Prompt capture
TaskOutput tool description
27 model strings share this prompt, byte for byte.
1DEPRECATED: Background tasks return their output file path in the tool result, and you receive a <task-notification> with the same path when the task completes.
2- For bash tasks: prefer using the Read tool on that output file path — it contains stdout/stderr.
3- For local_agent tasks: use the Agent tool result directly. Do NOT Read the .output file — it is a symlink to the full subagent conversation transcript (JSONL) and will overflow your context window.
4- For remote_agent tasks: prefer using the Read tool on the output file path — it contains the streamed remote session output (same as bash).
6- Retrieves output from a running or completed task (background shell, agent, or remote session)
7- Takes a task_id parameter identifying the task
8- Returns the task output along with status information
9- Use block=true (default) to wait for task completion
10- Use block=false for non-blocking check of current status
11- Task IDs can be found using the /tasks command
12- Works with all task types: background shells, async agents, and remote sessions