Agents and delegation

A single agent working through a large task fills its context quickly. Seshat lets an agent delegate: it starts a sub-agent with a self-contained task, the sub-agent works on its own with a limited set of tools, and only its result comes back.

• Main agentTalks to you, plans, decides what to delegate
  • exploreRead-only: read, glob, grep
  • planDesigns an approach before anything changes
  • general-purposeDoes a self-contained piece of work
    • helperA sub-agent of a sub-agent, within the depth limit
  • verifyChecks the result

Two ways to delegate

The agent tool runs a sub-agent and waits for its answer. The main agent chooses a type and writes the task.

Parameter	Meaning
type	general-purpose, explore, plan, browse or verify
task	A self-contained description: paths, goal, constraints, what to return
max_turns	Turn limit for the sub-agent
run_in_background	Return immediately with a task id and let it run
fork	Give the sub-agent the parent’s message history
isolation	worktree runs it in its own git worktree, so its changes stay apart until merged
tools	Restrict its tools to a list of patterns

The background family starts an agent that keeps running while the main agent continues:

Tool	Use
spawn_agent	Start a background sub-agent
send_agent_message	Steer it between turns
wait_agent	Block until it finishes and read its result
list_agents	See what is running
resume_agent	Continue one that stopped
close_agent	Stop it

Built-in agent types

Type	For
general-purpose	A self-contained piece of work with the full toolset
explore	Understanding a codebase, read-only
plan	Designing an approach
browse	Deep read-only research across the web, documents and code
verify	Checking work that was done

A skill whose context is fork also runs as an isolated sub-agent. See Skills and MCP.

Keeping it under control

Delegation can run away if nothing stops it, so the runtime sets limits:

Limit	Default
Delegation depth (A starts B starts C)	3, adjustable up to 5
Background agents running at once, across the process	8
Turns for a sub-agent	Lower than the top-level default, unless the agent type says otherwise
Wall-clock time of one sub-agent	30 minutes, as a safety net for an agent that is stuck

Permissions of a sub-agent

Starting an agent is itself an action that asks for approval, like any other tool. Once you approve it, the sub-agent runs without asking again for each tool, within the tools it was given. That is why the tool list matters: explore can only read, and you can narrow any agent further with the tools parameter.

Teams of persistent agents

The repository also contains building blocks for persistent agents that have a name, a role and a mailbox, and message each other asynchronously: agent profiles, a mailbox stored in SQLite, a dispatcher that sends, replies and broadcasts, and a bus that polls each inbox.

Next