kanban-worker

Name: kanban-worker
Availability: InStock
Author: cabezno

Guide Hermes Kanban workers through task lifecycle actions with tenant-safe state handling.

Updated May 15, 2026

Search Tags:#workflow orchestration #multi-agent #kanban #tenant isolation #worker lifecycle #retry diagnostics #handoff metadata

Ready to run

npx skills add https://github.com/cabezno/bmb-encover-agent --skill kanban-worker-cabezno

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: kanban-worker
Source: https://github.com/cabezno/bmb-encover-agent/tree/main/skills/devops/kanban-worker
Command: npx skills add https://github.com/cabezno/bmb-encover-agent --skill kanban-worker-cabezno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The kanban-worker skill prevents failed handoffs and slow retries by guiding workers through workspace behavior, tenant-safe memory, and the correct use of kanban tools during the worker lifecycle.

Core Features & Use Cases

Workspace handling: Adapts behavior for scratch, persistent directories, and Git worktrees to avoid stale or mis-scoped edits.
Tenant isolation: Enforces safe memory prefixing with $HERMES_TENANT to prevent cross-tenant context leaks.
Reliable handoffs: Defines how to structure kanban_complete summary and metadata for downstream parsers, reviewers, and aggregators.
Operational correctness: Covers block reasons, heartbeat quality, and retry diagnostics based on previous run outcomes.

Quick Start

Ask the worker to complete a specific kanban task while producing a structured kanban_complete(summary, metadata) handoff that explains decisions, files changed, and any measured results.

Frequently Asked Questions about kanban-worker

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

FAQPage Schema

How do I prevent failed handoffs in a multi-agent workflow?▼

To prevent failed handoffs in a multi-agent workflow, structure kanban_complete summary and metadata payloads with high-signal context for downstream parsers. This ensures downstream agents receive clear decisions, changed files, and measured results, enabling reliable task lifecycle transitions.

How does tenant isolation work for multi-agent worker lifecycles?▼

Tenant isolation for multi-agent worker lifecycles works by enforcing safe memory prefixing using the $HERMES_TENANT environment variable. This mechanism prevents cross-tenant context leaks during task processing, ensuring agents operate strictly within their designated tenant boundaries.

What is the best way to handle workspace state across scratch and Git worktrees?▼

The best way to handle workspace state across scratch and Git worktrees is to adapt worker behavior based on the directory type. This prevents stale or mis-scoped edits during workflow orchestration by ensuring agents interact correctly with persistent directories and temporary worktrees.

How do I diagnose retry outcomes from previous kanban worker runs?▼

To diagnose retry outcomes from previous kanban worker runs, interpret the results from kanban_show. This allows workers to adjust their operational behavior by understanding previous block reasons, heartbeat quality, and specific failure contexts before attempting the task again.

When should I use kanban_block reasons during workflow orchestration?▼

You should use precise kanban_block reasons during workflow orchestration when a worker hits a genuine operational wall. Providing specific block context instead of failing silently improves retry diagnostics and informs the dispatcher exactly why the task cannot proceed.