skills/beads/SKILL.md
Beads (bd) Dolt-backed issue tracker for agent task memory. Covers CLI ops, molecules, Dolt sync, Linear/Jira/GitLab. Use when tracking tasks and dependencies with the Beads CLI, syncing issues via Dolt, or integrating with Linear/Jira/GitLab. Keywords: bd, beads, Dolt, issue tracker.
npx skillsauth add itechmeat/llm-code beadsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Distributed, Dolt-backed (Git-like) graph issue tracker for AI coding agents. Persistent memory with dependency-aware task tracking.
Install: brew install beads or use the install scripts/binaries from the GitHub repo.
# Initialize in repo (humans run once)
bd init
# Tell your agent
echo "Use 'bd' for task tracking" >> AGENTS.md
blocks:, depends_on:)| Command | Action |
| ----------------------------- | ----------------------------------------- |
| bd ready | List tasks with no open blockers |
| bd ready --explain | Explain why tasks are or are not ready |
| bd ready --gated | Tasks waiting at gate checkpoints |
| bd ready --exclude-type=X | Exclude specific issue types |
| bd create "Title" -p 0 | Create P0 task |
| bd show <id> | View task details and audit trail |
| bd update <id> --status=X | Update status (open/in_progress/done) |
| bd close <id> | Close task |
| bd close <id> --claim-next | Close current task and claim next |
| bd dep add <child> <parent> | Link tasks (blocks, related, parent) |
| bd list | List issues (default: 50, non-closed) |
| bd list --format json | JSON output (alias for --json) |
| bd show --current | Show active issue (no ID needed) |
| bd update <id> --claim | Atomically claim issue for work |
| bd note <id> "text" | Append note (shorthand) |
| bd import -i <file> | Import JSONL incrementally |
| bd sync | Sync database state |
| bd dolt pull | Pull latest DB changes (advanced) |
| bd dolt push | Push DB changes (advanced) |
| bd bootstrap | Repair/bootstrap workspace identity |
| bd context | Show current workspace/task context |
| bd kv set <key> <value> | Store key-value pair |
| bd kv get <key> | Retrieve stored value |
| bd dolt show | Show Dolt connection/remote settings |
| bd config set-many | Apply multiple config changes in one step |
| bd ado sync | Sync with Azure DevOps work items |
| bd ado status | Check Azure DevOps sync status |
| bd ado projects | List Azure DevOps projects |
| bd gitlab sync | Sync with GitLab |
| bd github sync | Sync with GitHub Issues |
| bd remember | Write persistent agent memory |
| bd recall | Read persistent agent memory |
| bd purge | Delete closed ephemeral beads (wisps) |
Issues use hash-based IDs like bd-a1b2 to prevent merge conflicts:
bd create "Fix login bug" -p 1
# Created: bd-x7k3
bd show bd-x7k3
bd-a3f8 (Epic)
bd-a3f8.1 (Task)
bd-a3f8.1.1 (Sub-task)
Use bd children <id> to view hierarchy.
| File | Purpose | | --------------------------------------- | ------------------------------------- | | workflow.md | Daily operations, status flow, sync | | authoring.md | Writing quality issues, EARS patterns | | molecules.md | Molecules, gates, formulas, compounds | | sync.md | Dolt sync, upgrades, and integrations |
Beads stores issues in a Dolt database. Team synchronization happens via Dolt-style
pull/push, not by committing JSONL files into your repo history.
bd dep add bd-child bd-parent --blocks # child blocks parent
bd dep add bd-a bd-b --related # related items
bd ready # only shows unblocked work
Molecules group related issues with gates for incremental delivery:
bd mol create "Feature X" --steps=3 # Create 3-step molecule
bd mol progress bd-xyz # Check progress
bd mol burn bd-xyz # Complete molecule
Use Beads locally without committing to repo:
bd init --stealth
# Contributor (forked repos) — separate planning repo
bd init --contributor
# Maintainer auto-detected via SSH/HTTPS credentials
Config stored in .beads/config.yaml:
The exact schema evolves between releases. Prefer using CLI helpers to inspect and validate your current setup:
bd dolt show to see current Dolt connection/remote settingsbd dolt test to validate connectivitybd doctor / bd doctor --deep for health checksBeads uses Dolt as its primary backend. Depending on your setup, Dolt can run:
Use bd doctor (and bd doctor --server when applicable) to validate your
environment. For legacy stores, use bd migrate workflows.
Add to AGENTS.md:
## Task Tracking
Use `bd` for task tracking. Run `bd ready` to find work.
BD_AGENT_MODE=1 bd list --json # Ultra-compact JSON output
bd list --json # Standard JSON output
Beads includes Claude Code MCP plugin for direct integration.
bd -C changes working directory before running, bd close gains --reason-file, and setup/bootstrap flows gain better remote/server config handling.bd init --non-interactive / --role and bd bootstrap --non-interactive improve CI/cloud-agent setup.bd ready --explain, bd config set-many, batch dependency listing, and comma-separated status filters improve agent ergonomics.spike, story, and milestone are now first-class issue types; custom statuses/types moved to normalized tables.bd ado CLI commands (sync, status, projects) for work item tracking.bd note command: shorthand for appending notes to issues.--exclude-type flag: filter by issue type on bd ready and bd list.--format json alias: alternative to --json flag for consistency.interactions.jsonl.--agents-profile flag added.--validate checks --acceptance field; validation.on-close config.bd close --claim-next shortens the common close-and-claim-next loop for agents.bd create gains --skills, --context, and --no-history for richer task creation and optional Dolt-history suppression.bd import adds incremental JSONL import for portability and recovery workflows.bd init / bd bootstrap can auto-detect the Beads database from the repository git origin.BD_BACKUP_ENABLED=false support.# What to work on
bd ready # Unblocked tasks
bd ready --pretty # Formatted output
# Create with dependencies
bd create "Task B" --blocks bd-a1b2
bd create "Task C" --context "Need schema review" --skills "python,sql"
# Doctor (fix issues)
bd doctor # Check health
bd doctor --fix # Auto-fix problems
bd sync # Sync DB state
bd import -i backup.jsonl # Incremental JSONL import
bd dolt pull # Pull latest changes (advanced)
bd dolt push # Push to remote (advanced)
| ❌ Wrong | ✅ Correct |
| --------------------- | --------------------------- |
| priority: high | -p 1 (P0-P4 numeric) |
| Manual JSON editing | Use bd commands |
| Ignoring bd ready | Always check blockers first |
| Skipping bd sync | Sync before/after work |
| Creating without deps | Declare --blocks upfront |
data-ai
Zvec in-process vector database. Covers collections, indexing, embeddings, reranking, and persistence. Use when embedding Zvec into applications or tuning retrieval/storage behavior. Keywords: Zvec, HNSW-RaBitQ, vector database, ANN.
development
Vitest testing framework: Vite-powered tests, Jest-compatible API, mocking, snapshots, coverage, browser mode, and TypeScript support. Use when writing or configuring tests with Vitest, setting up mocking/snapshots, configuring coverage, or running browser-mode tests. Keywords: Vitest, testing, Vite, Jest, mocking, coverage.
tools
Vite next-gen frontend tooling: dev server, HMR, build, config, plugins, Environment API, Rolldown. Use when setting up or running a Vite project, configuring vite.config.*, authoring plugins, working with HMR or JS API, or managing environment variables and modes. Keywords: vite.config, bundler, Vite, HMR, Rolldown.
development
Orchestrate AI coding with Vibe Kanban: tasks, review, sessions, workspaces, and isolated git worktrees. Use when managing AI-generated code in isolated environments, planning coding tasks, reviewing AI output, or configuring Vibe Kanban workspaces and agents. Keywords: Vibe Kanban, AI orchestration, worktrees.