beads

Track multi-session work with dependency graphs and persistent notes.

Updated Dec 27, 2025
One-click install
npx skills add https://github.com/fredpope/tandas --skill beads-fredpope
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: beads
Source: https://github.com/fredpope/tandas/tree/main/.claude/skills/beads
Command: npx skills add https://github.com/fredpope/tandas --skill beads-fredpope

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Beads provides a structured, persistent memory for multi-session work by capturing tasks with dependency graphs and a notes field, enabling you to resume complex efforts after interruptions.

Core Features & Use Cases

  • Dependency graphs (blocks, related, parent-child, discovered-from) to organize work across sessions.
  • Persistent notes capturing COMPLETED/IN_PROGRESS/NEXT, blockers, and key decisions to survive compaction.
  • Epics and subtasks with automatic unblocking and session handoff patterns for multi-session projects.

Quick Start

  • Start a beads-enabled session by ensuring a .beads database exists.
  • Run bd ready --json to identify unblocked work.
  • Create a high-level epic or a set of tasks and link them with dependencies to establish your multi-session workflow.

Frequently Asked Questions about beads

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

FAQPage Schema
How do I maintain persistent memory for complex tasks across multiple sessions?▼

Persistent memory across multiple sessions is maintained by capturing tasks in a structured database with dependency graphs and notes fields. This records COMPLETED, IN_PROGRESS, and NEXT states to reconstruct context and resume work after interruptions.

What is the best way to track dependencies in long-running feature development?▼

Tracking dependencies in long-running feature development is best handled by linking tasks with blocks, related, parent-child, and discovered-from relationships. This dependency graph organizes work and automatically unblocks subtasks as prerequisites are met.

How do I preserve task context and notes through context window compaction?▼

Task context and notes survive compaction by storing them in a structured persistent memory database. This database retains key decisions, blockers, and task states independently, ensuring context is reconstructed in future sessions.

Can I manage epics and subtasks for research projects that span weeks?▼

Yes, you can manage epics and subtasks for research projects spanning weeks. The system supports automatic unblocking and session handoff patterns, linking parent-child tasks to preserve the overall project structure and progress.

How do I identify unblocked work before starting a new session?▼

To identify unblocked work before starting a new session, run a readiness check command against the database. This queries the dependency graph and outputs available tasks, allowing you to quickly resume work without reviewing blocked items.

When do I need a dependency graph for issue tracking instead of a flat list?▼

A dependency graph for issue tracking is needed when tasks span days or weeks and require persistent memory. Unlike a flat list, it organizes work with blocks and parent-child links, making it essential for architecture decisions and complex research projects.