beads/docs/CLI_REFERENCE.md

CLI Command Reference

For: AI agents and developers using bd command-line interface
Version: 0.21.0+

Quick Navigation

• Basic Operations
• Issue Management
• Dependencies & Labels
• Filtering & Search
• Advanced Operations
• Molecular Chemistry
• Database Management
• Editor Integration

Basic Operations

Check Status

# Check database path and daemon status
bd info --json

# Example output:
# {
#   "database_path": "/path/to/.beads/beads.db",
#   "issue_prefix": "bd",
#   "daemon_running": true,
#   "agent_mail_enabled": false
# }

Find Work

# Find ready work (no blockers)
bd ready --json

# Find stale issues (not updated recently)
bd stale --days 30 --json                    # Default: 30 days
bd stale --days 90 --status in_progress --json  # Filter by status
bd stale --limit 20 --json                   # Limit results

Issue Management

Create Issues

# Basic creation
# IMPORTANT: Always quote titles and descriptions with double quotes
bd create "Issue title" -t bug|feature|task -p 0-4 -d "Description" --json

# Create with explicit ID (for parallel workers)
bd create "Issue title" --id worker1-100 -p 1 --json

# Create with labels (--labels or --label work)
bd create "Issue title" -t bug -p 1 -l bug,critical --json
bd create "Issue title" -t bug -p 1 --label bug,critical --json

# Examples with special characters (all require quoting):
bd create "Fix: auth doesn't validate tokens" -t bug -p 1 --json
bd create "Add support for OAuth 2.0" -d "Implement RFC 6749 (OAuth 2.0 spec)" --json

# Create multiple issues from markdown file
bd create -f feature-plan.md --json

# Create with description from file (avoids shell escaping issues)
bd create "Issue title" --body-file=description.md --json
bd create "Issue title" --body-file description.md -p 1 --json

# Read description from stdin
echo "Description text" | bd create "Issue title" --body-file=- --json
cat description.md | bd create "Issue title" --body-file - -p 1 --json

# Create epic with hierarchical child tasks
bd create "Auth System" -t epic -p 1 --json         # Returns: bd-a3f8e9
bd create "Login UI" -p 1 --json                     # Auto-assigned: bd-a3f8e9.1
bd create "Backend validation" -p 1 --json           # Auto-assigned: bd-a3f8e9.2
bd create "Tests" -p 1 --json                        # Auto-assigned: bd-a3f8e9.3

# Create and link discovered work (one command)
bd create "Found bug" -t bug -p 1 --deps discovered-from:<parent-id> --json

Update Issues

# Update one or more issues
bd update <id> [<id>...] --status in_progress --json
bd update <id> [<id>...] --priority 1 --json

# Edit issue fields in $EDITOR (HUMANS ONLY - not for agents)
# NOTE: This command is intentionally NOT exposed via the MCP server
# Agents should use 'bd update' with field-specific parameters instead
bd edit <id>                    # Edit description
bd edit <id> --title            # Edit title
bd edit <id> --design           # Edit design notes
bd edit <id> --notes            # Edit notes
bd edit <id> --acceptance       # Edit acceptance criteria

Close/Reopen Issues

# Complete work (supports multiple IDs)
bd close <id> [<id>...] --reason "Done" --json

# Reopen closed issues (supports multiple IDs)
bd reopen <id> [<id>...] --reason "Reopening" --json

View Issues

# Show dependency tree
bd dep tree <id>

# Get issue details (supports multiple IDs)
bd show <id> [<id>...] --json

Dependencies & Labels

Dependencies

# Link discovered work (old way - two commands)
bd dep add <discovered-id> <parent-id> --type discovered-from

# Create and link in one command (new way - preferred)
bd create "Issue title" -t bug -p 1 --deps discovered-from:<parent-id> --json

Labels

# Label management (supports multiple IDs)
bd label add <id> [<id>...] <label> --json
bd label remove <id> [<id>...] <label> --json
bd label list <id> --json
bd label list-all --json

Filtering & Search

Basic Filters

# Filter by status, priority, type
bd list --status open --priority 1 --json               # Status and priority
bd list --assignee alice --json                         # By assignee
bd list --type bug --json                               # By issue type
bd list --id bd-123,bd-456 --json                       # Specific IDs

Label Filters

# Labels (AND: must have ALL)
bd list --label bug,critical --json

# Labels (OR: has ANY)
bd list --label-any frontend,backend --json

Text Search

# Title search (substring)
bd list --title "auth" --json

# Pattern matching (case-insensitive substring)
bd list --title-contains "auth" --json                  # Search in title
bd list --desc-contains "implement" --json              # Search in description
bd list --notes-contains "TODO" --json                  # Search in notes

Date Range Filters

# Date range filters (YYYY-MM-DD or RFC3339)
bd list --created-after 2024-01-01 --json               # Created after date
bd list --created-before 2024-12-31 --json              # Created before date
bd list --updated-after 2024-06-01 --json               # Updated after date
bd list --updated-before 2024-12-31 --json              # Updated before date
bd list --closed-after 2024-01-01 --json                # Closed after date
bd list --closed-before 2024-12-31 --json               # Closed before date

Empty/Null Checks

# Empty/null checks
bd list --empty-description --json                      # Issues with no description
bd list --no-assignee --json                            # Unassigned issues
bd list --no-labels --json                              # Issues with no labels

Priority Ranges

# Priority ranges
bd list --priority-min 0 --priority-max 1 --json        # P0 and P1 only
bd list --priority-min 2 --json                         # P2 and below

Combine Filters

# Combine multiple filters
bd list --status open --priority 1 --label-any urgent,critical --no-assignee --json

Global Flags

Global flags work with any bd command and must appear before the subcommand.

Sandbox Mode

Auto-detection (v0.21.1+): bd automatically detects sandboxed environments and enables sandbox mode.

When detected, you'll see: ℹ️ Sandbox detected, using direct mode

Manual override:

# Explicitly enable sandbox mode
bd --sandbox <command>

# Equivalent to combining these flags:
bd --no-daemon --no-auto-flush --no-auto-import <command>

What it does:

• Disables daemon (uses direct SQLite mode)
• Disables auto-export to JSONL
• Disables auto-import from JSONL

When to use: Sandboxed environments where daemon can't be controlled (permission restrictions), or when auto-detection doesn't trigger.

Staleness Control

# Skip staleness check (emergency escape hatch)
bd --allow-stale <command>

# Example: access database even if out of sync with JSONL
bd --allow-stale ready --json
bd --allow-stale list --status open --json

Shows: ⚠️ Staleness check skipped (--allow-stale), data may be out of sync

⚠️ Caution: May show stale or incomplete data. Use only when stuck and other options fail.

Force Import

# Force metadata update even when DB appears synced
bd import --force -i .beads/issues.jsonl

When to use: bd import reports "0 created, 0 updated" but staleness errors persist.

Shows: Metadata updated (database already in sync with JSONL)

Other Global Flags

# JSON output for programmatic use
bd --json <command>

# Force direct mode (bypass daemon)
bd --no-daemon <command>

# Disable auto-sync
bd --no-auto-flush <command>    # Disable auto-export to JSONL
bd --no-auto-import <command>   # Disable auto-import from JSONL

# Custom database path
bd --db /path/to/.beads/beads.db <command>

# Custom actor for audit trail
bd --actor alice <command>

See also:

• TROUBLESHOOTING.md - Sandboxed environments for detailed sandbox troubleshooting
• DAEMON.md for daemon mode details

Advanced Operations

Cleanup

# Clean up closed issues (bulk deletion)
bd admin cleanup --force --json                                   # Delete ALL closed issues
bd admin cleanup --older-than 30 --force --json                   # Delete closed >30 days ago
bd admin cleanup --dry-run --json                                 # Preview what would be deleted
bd admin cleanup --older-than 90 --cascade --force --json         # Delete old + dependents

Duplicate Detection & Merging

# Find and merge duplicate issues
bd duplicates                                          # Show all duplicates
bd duplicates --auto-merge                             # Automatically merge all
bd duplicates --dry-run                                # Preview merge operations

# Merge specific duplicate issues
bd merge <source-id...> --into <target-id> --json      # Consolidate duplicates
bd merge bd-42 bd-43 --into bd-41 --dry-run            # Preview merge

Compaction (Memory Decay)

# Agent-driven compaction
bd admin compact --analyze --json                           # Get candidates for review
bd admin compact --analyze --tier 1 --limit 10 --json       # Limited batch
bd admin compact --apply --id bd-42 --summary summary.txt   # Apply compaction
bd admin compact --apply --id bd-42 --summary - < summary.txt  # From stdin
bd admin compact --stats --json                             # Show statistics

# Legacy AI-powered compaction (requires ANTHROPIC_API_KEY)
bd admin compact --auto --dry-run --all                     # Preview
bd admin compact --auto --all --tier 1                      # Auto-compact tier 1

# Restore compacted issue from git history
bd restore <id>  # View full history at time of compaction

Rename Prefix

# Rename issue prefix (e.g., from 'knowledge-work-' to 'kw-')
bd rename-prefix kw- --dry-run  # Preview changes
bd rename-prefix kw- --json     # Apply rename

Molecular Chemistry

Beads uses a chemistry metaphor for template-based workflows. See MOLECULES.md for full documentation.

Phase Transitions

Phase	State	Storage	Command
Solid	Proto	.beads/	bd formula list
Liquid	Mol	.beads/	bd mol pour
Vapor	Wisp	.beads/ (Ephemeral=true, not exported)	bd mol wisp

Proto/Template Commands

# List available formulas (templates)
bd formula list --json

# Show proto structure and variables
bd mol show <proto-id> --json

# Extract proto from ad-hoc epic
bd mol distill <epic-id> --json

Pour (Proto to Mol)

# Instantiate proto as persistent mol (solid → liquid)
bd mol pour <proto-id> --var key=value --json

# Preview what would be created
bd mol pour <proto-id> --var key=value --dry-run

# Assign root issue
bd mol pour <proto-id> --var key=value --assignee alice --json

# Attach additional protos during pour
bd mol pour <proto-id> --attach <other-proto> --json

Wisp Commands

# Instantiate proto as ephemeral wisp (solid → vapor)
bd mol wisp <proto-id> --var key=value --json

# List all wisps
bd mol wisp list --json
bd mol wisp list --all --json    # Include closed

# Garbage collect orphaned wisps
bd mol wisp gc --json
bd mol wisp gc --age 24h --json  # Custom age threshold
bd mol wisp gc --dry-run         # Preview what would be cleaned

Bonding (Combining Work)

# Polymorphic combine - handles proto+proto, proto+mol, mol+mol
bd mol bond <A> <B> --json

# Bond types
bd mol bond <A> <B> --type sequential --json   # B runs after A (default)
bd mol bond <A> <B> --type parallel --json     # B runs alongside A
bd mol bond <A> <B> --type conditional --json  # B runs only if A fails

# Phase control
bd mol bond <proto> <mol> --pour --json   # Force persistent spawn
bd mol bond <proto> <mol> --wisp --json   # Force ephemeral spawn

# Dynamic bonding (custom child IDs)
bd mol bond <proto> <mol> --ref arm-{{name}} --var name=ace --json

# Preview bonding
bd mol bond <A> <B> --dry-run

Squash (Wisp to Digest)

# Compress wisp to permanent digest
bd mol squash <ephemeral-id> --json

# With agent-provided summary
bd mol squash <ephemeral-id> --summary "Work completed" --json

# Preview
bd mol squash <ephemeral-id> --dry-run

# Keep wisp children after squash
bd mol squash <ephemeral-id> --keep-children --json

Burn (Discard Wisp)

# Delete wisp without digest (destructive)
bd mol burn <ephemeral-id> --json

# Preview
bd mol burn <ephemeral-id> --dry-run

# Skip confirmation
bd mol burn <ephemeral-id> --force --json

Note: Most mol commands require --no-daemon flag when daemon is running.

Database Management

Import/Export

# Import issues from JSONL
bd import -i .beads/issues.jsonl --dry-run      # Preview changes
bd import -i .beads/issues.jsonl                # Import and update issues
bd import -i .beads/issues.jsonl --dedupe-after # Import + detect duplicates

# Handle missing parents during import
bd import -i issues.jsonl --orphan-handling allow      # Default: import orphans without validation
bd import -i issues.jsonl --orphan-handling resurrect  # Auto-resurrect deleted parents as tombstones
bd import -i issues.jsonl --orphan-handling skip       # Skip orphans with warning
bd import -i issues.jsonl --orphan-handling strict     # Fail if parent is missing

# Configure default orphan handling behavior
bd config set import.orphan_handling "resurrect"
bd sync  # Now uses resurrect mode by default

Orphan handling modes:

• allow (default) - Import orphaned children without parent validation. Most permissive, ensures no data loss even if hierarchy is temporarily broken.
• resurrect - Search JSONL history for deleted parents and recreate them as tombstones (Status=Closed, Priority=4). Preserves hierarchy with minimal data. Dependencies are also resurrected on best-effort basis.
• skip - Skip orphaned children with warning. Partial import succeeds but some issues are excluded.
• strict - Fail import immediately if a child's parent is missing. Use when database integrity is critical.

When to use:

• Use allow (default) for daily imports and auto-sync
• Use resurrect when importing from databases with deleted parents
• Use strict for controlled imports requiring guaranteed parent existence
• Use skip rarely - only for selective imports

See CONFIG.md and TROUBLESHOOTING.md for more details.

Migration

# Migrate databases after version upgrade
bd migrate                                             # Detect and migrate old databases
bd migrate --dry-run                                   # Preview migration
bd migrate --cleanup --yes                             # Migrate and remove old files

# AI-supervised migration (check before running bd migrate)
bd migrate --inspect --json                            # Show migration plan for AI agents
bd info --schema --json                                # Get schema, tables, config, sample IDs

Migration workflow for AI agents:

1. Run --inspect to see pending migrations and warnings
2. Check for missing_config (like issue_prefix)
3. Review invariants_to_check for safety guarantees
4. If warnings exist, fix config issues first
5. Then run bd migrate safely

Migration safety invariants:

• required_config_present: Ensures issue_prefix and schema_version are set
• foreign_keys_valid: No orphaned dependencies or labels
• issue_count_stable: Issue count doesn't decrease unexpectedly

These invariants prevent data loss and would have caught issues like GH #201 (missing issue_prefix after migration).

Daemon Management

See docs/DAEMON.md for complete daemon management reference.

# List all running daemons
bd daemons list --json

# Check health (version mismatches, stale sockets)
bd daemons health --json

# Stop/restart specific daemon
bd daemons stop /path/to/workspace --json
bd daemons restart 12345 --json  # By PID

# View daemon logs
bd daemons logs /path/to/workspace -n 100
bd daemons logs 12345 -f  # Follow mode

# Stop all daemons
bd daemons killall --json
bd daemons killall --force --json  # Force kill if graceful fails

Sync Operations

# Manual sync (force immediate export/import/commit/push)
bd sync

# What it does:
# 1. Export pending changes to JSONL
# 2. Commit to git
# 3. Pull from remote
# 4. Import any updates
# 5. Push to remote

Issue Types

• bug - Something broken that needs fixing
• feature - New functionality
• task - Work item (tests, docs, refactoring)
• epic - Large feature composed of multiple issues (supports hierarchical children)
• chore - Maintenance work (dependencies, tooling)

Hierarchical children: Epics can have child issues with dotted IDs (e.g., bd-a3f8e9.1, bd-a3f8e9.2). Children are auto-numbered sequentially. Up to 3 levels of nesting supported.

Issue Statuses

• open - Ready to be worked on
• in_progress - Currently being worked on
• blocked - Cannot proceed (waiting on dependencies)
• deferred - Deliberately put on ice for later
• closed - Work completed
• tombstone - Deleted issue (suppresses resurrections)
• pinned - Stays open indefinitely (used for hooks, anchors)

Note: The pinned status is used by Gas Town for hook management and persistent work items that should never be auto-closed or cleaned up.

Priorities

• 0 - Critical (security, data loss, broken builds)
• 1 - High (major features, important bugs)
• 2 - Medium (nice-to-have features, minor bugs)
• 3 - Low (polish, optimization)
• 4 - Backlog (future ideas)

Dependency Types

• blocks - Hard dependency (issue X blocks issue Y)
• related - Soft relationship (issues are connected)
• parent-child - Epic/subtask relationship
• discovered-from - Track issues discovered during work

Only blocks dependencies affect the ready work queue.

Note: When creating an issue with a discovered-from dependency, the new issue automatically inherits the parent's source_repo field.

Output Formats

JSON Output (Recommended for Agents)

Always use --json flag for programmatic use:

# Single issue
bd show bd-42 --json

# List of issues
bd ready --json

# Operation result
bd create "Issue" -p 1 --json

Human-Readable Output

Default output without --json:

bd ready
# bd-42  Fix authentication bug  [P1, bug, in_progress]
# bd-43  Add user settings page  [P2, feature, open]

Common Patterns for AI Agents

Claim and Complete Work

# 1. Find available work
bd ready --json

# 2. Claim issue
bd update bd-42 --status in_progress --json

# 3. Work on it...

# 4. Close when done
bd close bd-42 --reason "Implemented and tested" --json

Discover and Link Work

# While working on bd-100, discover a bug

# Old way (two commands):
bd create "Found auth bug" -t bug -p 1 --json  # Returns bd-101
bd dep add bd-101 bd-100 --type discovered-from

# New way (one command):
bd create "Found auth bug" -t bug -p 1 --deps discovered-from:bd-100 --json

Batch Operations

# Update multiple issues at once
bd update bd-41 bd-42 bd-43 --priority 0 --json

# Close multiple issues
bd close bd-41 bd-42 bd-43 --reason "Batch completion" --json

# Add label to multiple issues
bd label add bd-41 bd-42 bd-43 urgent --json

Session Workflow

# Start of session
bd ready --json  # Find work

# During session
bd create "..." -p 1 --json
bd update bd-42 --status in_progress --json
# ... work ...

# End of session (IMPORTANT!)
bd sync  # Force immediate sync, bypass debounce

ALWAYS run bd sync at end of agent sessions to ensure changes are committed/pushed immediately.

Editor Integration

Setup Commands

# Setup editor integration (choose based on your editor)
bd setup factory  # Factory.ai Droid - creates/updates AGENTS.md (universal standard)
bd setup claude   # Claude Code - installs SessionStart/PreCompact hooks
bd setup cursor   # Cursor IDE - creates .cursor/rules/beads.mdc
bd setup aider    # Aider - creates .aider.conf.yml

# Check if integration is installed
bd setup factory --check
bd setup claude --check
bd setup cursor --check
bd setup aider --check

# Remove integration
bd setup factory --remove
bd setup claude --remove
bd setup cursor --remove
bd setup aider --remove

Claude Code options:

bd setup claude              # Install globally (~/.claude/settings.json)
bd setup claude --project    # Install for this project only
bd setup claude --stealth    # Use stealth mode (flush only, no git operations)

What each setup does:

• Factory.ai (bd setup factory): Creates or updates AGENTS.md with beads workflow instructions (works with multiple AI tools using the AGENTS.md standard)
• Claude Code (bd setup claude): Adds hooks to Claude Code's settings.json that run bd prime on SessionStart and PreCompact events
• Cursor (bd setup cursor): Creates .cursor/rules/beads.mdc with workflow instructions
• Aider (bd setup aider): Creates .aider.conf.yml with bd workflow instructions

See also:

• INSTALLING.md - Installation guide
• AIDER_INTEGRATION.md - Detailed Aider guide
• CLAUDE_INTEGRATION.md - Claude integration design

See Also

• AGENTS.md - Main agent workflow guide
• MOLECULES.md - Molecular chemistry metaphor (protos, pour, bond, squash, burn)
• DAEMON.md - Daemon management and event-driven mode
• GIT_INTEGRATION.md - Git workflows and merge strategies
• LABELS.md - Label system guide
• README.md - User documentation