spur-way

Enforce beads as the source of truth for multi-agent task delegation.

2|Updated Apr 15, 2026

Search Tags:#workflow #collaboration #audit #beads #multi-agent #orchestration

Ready to run

npx skills add https://github.com/getspur/spur --skill spur-way

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: spur-way
Source: https://github.com/getspur/spur/tree/main/.spur/skills/spur-way
Command: npx skills add https://github.com/getspur/spur --skill spur-way

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of fragmented communication and invisible state in multi-agent systems by enforcing a single source of truth for all task delegations and outcomes.

Core Features & Use Cases

Unified State Management: Mandates that all agent actions are recorded in beads, preventing synchronization errors and lost work.
Transaction Primitives: Enforces the Intent-Action-Record cycle to ensure every task is traceable, reviewable, and retryable.
Use Case: When a brain agent delegates a coding task to a worker, this Skill ensures the worker creates a beads issue, updates the status during execution, and provides an audit trail upon completion, allowing for seamless human review.

Quick Start

Apply the spur-way protocol to your current session by verifying that every task you initiate has a corresponding beads issue and audit trail.

Frequently Asked Questions about spur-way

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

FAQPage Schema

How do I standardize multi-agent orchestration and track task delegation state?▼

Standardize multi-agent orchestration by enforcing beads as the single source of truth for all system state. This ensures task delegation, progress tracking, and outcome verification remain observable and auditable across your agent fleet.

What is the intent-action-record cycle for agent collaboration workflows?▼

The intent-action-record cycle is a transaction primitive for agent collaboration that ensures every delegated task is traceable, reviewable, and retryable. It maintains strict auditability by recording intent, executing action, and logging the final record.

How do I prevent fragmented communication and invisible state in multi-agent systems?▼

Prevent fragmented communication in multi-agent systems by mandating that all worker actions are recorded in beads. This unified state management approach prevents synchronization errors and eliminates lost work during task execution.

Can I use this workflow to audit coding tasks delegated from a brain agent to a worker?▼

Yes, you can audit coding tasks delegated from a brain agent to a worker. The worker creates a beads issue, updates execution status, and provides a complete audit trail upon completion for seamless human review.

Do I need specific dependencies to maintain observability across my agent fleet?▼

No specific dependencies are required to maintain observability across your agent fleet. You only need strict adherence to the three primitives of intent, action, and record to sustain system reliability during multi-agent orchestration.