run

Execute specialized sub-agents within a multi-agent harness using file-based handoffs.

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/panicgit/wrangler --skill run-panicgit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: run
Source: https://github.com/panicgit/wrangler/tree/main/skills/run
Command: npx skills add https://github.com/panicgit/wrangler --skill run-panicgit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the challenge of managing complex, multi-step projects by coordinating specialized agents that work together to diagnose failures and execute tasks.

Core Features & Use Cases

  • Agent Orchestration: Automatically dispatches sub-agents based on a custom harness configuration.
  • Sprint Management: Handles inter-agent communication via isolated file-based handoffs and progress tracking.
  • Use Case: If you are building a complex application, use this Skill to run a planner, generator, and evaluator in sequence to ensure high-quality code output while maintaining strict context separation.

Quick Start

Invoke the run skill to execute the planner agent within your current project harness.

Frequently Asked Questions about run

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

FAQPage Schema
How do I orchestrate multi-agent workflows for complex project tasks?

Multi-agent orchestration executes specialized sub-agents within a defined harness to handle complex project tasks. It manages inter-agent communication through isolated file-based handoffs and automated sprint directory tracking to ensure strict context separation.

What is file-based handoff in multi-agent automation?

File-based handoff is an inter-agent communication mechanism that isolates context between specialized agents. It manages task progress via automated sprint directory tracking, allowing sequential agents like planners and evaluators to exchange data without overlapping.

Do I need a harness configuration to run sub-agents?

Yes, you need a valid .wrangler/harness.json configuration to run sub-agents. This file is required to identify agent roles, define system prompts, and establish the workflow sequences necessary for the orchestration harness to dispatch tasks.

How do I set up a planner and evaluator agent sequence?

To set up a planner and evaluator agent sequence, configure your .wrangler/harness.json file to define the respective agent roles, system prompts, and workflow order. Invoking the run skill then executes this sequence to ensure high-quality code output.

When should I use a multi-agent harness instead of a single agent?

Use a multi-agent harness when managing complex, multi-step projects that require strict context separation. It is ideal when you need specialized agents, such as a planner, generator, and evaluator, to work together to diagnose failures and execute tasks.