiniMax Provider Configuration
A technical skill for integrating MiniMax M2.1 series models into OpenClaw using both direct API Key and OAuth portal access methods.
OpenClaw Command Center
A mission control dashboard providing real-time session monitoring and cost intelligence for your AI agent workforce.
Claw Score Agent Architecture Audit
An automated diagnostic tool that reviews AI agent configuration files to provide scoring and optimization insights.
EVM Wallet Skill for AI Agents
A self-sovereign EVM wallet enabling AI agents to manage assets, swap tokens, and access private AI inference via Venice AI.
SiliconFlow Provider Configuration
A comprehensive configuration skill to integrate SiliconFlow's inference platform into OpenClaw for access to over 98 AI models including DeepSeek, Qwen, and Kimi.
Callmac: Remote Voice Control for Mac
Control your Mac's voice remotely from mobile devices to play announcements, alarms, and stories using high-quality neural TTS.
Featured*
