Claude Code has added /ultrareview as a public research preview. Dozens of bug-hunting agents analyze your code in parallel from the cloud. The era of solo code review is coming to an end.
In May 2026, Claude Code's Hooks system received a significant upgrade. PostToolUse hooks can now intercept and replace output from any tool (not just MCP), hooks can read the current effort level via effort.level or $CLAUDE_EFFORT, and duration_ms tracks actual tool execution time. A new claude ultrareview subcommand also enables non-interactive code review from CI pipelines.
In May 2026, Claude Code received a massive update: Routines, /ultrareview, and Claude Opus 4.7 as the new default. Scheduled cloud agents, parallel multi-agent code review, and the xhigh effort level β an EdTech CEO analyzes what the finished form of a vibe coding tool looks like.