beads

Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.

10 stars

Best use case

beads is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.

Teams using beads should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/beads/SKILL.md --create-dirs "https://raw.githubusercontent.com/lambdamechanic/tooltest/main/skills/beads/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/beads/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How beads Compares

Feature / AgentbeadsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Beads (br) - Persistent Task Memory for AI Agents

Graph-based issue tracker that survives conversation compaction. Provides persistent memory for multi-session work with complex dependencies.

## br vs TodoWrite

| br (persistent) | TodoWrite (ephemeral) |
|-----------------|----------------------|
| Multi-session work | Single-session tasks |
| Complex dependencies | Linear execution |
| Survives compaction | Conversation-scoped |
| Git-backed, team sync | Local to session |

**Decision test**: "Will I need this context in 2 weeks?" -> YES = br

**When to use br**:
- Work spans multiple sessions or days
- Tasks have dependencies or blockers
- Need to survive conversation compaction
- Exploratory/research work with fuzzy boundaries
- Collaboration with team (git sync)

**When to use TodoWrite**:
- Single-session linear tasks
- Simple checklist for immediate work
- All context is in current conversation
- Will complete within current session

## Prerequisites

```bash
br version
```

- **br CLI** installed and in PATH
- **Git repository** (br stores issues in SQLite, exports to JSONL for git)
- **Fresh clone**: If `.beads/beads.db` is missing, hydrate it from `.beads/issues.jsonl`:
  - `br sync --import-only --db .beads/beads.db`

## CLI Reference

Run `br <command> --help` for specific command usage.

Essential commands: `br ready`, `br create`, `br show`, `br update`, `br close`, `br sync --flush-only`

## Session Protocol

1. `br ready` - Find unblocked work
2. `br show <id>` - Get full context
3. `br update <id> --status in_progress` - Start work
4. Add notes as you work (critical for compaction survival)
5. `br close <id> --reason "..."` - Complete task
6. Export issue changes and commit/push:
   - `br sync --flush-only`
   - `git add .beads/issues.jsonl && git commit -m "Update issues" && git push`

## Full Documentation

- `br --help`
- GitHub: https://github.com/Dicklesworthstone/beads_rust

Related Skills

tooltest-fix-loop

10
from lambdamechanic/tooltest

Use when running tooltest to validate MCP servers, interpret failures, and iterate fixes in this repo.

testing-patterns

10
from lambdamechanic/tooltest

Testing patterns and standards for this codebase, including async effects, fakes vs mocks, and property-based testing.

rust-guidelines

10
from lambdamechanic/tooltest

Pragmatic Rust conventions to keep code readable, testable, and performant for this project.

lambda-workflow

10
from lambdamechanic/tooltest

One lifecycle for Lambda repos: choose a br issue, start work, land the PR, and watch GitHub via Dumbwaiter MCP until it merges.

galahad

10
from lambdamechanic/tooltest

how to approach tests, types and coverage

bd-to-br-migration

10
from lambdamechanic/tooltest

Migrate docs from bd (beads) to br (beads_rust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.

plan-to-beads

9
from aspiers/ai-config

Decompose an approved implementation plan into self-contained beads issues with zero guesswork. Use when breaking down a plan file into actionable beads tasks.

beads

8
from mrf/beads-skill

Work with Beads issue tracker for AI agent memory. Use when managing tasks, tracking dependencies, filing issues, or maintaining context across coding sessions. Handles bd commands, issue graphs, and persistent agent memory.

kimchi:beads

7
from Tromml/kimchi

This command should be used to convert the final plan into standalone bead YAML task specifications for multi-agent execution. Ninth stage of the Kimchi planning pipeline. Produces .beads/ directory. Supports both ACFS and GasTown orchestration modes.

swe-cli-skills

12
from SylphAI-Inc/skills

Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms

DevOps & Infrastructure

PicoClaw Fleet

11
from EricGrill/agents-skills-plugins

Orchestrate a fleet of remote PicoClaw workers over SSH for fast, ephemeral one-shot tasks.

DevOps & Infrastructure

VibeCollab — Setup Instructions for AI Assistants

9
from flashpoint493/VibeCollab

You are helping a user set up VibeCollab in their project.

Workflow & Productivity