Claude Code 2.1.310, released October 23, brings the Monitor tool to AWS Bedrock, Google Vertex AI, and Azure AI Foundry. It also adds a new Safety telemetry event that logs every blocked tool call, plus /import commands to migrate settings from Gemini CLI, Cursor, or Codex in one step.
Claude Code 2.1.292 adds an effort parameter to the Agent tool, letting you run subagents at five levels β low through max β to balance cost and quality per task. The release also adds a --marketplace flag to plugin install, letting you register the marketplace and install a plugin in a single command.
Since Claude Code v2.1.224, separate sessions can message each other directly. ListAgents discovers reachable sessions; SendMessage delivers text to one by name. When one session's change breaks what another is building, it can warn that session before you notice β reshaping how parallel agent development coordinates.
Claude Code June 2026 brings Artifacts (live shareable web pages), sub-agent chains up to 5 levels deep, the /cd command, and important safety guardrails. Everything development teams need to know.
In June 2026, Claude Code shipped nested sub-agents, the /cd command, safe-mode, fallback models, and doubled rate limits. The era of agents spawning their own agents has arrived.