Coordinator Tools

On every turn the coordinator sends its full toolset to the model and dispatches whatever the model calls by name through the tool registry. The coordinator uses these tools to delegate and to inspect the workspace — it does not implement changes itself; that is the workers' job.

Agent management

Spawn and manage worker subprocesses.

Tool	Purpose
`spawn_agent`	Start a worker of a given agent type on a task
`kill_agent`	Terminate a running worker
`agent_status`	Inspect one worker's state
`list_agents`	List all workers and their states
`wait_for_agents`	Block until specified workers finish
`wait_for_any`	Return as soon as any specified worker finishes
`read_agent_output`	Read a worker's output so far
`read_new_agent_output`	Read only worker output produced since the last read

spawn_agent accepts the agent type, the task prompt, and optional overrides such as model, flags, and a worker_label. Every configured agent type — built-in or custom — appears automatically as a spawnable type (see Workers).

File system

Read and edit files. Paths may be relative or absolute — the file tools are not sandboxed to the working directory; access is limited only by the harness process's own permissions (see the trust model).

Tool	Purpose
`read_file`	Read a file (also used to read skill instructions)
`write_file`	Write a new file or overwrite an existing one
`append_file`	Append to a file
`edit_file`	Replace a string in a file
`multi_edit_file`	Apply multiple edits to one file
`ls`	List a directory
`glob`	Match files by glob pattern
`grep`	Search file contents
`read_new_file_content`	Read content produced since a prior read

Shell

Tool	Purpose
`bash`	Run a shell command (unsandboxed, `stdin=/dev/null`)

Task tracking

Tool	Purpose
`todo_write`	Write / update the persistent task list
`todo_read`	Read the current task list

The task list is persisted per run as todo.json — see Run Logs.