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.
Manages persistent task memory across sessions using a git-backed issue tracker for complex, multi-session work.
/plugin marketplace add steveyegge/beads/plugin install beads@beads-marketplaceThis skill is limited to using the following tools:
CLAUDE.mdREADME.mdadr/0001-bd-prime-as-source-of-truth.mdresources/AGENTS.mdresources/ASYNC_GATES.mdresources/BOUNDARIES.mdresources/CHEMISTRY_PATTERNS.mdresources/CLI_REFERENCE.mdresources/DEPENDENCIES.mdresources/INTEGRATION_PATTERNS.mdresources/ISSUE_CREATION.mdresources/MOLECULES.mdresources/PATTERNS.mdresources/RESUMABILITY.mdresources/STATIC_DATA.mdresources/TROUBLESHOOTING.mdresources/WORKFLOWS.mdresources/WORKTREES.mdGraph-based issue tracker that survives conversation compaction. Provides persistent memory for multi-session work with complex dependencies.
| bd (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 = bd
When to use bd:
When to use TodoWrite:
bd --version # Requires v0.47.0+
bd init run once (humans do this, not agents)Run bd prime for AI-optimized workflow context (auto-loaded by hooks).
Run bd <command> --help for specific command usage.
Essential commands: bd ready, bd create, bd show, bd update, bd close, bd dolt push
bd ready — Find unblocked workbd show <id> — Get full contextbd update <id> --claim — Claim and start work atomicallybd close <id> --reason "..." — Complete taskbd dolt push — Push to Dolt remote (if configured)| Feature | CLI | Resource |
|---|---|---|
| Molecules (templates) | bd mol --help | MOLECULES.md |
| Chemistry (pour/wisp) | bd pour, bd wisp | CHEMISTRY_PATTERNS.md |
| Agent beads | bd agent --help | AGENTS.md |
| Async gates | bd gate --help | ASYNC_GATES.md |
| Worktrees | bd worktree --help | WORKTREES.md |
| Resource | Content |
|---|---|
| BOUNDARIES.md | bd vs TodoWrite detailed comparison |
| CLI_REFERENCE.md | Complete command syntax |
| DEPENDENCIES.md | Dependency system deep dive |
| INTEGRATION_PATTERNS.md | TodoWrite and tool integration |
| ISSUE_CREATION.md | When and how to create issues |
| MOLECULES.md | Proto definitions, component labels |
| PATTERNS.md | Common usage patterns |
| RESUMABILITY.md | Compaction survival guide |
| STATIC_DATA.md | Database schema reference |
| TROUBLESHOOTING.md | Error handling and fixes |
| WORKFLOWS.md | Step-by-step workflow patterns |
| AGENTS.md | Agent bead tracking (v0.40+) |
| ASYNC_GATES.md | Human-in-the-loop gates |
| CHEMISTRY_PATTERNS.md | Mol vs Wisp decision tree |
| WORKTREES.md | Parallel development patterns |
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.