beads

Manage persistent dependency graphs and task lifecycles across sessions.

Updated Aug 30, 2024
One-click install
npx skills add https://github.com/minhtri2710/dotfiles --skill beads-minhtri2710
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: beads
Source: https://github.com/minhtri2710/dotfiles/tree/main/dot_config/opencode/skills/beads
Command: npx skills add https://github.com/minhtri2710/dotfiles --skill beads-minhtri2710

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Beads is a graph-based issue tracker that provides persistent memory across sessions. Use Beads when work spans multiple sessions, has complex dependencies, or requires maintaining context across compaction cycles. For simple single-session tasks, TodoWrite remains appropriate.

Core Features & Use Cases

  • Multi-session tracking: Work that spans days or compaction cycles.
  • Dependency graphs: Manage blockers, prerequisites, and hierarchies.
  • Project memory: Resume work later with preserved context.

Quick Start

bd ready --json bd create "Beads: Start multi-session task" -p 1 --json bd show <issue-id> --json

Frequently Asked Questions about beads

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

FAQPage Schema
How do I track work across multiple sessions without losing context?

Beads provides persistent memory for multi-session projects by storing tasks, dependencies, and metadata in a git-backed graph that survives conversation compaction. Use `bd ready --json` to resume where you left off.

Can I manage complex task dependencies and blockers in a single project?

Beads tracks blockers, prerequisites, and hierarchies through a dependency graph. Set task states (open, in_progress, blocked, closed) and query ready tasks with `bd ready --json` to surface unblocked work.

What's the difference between Beads and simple task lists for multi-session work?

Beads maintains a persistent dependency graph with audit trails, priority, labels, and type metadata across compaction cycles. Simple task lists lack cross-session memory and cannot model complex blocker relationships.

How do I create and organize tasks in a multi-session project?

Use `bd create "task name" -p [priority]` to add tasks, then link dependencies and set states. Beads stores all metadata and relationships so you resume with full context on the next session.

When should I use Beads instead of a single-session tracker?

Use Beads when work spans days, requires managing blockers and discovered-from relationships, or needs to persist across AI agent compaction. For single-session tasks, simpler trackers remain appropriate.