session:start

Coordinate multi-agent orchestration sessions by delegating tasks to worker agents.

Updated Mar 14, 2026

Search Tags:#multi-agent #orchestration #signals #session #agent-coordination #task-delegation #harness

Ready to run

npx skills add https://github.com/smykla-skalski/harness --skill session-start-smykla-skalski

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: session:start
Source: https://github.com/smykla-skalski/harness/tree/main/plugins/harness/skills/start
Command: npx skills add https://github.com/smykla-skalski/harness --skill session-start-smykla-skalski

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill ensures a human leader can coordinate multi-agent workflows without executing the work themselves, avoiding conflicting edits, lost state, and uncoordinated effort during complex orchestration tasks.

Core Features & Use Cases

Structured Planning and Task Creation: Break a high-level goal into independent, file-scoped tasks with clear acceptance criteria.
Agent Management and Assignment: Start sessions, instruct users how to spawn workers, wait for joins, assign tasks to capable agents, and transfer leadership when needed.
Monitoring and Signaling: Observe session progress, poll status in machine-readable form, and send signals to redirect or pause workers safely.

Quick Start

Start a session by running harness session start with a clear --context describing the goal and then wait for agents to join before creating and assigning tasks.

Frequently Asked Questions about session:start

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

FAQPage Schema

How do I start a multi-agent orchestration session for software test environments?▼

Start a multi-agent orchestration session by running the harness session start command with a clear context flag describing the goal. Wait for worker agents to join before creating and assigning discrete, file-scoped tasks to coordinate test environments effectively.

Can a leader agent execute tasks directly during multi-agent session coordination?▼

No, a leader agent cannot execute tasks directly during multi-agent session coordination. The leader must delegate all work to worker agents, avoiding conflicting edits and uncoordinated effort while breaking goals into independent tasks with acceptance criteria.

What is the best way to delegate tasks to worker agents in a harness session?▼

The best way to delegate tasks in a harness session is to break the high-level goal into independent, file-scoped tasks with clear acceptance criteria, wait for capable agents to join, and then assign tasks using the task assignment and role transfer APIs.

How do I monitor agent progress and send signals during a multi-agent workflow?▼

Monitor agent progress and send signals during a multi-agent workflow by polling session status in machine-readable form. Observe progress and send signals to safely redirect or pause worker agents when coordination adjustments are needed.

When should I transfer leadership in a multi-agent orchestration session?▼

Transfer leadership in a multi-agent orchestration session when the current leader needs to step down or when another agent is better suited to coordinate remaining tasks. Use the role transfer API to safely hand off session control without losing state.

Do I need to wait for agents to join before creating tasks in a harness session?▼

Yes, you need to wait for agents to join before creating tasks in a harness session. Starting a session with a clear context and waiting for joins ensures capable worker agents are available to receive assignments before task creation begins.