beads
Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.
What this skill does
This skill teaches effective use of **beads** (`bd`), a distributed git-backed issue tracker designed for AI agents. Use beads to track tasks, manage dependencies, and coordinate work across sessions.
## Getting Started
First, check if beads is available and initialized:
```bash
# Check if bd is installed
bd version
# Check if current project has beads initialized
bd status
```
**If `bd` is not installed**, ask the user which installation method they prefer:
- **npm:** `npm install -g @beads/bd`
- **Homebrew:** `brew install beads` (macOS)
- **Go:** `go install github.com/steveyegge/beads/cmd/bd@latest`
Do not install without user confirmation, as these are global system packages.
**If not initialized in the project**, run:
```bash
bd init
```
For personal use on shared projects (won't commit to repo):
```bash
bd init --stealth
```
For contributors on forked repos (routes to separate planning repo):
```bash
bd init --contributor
```
## Essential Commands
| Command | Purpose |
|---------|---------|
| `bd ready` | List tasks with no open blockers (what to work on next) |
| `bd create "Title" -p 1` | Create a task (priority 0-3, lower = higher priority) |
| `bd show <id>` | View task details and dependencies |
| `bd list` | List all open issues |
| `bd close <id>` | Mark task as complete |
| `bd update <id> --status in_progress` | Update task status |
| `bd dep add <child> <parent>` | Create dependency (child blocked by parent) |
| `bd sync` | Force immediate sync to git |
**Always use `--json` flag** for machine-readable output when parsing results.
## Task Hierarchy
Beads supports hierarchical IDs for organizing work:
- `bd-a3f8` — Epic (large feature)
- `bd-a3f8.1` — Task under epic
- `bd-a3f8.1.1` — Sub-task
Create hierarchical tasks:
```bash
bd create "Epic: User Authentication" -t epic -p 1
bd create "Implement login flow" -p 1 --parent bd-a3f8
```
## Session Workflow
### Starting a Session
```bash
# See what's ready to work on
bd ready --json
# Pick a task and mark it in progress
bd update <id> --status in_progress
# View full details
bd show <id> --json
```
### During Work
```bash
# Create new tasks as you discover them
bd create "Fix edge case in validation" -p 2
# Add dependencies
bd dep add <new-task> <blocking-task>
# Update task with notes
bd update <id> --notes "Found issue with timezone handling"
```
### Ending a Session ("Land the Plane")
When finishing work, complete ALL these steps:
```bash
# 1. File issues for remaining work
bd create "TODO: Add integration tests" -p 2
# 2. Close completed tasks
bd close <id> --reason "Completed"
# 3. Sync and push (MANDATORY)
git pull --rebase
bd sync
git push
# 4. Verify push succeeded
git status # Must show "up to date with origin"
# 5. Identify next task for follow-up
bd ready --json
```
**CRITICAL**: Always push before ending a session. Unpushed work causes coordination problems in multi-agent workflows.
## Important Rules
### DO use `bd update` with flags
```bash
bd update <id> --description "new description"
bd update <id> --title "new title"
bd update <id> --design "design notes"
bd update <id> --notes "additional notes"
bd update <id> --acceptance "acceptance criteria"
bd update <id> --status in_progress
```
### DO NOT use `bd edit`
The `edit` command opens an interactive editor (`$EDITOR`) which AI agents cannot use. Always use `bd update` with flags instead.
### DO sync before ending sessions
```bash
bd sync # Forces immediate export, commit, and push
```
Without `bd sync`, changes sit in a 30-second debounce window and may not be committed.
### DO include issue IDs in commit messages
```bash
git commit -m "Fix auth validation bug (bd-abc)"
```
This enables `bd doctor` to detect orphaned issues.
## Dependency Types
```bash
# Hard blocker - child cannot start until parent is done
bd dep add <child> <parent> --type blocks
# Soft link - related but not blocking
bd dep add <issue1> <issue2> --type related
# Parent-child - hierarchical relationship
bd dep add <child> <parent> --type parent-child
```
## Handling Merge Conflicts
If conflicts occur in `.beads/issues.jsonl`:
```bash
# Accept remote version
git checkout --theirs .beads/issues.jsonl
# Re-import to database
bd import -i .beads/issues.jsonl
# Continue with your work
```
## Git Hooks (Recommended)
Install hooks for automatic sync:
```bash
bd hooks install
```
This prevents stale JSONL problems by auto-syncing on commit, merge, push, and checkout.
## MCP Server Alternative
For tighter integration, beads also offers an MCP server (`beads-mcp`) that provides tools directly to your agent. Install via:
```bash
pip install beads-mcp
```
The CLI (`bd`) and MCP server work with the same underlying database.
## Quick Reference
```bash
# What should I work on?
bd ready
# Create a task
bd create "Fix bug in login" -p 1
# Start working
bd update bd-xyz --status in_progress
# Done working
bd close bd-xyz --reason "Completed"
bd sync
git push
```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.