Config Guard

What it does

Config Guard protects OpenClaw gateways from configuration errors made by AI agents. It performs automated backups, JSON syntax and schema validation, semantic checks for common AI mistakes (like incorrect model names or missing fields), and includes a health check with automatic rollback if the gateway fails to recover after changes. This prevents cascading failures caused by agent-introduced configuration issues.

When to use it

• Automated Configuration Updates: Use when AI agents are directly modifying openclaw.json.
• Complex Configurations: Ideal for gateways with many channels, models, or tools where errors are more likely.
• Remote Management: Essential for scenarios where remote troubleshooting of gateway crashes is difficult.
• Plugin Development: Crucial when plugins introduce new configuration options that agents might mismanage.

Key capabilities

• Automatic timestamped backups before config changes
• JSON syntax validation
• Schema validation (required fields, types, values)
• Semantic checks for AI-specific errors (e.g., incorrect model names, missing required fields)
• Critical field diff warnings (Telegram channels, authentication tokens, tool deny lists)
• Gateway health check with 30-second polling
• Automatic rollback to the previous backup if the gateway fails

Example prompts

These are not direct prompts to the skill, but rather scenarios where it protects against errors made by agents:

• "Update the model configuration to use claude-sonnet-4.5." (Config Guard will correct "claude-sonnet-4.5" to "claude-sonnet-4-5")
• "Add a new Telegram channel with ID 123." (Config Guard ensures required fields for the channel are present)
• “Enable authentication using API keys.” (Config Guard will check for placeholder values in sensitive fields.)

Tips & gotchas

The skill requires access to and modification rights of openclaw.json. Consider integrating it as a git hook (pre-config-hook.sh) to automatically validate changes before they are applied.