Run vercel-plugin eval scenarios in Vercel Sandboxes instead of local WezTerm panels. Provisions ephemeral microVMs with Claude Code + plugin pre-installed, runs benchmark prompts, extracts hook artifacts, and produces coverage reports.
Install
npx skills add vercel/vercel-plugin --skill benchmark-sandboxnpx skills add vercel/vercel-plugin --skill benchmark-sandbox -a claude-code -gnpx skills add vercel/vercel-plugin --skill benchmark-sandbox -a codex -ggemini skills install https://github.com/vercel/vercel-plugin.git --path .claude/skills/benchmark-sandboxgh skill install vercel/vercel-plugin benchmark-sandboxgit clone --depth 1 https://github.com/vercel/vercel-plugin /tmp/vercel__vercel-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/vercel__vercel-plugin/.claude/skills/benchmark-sandbox ~/.claude/skills/benchmark-sandbox # Claude Code
cp -R /tmp/vercel__vercel-plugin/.claude/skills/benchmark-sandbox ~/.agents/skills/benchmark-sandbox # Codex, Cursor, Gemini CLI, Copilot, OpenCode