Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
Submit a plan, code, or question to Claude Code for a second opinion. Use this skill when you want to challenge Vibe's proposed approach with Claude's opinion, or for any external review.