Claude Code sessions can now message each other
Two open sessions can talk: Claude finds the others with ListAgents and sends a message through SendMessage, either because you asked or on its own when a change in one session affects the work in another. Only text Claude writes crosses over — never conversation history, never files. Since version 2.1.232 you can also address a session directly by typing @ followed by its name. The feature runs on macOS and Linux and needs version 2.1.224 or later, and /list-agents shows what is available. It pays off most when you keep the frontend and backend of the same project in separate sessions.
Source
Sesije Claude Codea sada mogu da razmjenjuju porukeClaude Code official documentation · Original published August 7, 2026
Two open Claude Code sessions can now exchange messages, with you no longer acting as the courier.
How it works
A session discovers the others through the ListAgents tool and writes to them with SendMessage, either because you asked or on its own when a change in one session affects the work in another. Only the text Claude writes goes through the channel: conversation history and files stay where they are.
How to use it
Since version 2.1.232 you can address a session directly by typing @ followed by its name. The /list-agents command shows what is available. The feature runs on macOS and Linux and needs version 2.1.224 or later.
Where it actually pays off
The payoff is largest when the frontend and the backend of one project sit in separate sessions. A change to the API contract in one session reaches the other immediately, without you retelling it and without carrying types from window to window.
Sources
Related
OpenClaw 2026.10.2 stops long tool output from slipping credentials past redaction
A bug in OpenClaw's secret masking let a credential through whenever it straddled the boundary between two slices of a long text. The fix ships in 2026.10.2 along with repaired updates from 2026.10.1 and a new compaction default for OpenAI and Anthropic API keys.
OpenClawverified
OpenClaw 2026.10.1 lets agents search installed skills and changes how sessions message each other
OpenClaw released version 2026.10.1 on October 10, 2026, its first stable release since 2026.9.7. Agents can now search the skills installed on a machine and read only the one a task needs, instead of carrying the whole library in the prompt. Opt-in MCP Apps run beside chat, and full backups can go to an external drive or Cloudflare R2. Three changes can break existing setups: session-to-session messaging, the old required argument, and Workboard data stored before July 2026.
OpenClawverified
Claude Code 2.1.294 fixes prompt hooks that let through the actions they were written to block
Anthropic released Claude Code 2.1.294 on October 8, 2026. It fixes prompt and agent hooks phrased as instructions, which could allow exactly the actions they were meant to stop. Version 2.1.295 followed the same day with an onFailure setting that makes a crashed or timed-out command or HTTP hook block the action. Releases 2.1.292 and 2.1.293 from earlier in the week closed several permission and sandbox gaps.
Claude Code Releases (GitHub)verified