kanban-worker

Standardize workspace handling, tenant isolation, and handoff behaviors for Kanban worker runs.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/mattei2005/mgs-agent --skill kanban-worker-mattei2005
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kanban-worker
Source: https://github.com/mattei2005/mgs-agent/tree/main/profiles/atena-skills/devops/kanban-worker
Command: npx skills add https://github.com/mattei2005/mgs-agent --skill kanban-worker-mattei2005

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents stalled or confusing Kanban worker completions by documenting the lifecycle expectations, workspace/tenant isolation rules, and the exact handoff and retry patterns that downstream schedulers and reviewers need.

Core Features & Use Cases

  • Workspace-aware execution: Correct behavior for scratch, persistent directories, and git worktrees.
  • Tenant-safe persistent memory: Prevents cross-tenant context leakage by enforcing tenant-prefixed storage.
  • Structured handoffs and fast review blocking: Defines when to use complete vs block, how to shape metadata, and how to attach durable comments for reviewers.

Quick Start

Load the skill into your worker run and use kanban_show first, then report progress and either kanban_complete or kanban_block with a structured, reviewer-friendly reason and accompanying comment when human review is required.

Frequently Asked Questions about kanban-worker

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

FAQPage Schema
How do I standardize workspace handling for Kanban worker handoffs?

To standardize Kanban worker handoffs, this skill enforces workspace-aware execution across scratch directories, persistent paths, and git worktrees while defining exact complete versus block semantics for downstream schedulers.

What is the best way to prevent cross-tenant context leakage in multi-agent workflows?

Preventing cross-tenant context leakage in multi-agent workflows requires tenant-prefixed persistent memory storage, which this skill enforces to keep isolated workspace data separated during dispatched worker tasks.

How do I shape metadata for review-gated Kanban tasks?

Shaping metadata for review-gated Kanban tasks involves attaching durable comments with structured, reviewer-friendly reasons when using kanban_block, ensuring human reviewers receive clear context for fast blocking.

When do I use kanban_complete versus kanban_block for worker task handoffs?

Use kanban_complete for successful task finishing and kanban_block when human review is required, ensuring downstream schedulers understand the worker handoff state through structured metadata and durable comments.

Does this Kanban worker skill handle retry behaviors for failed dispatched tasks?

Yes, the skill handles retry behaviors by documenting exact retry patterns and providing guardrails for claiming only created cards, reducing stalled worker completions during dispatched coding and research runs.

Why should I use tools instead of CLI in containerized Kanban backends?

Using tools instead of CLI in containerized backends prevents execution failures and ensures safer worker runs, as this skill provides specific guardrails for tool usage within isolated workspace environments.