subagent

Spawn parallel background subagents for research, planning, and coding tasks.

2|2|Updated May 13, 2026
One-click install
npx skills add https://github.com/autonomy-cloud/kairos-interface --skill subagent-autonomy-cloud
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent
Source: https://github.com/autonomy-cloud/kairos-interface/tree/main/assistant/src/config/bundled-skills/subagent
Command: npx skills add https://github.com/autonomy-cloud/kairos-interface --skill subagent-autonomy-cloud

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It solves the problem of slow, single-threaded assistants by letting you spawn background agents that work independently and in parallel.

Core Features & Use Cases

  • Parallel subagent execution: Run independent workers concurrently for research, planning, or implementation.
  • Scoped tool access via roles: Use researcher, coder, and planner roles to restrict tool permissions to what each task needs.
  • Mid-run parent updates: Use notify_parent so the main conversation can react to important progress without waiting.
  • Fork mode for context reuse: Spawn subagents that inherit the parent’s full messages and memory for near-free context carryover.

Use Case: You need to research an unfamiliar library and simultaneously start an implementation plan; spawn a researcher and a planner in parallel, then read the results when they finish.

Quick Start

Spawn a background research agent labeled "investigate-auth" with the objective "Find how this project secures authentication and summarize the recommended approach," and let it notify the parent while it runs.

Frequently Asked Questions about subagent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run parallel research and coding tasks with autonomous agents?

Yes, you can delegate web research to background agents by spawning parallel subagents. This enables you to conduct documentation review or research an unfamiliar library concurrently while planning or implementation work continues in the main conversation.

How do I restrict tool access when delegating work to background agents?

During parallel execution, a subagent can use the notify_parent mechanism to send mid-run progress updates. This allows the main conversation to react to important milestones without waiting for the background agent to reach a terminal completion status.

Can I spawn a background agent that inherits the parent conversation's context?

Yes, you can spawn a background agent that inherits the parent conversation's context by using fork mode. This enables near-free context carryover by forking the parent's full messages and memory into the new subagent.

What is the best way to retrieve output from a completed background agent?

The best way to retrieve output from a completed background agent is through subagent_read. This mechanism handles terminal-status completion notifications and fetches the final results from the parallel subagent once its independent work is finished.