kanbanzai-agents

Orchestrate agent interactions with context assembly, task claiming, and sub-agent handoffs.

5|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/sambeau/kanbanzai --skill kanbanzai-agents
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kanbanzai-agents
Source: https://github.com/sambeau/kanbanzai/tree/main/.agents/skills/kanbanzai-agents
Command: npx skills add https://github.com/sambeau/kanbanzai --skill kanbanzai-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

As the central interaction layer for Kanbanzai, this skill defines how AI agents coordinate context, dispatch work, and manage knowledge entries and sub-agent orchestration within the workflow system.

Core Features & Use Cases

  • Organizes agent interactions: context assembly, task claiming, commit creation, and knowledge propagation.
  • Enables spawning sub-agents for parallelized work and coordinated handoffs across tasks.
  • Guides best practices for agent discipline, handoffs, and context preservation across sessions.

Quick Start

Claim a ready task with next() and use handoff(task_id) to spawn a sub-agent when needed.

Frequently Asked Questions about kanbanzai-agents

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

FAQPage Schema
How do I orchestrate AI agents for parallel task dispatch and context coordination?

You orchestrate AI agents by applying a protocol for task claiming, context assembly, and knowledge propagation. This coordinates agent interactions by guiding sub-agent spawning and context preservation across sessions.

What is the best way to spawn sub-agents for parallel work and manage task handoffs?

The best way to spawn sub-agents is using the handoff(task_id) function. This creates parallelized work branches, while the next() function claims ready tasks to ensure coordinated task dispatch and handoffs.

How does agent protocol context assembly work when dispatching tasks across sessions?

Context assembly works by packaging context packets that preserve knowledge and task state across sessions. Agents claim these packets during task dispatch to maintain context continuity and verification during handoffs.

Do I need to follow a specific agent protocol for commits and knowledge propagation?

Yes, you need to follow the agent protocol for writing commits and contributing knowledge. This ensures proper knowledge propagation and maintains agent discipline when claiming tasks or executing next and finish handoffs.

Can I use agent orchestration to manage context packets and verification for sub-agent handoffs?

Yes, agent orchestration supports context packets and verification for sub-agent handoffs. The protocol manages context assembly and task claiming to ensure knowledge propagation remains consistent across parallelized work.

When should I not use sub-agent spawning for task dispatch in my workflow?

You should avoid sub-agent spawning when tasks require strict sequential execution or lack independent context boundaries. Over-spawning without proper context packets can disrupt knowledge propagation and break handoff verification.