beads

Track multi-session tasks with dependency management via Git-backed workflows.

Updated Jan 16, 2026
One-click install
npx skills add https://github.com/quanhavn/workflow-skills --skill beads-quanhavn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: beads
Source: https://github.com/quanhavn/workflow-skills/tree/main/beads
Command: npx skills add https://github.com/quanhavn/workflow-skills --skill beads-quanhavn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Beads enables persistent, multi-session task tracking with dependency management for AI agents. It preserves context across conversation boundaries and coordinates complex workflows, reducing cognitive load and context-switching.

Core Features & Use Cases

  • Git-backed persistence: Long-running work survives compaction and session changes.
  • Dependency graph: Blocks, related, parent-child, and discovered-from relationships guide execution.
  • Contextual memory: Rich notes and decision history remain available across sessions.
  • Cross-session workflows: Ideal for multi-day projects, research, integration work, and ongoing improvement cycles.

Quick Start

Start by inspecting ready work and then activate a multi-step task workflow using the beads skill and the bd CLI, ensuring you reference the persistent context and dependencies when planning next actions.

Frequently Asked Questions about beads

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

FAQPage Schema
How do I maintain AI agent task tracking across multiple sessions after context compaction?

Persistent multi-session task tracking survives conversation compaction by using Git-backed persistence to store dependency graphs, rich notes, and decision history. This preserves context across session boundaries for long-running projects.

What is the best way to manage dependencies for long-running AI workflows spanning days or weeks?

Managing dependencies for long-running AI workflows requires a dependency graph tracking blocks, related, parent-child, and discovered-from relationships. This coordinates complex cross-session workflows and reduces context-switching cognitive load.

Can I use Git-backed persistence to coordinate complex AI agent workflows with blockers?

Git-backed persistence supports coordinating complex AI agent workflows with blockers by maintaining dependency relationships and contextual memory. It preserves task states and decision history across multiple sessions for ongoing improvement cycles.

How do I start a multi-step task workflow using persistent context and dependencies?

Start a multi-step task workflow by inspecting ready work, then activate the workflow using the beads skill and the bd CLI. Reference persistent context and dependencies when planning next actions to ensure cross-session continuity.

Does persistent task tracking work without a SKILL.md frontmatter?

Persistent task tracking requires a SKILL.md frontmatter with a name and description. Optional resources directories may be included to support the dependency management and contextual memory features.

When should I not use multi-session dependency management for AI agents?

Multi-session dependency management is not suited for short-lived, single-session tasks that do not span days or weeks. It is designed for long-running projects, research, and integration work requiring context survival across compaction.