Slack × Claude Managed Agents Guide
@mention a Claude Managed Agent in Slack and get the reply in-thread. `` Slack @mention ──▶ /slack/events ──▶ sessions.create (+ metadata) ──▶ 200 │ Claude runs to idle on Anthropic infra │ /cma-webhook ◀── session.status_idled ◀───────┘ │ └──▶ sessions.retrieve → read metadata → chat.postMessage ` The CMA session's metadata (slack_channel, slack_thread_ts`) is the entire routing state.
When to use Slack × Claude Managed Agents
@mention a Claude Managed Agent in Slack and get the reply in-thread. `` Slack @mention ──▶ /slack/events ──▶ sessions.create (+ metadata) ──▶ 200 │ Claude runs to idle on Anthropic infra │ /cma-webhook ◀── session.status_idled ◀───────┘ │ └──▶ sessions.retrieve → read metadata → chat.postMessage ` The CMA session's metadata (slack_channel, slack_thread_ts`) is the entire routing state.
How to use Slack × Claude Managed Agents
Slack × Claude Managed Agents is a single agent agent built on the Anthropic SDK framework. Set it up from the source repository, configure your model credentials, and invoke it for tasks that match its description. Review the safety profile below before running it against production data or systems.
Safety profile
Autonomy
Semi-autonomous
Sandbox-aware
Yes
Network access
Unspecified
Filesystem access
Unspecified