bees
Guide for using Bees, a lightweight SQLite-backed local issue tracker. Use when managing issues, tracking dependencies, exporting for AI context, or running local-first project management.
What this skill does
# Bees - Lightweight SQLite-Backed Issue Tracker
This skill activates when working with Bees for issue tracking, dependency management, and AI-augmented workflows.
## When to Use This Skill
Activate when:
- Managing issues with dependencies in a local repository
- Exporting issue context for AI agents (`bees prime`)
- Tracking issue hierarchies and dependency graphs
- Needing SQLite-backed performance for large issue sets
- Syncing issues to JSONL for portability (`bees sync`)
- Working with AI agents that need structured task queues
## What is Bees?
Bees is a lightweight, local-first issue tracker designed for AI-augmented development:
- **SQLite storage**: WAL-mode SQLite database for fast queries
- **Single binary**: Written in Zig, compiles to a small static binary
- **AI-augmented**: `bees prime` outputs markdown for LLM context, `bees sync` exports JSONL
- **Dependency-aware**: Query ready issues with `bees ready`, supports blocks/related/parent-child
- **VS Code integration**: Compatible with beads VS Code extensions via `.beads` symlink
- **Local-first**: No server required, everything stored in `.bees/` directory
## Installation
### mise (Preferred)
Add to your `mise.toml`:
```toml
[tools."github:ctxshift/bees"]
version = "latest"
[tools."github:ctxshift/bees".platforms]
linux-x64 = { asset_pattern = "bees-linux-x86_64.tar.gz" }
linux-arm64 = { asset_pattern = "bees-linux-aarch64.tar.gz" }
macos-arm64 = { asset_pattern = "bees-macos-aarch64.tar.gz" }
macos-x64 = { asset_pattern = "bees-macos-x86_64.tar.gz" }
```
See `templates/mise.toml` for the full mise task definitions.
### Pre-built Binaries
Download from [GitHub Releases](https://github.com/ctxshift/bees/releases):
| Platform | Asset |
|----------|-------|
| Linux x86_64 | `bees-linux-x86_64.tar.gz` |
| Linux aarch64 | `bees-linux-aarch64.tar.gz` |
| macOS aarch64 | `bees-macos-aarch64.tar.gz` |
| macOS x86_64 | `bees-macos-x86_64.tar.gz` |
### Build from Source
Requires Zig 0.15.0+:
```bash
git clone https://github.com/ctxshift/bees.git
cd bees
zig build -Doptimize=ReleaseSafe
```
## Getting Started
### Initialize Bees
```bash
bees init
```
Creates the `.bees/` directory with SQLite database and configuration.
### Create an Issue
```bash
bees create "Implement user authentication"
```
### List Issues
```bash
bees list
```
### Show Issue Details
```bash
bees show <id>
```
### Close an Issue
```bash
bees close <id>
```
### Find Ready Issues
```bash
bees ready
```
Returns issues with no unresolved dependencies.
## Commands Reference
### create
Create a new issue:
```bash
bees create "Title"
bees create "Title" -d "Description text"
bees create "Title" -l "bug,priority:high"
bees create "Title" -a "alice" -o "bob"
bees create "Title" -p <parent-id>
```
Flags:
- `-d` / `--description`: Issue description
- `-l` / `--labels`: Comma-separated labels
- `-a` / `--assignee`: Assignee name
- `-o` / `--owner`: Owner name
- `-p` / `--parent`: Parent issue ID
### list
List issues with filtering:
```bash
bees list
bees list --status open
bees list --status closed
bees list --labels "bug"
bees list --assignee "alice"
bees list --json
```
### show
Show issue details:
```bash
bees show <id>
bees show <id> --json
```
### update
Update issue fields:
```bash
bees update <id> -d "Updated description"
bees update <id> -a "bob"
bees update <id> --status in_progress
```
### close
Close an issue:
```bash
bees close <id>
bees close <id> -r "Completed in PR #42"
```
The `-r` flag adds a closing reason.
### ready
List issues with no unresolved dependencies:
```bash
bees ready
bees ready --json
bees ready --labels "priority:high"
```
### dep
Manage dependencies between issues:
```bash
bees dep add <id> <blocker-id> # id depends on blocker-id
bees dep add <id> <related-id> -t related # related relationship
bees dep remove <id> <blocker-id>
bees dep list <id>
```
Dependency types (via `-t` flag):
- `blocks` (default): Blocker relationship
- `related`: Related issue, no blocking
- `parent`: Parent-child hierarchy
### label
Manage labels on issues:
```bash
bees label add <id> "bug,priority:high"
bees label remove <id> "wip"
```
### comment
Add and list comments on issues:
```bash
bees comment add <id> "Working on this now"
bees comment list <id>
```
### config
View and set configuration:
```bash
bees config # Show current config
bees config set key value # Set a config value
bees config get key # Get a config value
```
### sync
Export issues to JSONL format:
```bash
bees sync
```
Writes issues from the SQLite database to `issues.jsonl` in the `.bees/` directory. This is a one-directional export (database to JSONL).
### prime
Generate markdown output for LLM context:
```bash
bees prime
bees prime --status open
bees prime --labels "sprint:current"
```
Outputs a formatted markdown summary of issues suitable for including in AI agent prompts.
## Dependency Management
### Dependency Types
Bees supports three relationship types between issues:
| Type | Flag | Behavior |
|------|------|----------|
| blocks | `-t blocks` (default) | Prevents `bees ready` from showing dependent issue |
| related | `-t related` | Informational link, no blocking |
| parent | `-t parent` | Parent-child hierarchy |
### Ready Queue
`bees ready` returns issues where:
- Status is `open`
- No open `blocks` dependencies remain
- Parent issues (if any) are still open
### Cycle Detection
Bees detects circular dependencies and rejects them:
```bash
bees dep add taskA taskB
bees dep add taskB taskA # Error: would create cycle
```
## AI Integration
### bees sync (JSONL Export)
Export all issues to JSONL for external tooling:
```bash
bees sync
# Writes .bees/issues.jsonl
```
The JSONL file contains one JSON object per line, compatible with standard data processing tools.
### bees prime (Markdown for LLMs)
Generate a markdown summary for LLM context windows:
```bash
bees prime
```
Output includes issue titles, descriptions, labels, dependencies, and status in a readable markdown format. Pipe directly into agent prompts or save to file.
### JSON Output
All list commands support `--json` for machine-readable output:
```bash
bees list --json
bees ready --json
bees show <id> --json
```
### Parse JSON in Scripts
```bash
# Get first ready issue ID
TASK_ID=$(bees ready --json | jq -r '.[0].id')
# Count open issues
bees list --json | jq 'length'
# Get issue titles
bees list --json | jq -r '.[].title'
```
## Storage and File Structure
```
.bees/
├── bees.db # SQLite database (WAL mode) - primary storage
├── issues.jsonl # JSONL export (created by bees sync)
├── metadata.json # Repository metadata
├── config.json # Local configuration
└── .beads # Symlink for VS Code extension compatibility
```
### SQLite as Primary Storage
Unlike beads (which uses JSONL as primary with SQLite cache), bees uses SQLite as the primary data store:
- WAL mode for concurrent read access
- No need for `rebuild` commands
- `bees sync` exports to JSONL for portability
### The .beads Symlink
Bees creates a `.beads` symlink pointing to the `.bees/` directory. This enables compatibility with VS Code extensions designed for beads (`vscode-beads` and `beads-kanban`).
## Workflow Examples
### PR-Based Development Workflow
#### Session Start
```bash
git checkout main && git pull
bees ready # Find available issues
bees show <id> # Read requirements
```
#### Issue Execution
```bash
git checkout -b feature/<name>
bees update <id> --status in_progress
# Do the work:
# - Read existing code to understand patterns
# - Implement following project conventions
# - Run quality gates (tests, linters, formatters)
git add <files>
git commit -m "type(scope): description"
```
#### PR Creation
```bash
git push -u origin <branch>
gh pr create --title "type(scope): description" --body "- Related in Data & Analytics
clawarr-suite
IncludedComprehensive management for self-hosted media stacks (Sonarr, Radarr, Lidarr, Readarr, Prowlarr, Bazarr, Overseerr, Plex, Tautulli, SABnzbd, Recyclarr, Unpackerr, Notifiarr, Maintainerr, Kometa, FlareSolverr). Deep library exploration, analytics, dashboard generation, content management, request handling, subtitle management, indexer control, download monitoring, quality profile sync, library cleanup automation, notification routing, collection/overlay management, and media tracker integration (Trakt, Letterboxd, Simkl).
querying-soql
IncludedSOQL query generation, optimization, and analysis with 100-point scoring. Use this skill when the user needs SOQL/SOSL authoring or optimization: natural-language-to-query generation, relationship queries, aggregates, query-plan analysis, and performance or safety improvements for Salesforce queries. TRIGGER when: user writes, optimizes, or debugs SOQL/SOSL queries, touches .soql files, or asks about relationship queries, aggregates, or query performance. DO NOT TRIGGER when: bulk data operations (use handling-sf-data), Apex DML logic (use generating-apex), or report/dashboard queries.
app-store-optimization
IncludedApp Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklists, and tracking ranking changes.
habit-flow
IncludedAI-powered atomic habit tracker with natural language logging, streak tracking, smart reminders, and coaching. Use for creating habits, logging completions naturally ("I meditated today"), viewing progress, and getting personalized coaching.
app-store-optimization
IncludedApp Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklists, and tracking ranking changes.
visualizing-data
IncludedBuilds dashboards, reports, and data-driven interfaces requiring charts, graphs, or visual analytics. Provides systematic framework for selecting appropriate visualizations based on data characteristics and analytical purpose. Includes 24+ visualization types organized by purpose (trends, comparisons, distributions, relationships, flows, hierarchies, geospatial), accessibility patterns (WCAG 2.1 AA compliance), colorblind-safe palettes, and performance optimization strategies. Use when creating visualizations, choosing chart types, displaying data graphically, or designing data interfaces.