Doublecheck

This is a three-layer verification pipeline that checks AI output for hallucinations and sourcing problems. It runs in two modes: active mode that stays on and adds inline verification to every substantive response, or one-shot mode where you point it at specific text. The pipeline extracts verifiable claims, runs web searches for supporting or contradicting sources, looks for hallucination patterns, and produces a structured report with links you can check yourself. It auto-escalates to a full report when it finds disputed claims or fabrication risks, and always runs the full check on high-stakes content like legal analysis or regulatory guidance. Useful when you need to trust the output or hand it to someone else.

Install to Claude Code

npx -y skills add github/awesome-copilot --skill doublecheck --agent claude-code