beads
Dolt-powered issue tracker for multi-session work with dependencies and persistent memory across conversation compaction.
Skill by taowang1993
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/taowang1993-beads
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/beads
Tools it pre-approves 1
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Write,Bash(bd:*),Bash(mkdir:*)
What's inside
- Skill name
beads- Description
- Dolt-powered 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. Trigger with "write a plan", "create task", "what's ready", "track this work", "resume after compaction". Make sure to use this skill whenever managing multi-session work, tracking dependencies, or recovering context.
- License
- MIT
- Allowed tools
- Read,Write,Bash(bd:*),Bash(mkdir:*)
- Instructions
- 114 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: contains an absolute path from the author's machine
Files (48)
- SKILL.md
- 0001-bd-prime-as-source-of-truth.md · adr/
- openai.yaml · agents/
- audit.md · commands/
- blocked.md · commands/
- close.md · commands/
- comments.md · commands/
- compact.md · commands/
- create.md · commands/
- decision.md · commands/
- delete.md · commands/
- dep.md · commands/
- epic.md · commands/
- export.md · commands/
- import.md · commands/
- init.md · commands/
- label.md · commands/
- list.md · commands/
- prime.md · commands/
- quickstart.md · commands/
- ready.md · commands/
- rename-prefix.md · commands/
- reopen.md · commands/
- restore.md · commands/
- search.md · commands/
- show.md · commands/
- stats.md · commands/
- sync.md · commands/
- template.md · commands/
- update.md · commands/
- version.md · commands/
- workflow.md · commands/
- planning.md · references/
- AGENTS.md · resources/
- ASYNC_GATES.md · resources/
- BOUNDARIES.md · resources/
- CHEMISTRY_PATTERNS.md · resources/
- CLI_REFERENCE.md · resources/
- DEPENDENCIES.md · resources/
- INTEGRATION_PATTERNS.md · resources/
- ISSUE_CREATION.md · resources/
- MOLECULES.md · resources/
- PATTERNS.md · resources/
- RESUMABILITY.md · resources/
- STATIC_DATA.md · resources/
- TROUBLESHOOTING.md · resources/
- WORKFLOWS.md · resources/
- WORKTREES.md · resources/
SKILL.md (first lines)
# Beads - Persistent Task Memory for AI Agents Graph-based issue tracker that survives conversation compaction. Provides persistent memory for multi-session work with complex dependencies. ## bd vs TodoWrite **Decision test**: "Will I need this context in 2 weeks?" YES = bd, NO = TodoWrite. | bd (persistent) | TodoWrite (ephemeral) | |-----------------|----------------------| | Multi-session, dependencies, compaction survival | Single-session linear tasks | | Dolt-backed team sync | Conversation-scoped | See [BOUNDARIES.md](resources/BOUNDARIES.md) for detailed comparison. ## Prerequisites ```bash bd --version # Requires v0.60.0+ ``` - **bd CLI** installed and in PATH - **Git repository** (optional — use `BEADS_DIR` + `--stealth` for git-free operation) - **Initialization**: `bd init` run once (humans do this, not agents) ## CLI Reference **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` ## Session Protocol 1. `bd ready` — Find unblocked work 2. `bd show <id>` — Get full context 3. `bd update <id> --claim` — Claim and start work atomically 4. Add notes as you work (critical for compaction survival) 5. `bd close <id> --reason "..."` — Complete task 6. `bd dolt push` — Push to Dolt remote (if configured) ## Planning Protocol When the user asks you to "write a plan", create both artifacts: 1. A markdown plan file in the repository's `.beads/plans/` directory. For Tockbot, use `/Users/max/projects/tockbot/.beads/plans/`. 2. A beads epic plus child issues that mirror the plan's vertical-slice work breakdown. Read [planning.md](references/planning.md) before drafting any non-trivial plan. Use a stable filename: `YYYY-MM-DD-short-slug.md`. Create `.beads/plans/` if it is missing. Synthesize from the existing conversation and codebase context first; ask only blocking questions. Keep the plan practical: problem, solution, non-goals, implementation/testing decisions, vertical slices, acceptance checks, risks, and the beads epic/issue IDs. Each child issue should be a tracer-bullet slice: a narrow, demoable path through the necessary layers, not a horizontal "database/API/UI" chunk. Publish blockers before dependents so their IDs can be referenced in dependent issues. After creating the epic, attach the plan path if the CLI supports it (`--spec-id .beads/plans/<file>.md` in current bd versions), or include the plan path in the epic description/notes. Skip the plan file only for tiny single-session tasks where an epic would also be overkill; say so explicitly. ## Output Append `--json` to any command for structured output. Use `bd show <id> --long` for extended metadata. Status icons: `○` open `◐` in_progress `●` blocked `✓` closed `❄` deferred. ## Error Handling | Error | Fix | |-------|-----| | `database not found` | `bd init <prefix>` in project root | | `not in a git repository` | `git init` first | | `disk I/O error (522)` | Move `.beads/` off cloud-synced filesystem | | Status updates lag | Use server mode: `bd dolt start` | See [TROUBLESHOOTING.md](resources/TROUBLESHOOTING.md) for full details. ## Examples **Track a multi-session feature:** ```bash bd create "OAuth integration" -t epic -p 1 --json bd create "Token storage" -t task --deps blocks:oauth-id --json bd ready --json # Shows unblocked work bd update <id> --claim --json # Claim and start bd close <id> --reason "Implemented with refresh tokens" --json ``` **Recover after compaction:** `bd list --status in_progress --json` then `bd show <id> --long` **Discover work mid-task:** `bd create "Found bug" -t bug -p 1 --deps discovered-from:<current-id> --json` ## Advanced Features | Feature | CLI | Resource | |---------|-----|----------| | Molecules (templates) | `bd mol --help` | [MOLECULES.md](resources/MOLECULES.md) | | Chemistry (pour/wisp) | `bd pour`, `bd wisp` | [CHEMISTRY_PATTERNS.md](resources/CHEMISTRY_PATTERNS.md) | | Agent beads | `bd agent --help` | [AGENTS.md](resources/AGENTS.md) | | Async gates | `bd gate --help` | [ASYNC_GATES.md](resources/ASYNC_GATES.md) | | Worktrees | `bd worktree --help` | [WORKTREES.md](resources/WORKTREES.md) | ## Resources | Category | Files | |----------|-------| | **Getting Started** | [BOUNDARIES.md](resources/BOUNDARIES.md), [CLI_REFERENCE.md](resources/CLI_REFERENCE.md) (live reference pointers), [WORKFLOWS.md](resources/WORKFLOWS.md) | | **Core Concepts** | [DEPENDENCIES.md](resources/DEPENDENCIES.md), [ISSUE_CREATION.md](resources/ISSUE_CREATION.md), [PATTERNS.md](resources/PATTERNS.md) | | **Resilience** | [RESUMABILITY.md](resources/RESUMABILITY.md), [TROUBLESHOOTING.md](resources/TROUBLESHOOTING.md) | | **Planning** | [planning.md](references/planning.md) | | **Advanced** | [MOLECULES.md](resources/MOLECULES.md), [CHEMISTRY_PATTERNS.md](resources/CHEMISTRY_PATTERNS.md), [AGENTS.md](resources/AGENTS.md), [ASYNC_GATES.md](resources/ASYNC_GATES.md), [WORKTREES.md](resources/WORKTREES.md) | | **Reference** | [STATIC_DATA.md](resources/STATIC_DATA.md), [INTEGRATION_PATTERNS.md](resources/INTEGRATION_PATTERNS.md) | ## Validation If `bd --version` reports newer than `0.60.0`, this skill may be stale. Run `bd prime` for current CLI guidance — it auto-updates with each bd release and is the canonical source of truth ([ADR-0001](adr/0001-bd-prime-as-source-of-truth.md)).
From taowang1993/agents, MIT.
More from taowang1993/agents
- 0.524score
anydoc
firecrawl
Convert local document files (PDF/DOCX/PPTX/XLSX/ODT/RTF/EPUB/CSV) to GitHub-Flavored Markdown with the anydoc CLI.
SkillBFreshness: BClaude Code +9 - 0.519score
dsh
taowang1993
Build, port, configure, test, package, or publish DeepSeek Harness plugins using Cordis.
SkillBFreshness: BClaude Code +9 - 0.519score
codex-security
taowang1993
Use the OpenAI Codex Security CLI to scan repositories or code changes for vulnerabilities, review scan coverage and findings, validate suspected issues…
SkillBFreshness: BClaude Code +9 - 0.515score
cleanmac
taowang1993
Find and safely clean large macOS developer/tooling junk: /private/var/folders code_sign_clone folders, pnpm store versions, Xcode/iOS simulator…
SkillBFreshness: BClaude Code +9 - 0.474score
design
taowang1993
Audit, redesign, and build web and product interfaces with strong design taste.
SkillCFreshness: CClaude Code +9 - 0.470score
codex
taowang1993
Check ChatGPT/Codex rate limit reset credit expiration dates.
SkillCFreshness: CClaude Code +9 - 0.469score
ascii-tutor
taowang1993
Use ASCII art animations in markdown files to explain complex concepts to students during tutoring sessions.
SkillCFreshness: CClaude Code +9 - 0.469score
e2e-setup
taowang1993
Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable…
SkillCFreshness: CClaude Code +9 - 0.469score
clawpatch
taowang1993
Automated repo-wide review workflow using the clawpatch CLI.
SkillCFreshness: CClaude Code +9 - 0.469score
architect
taowang1993
Find deepening opportunities in a codebase, informed by the project's `architecture.md`.
SkillCFreshness: CClaude Code +9 - 0.469score
docsee
taowang1993
Manage AGENTS.md doc indexes synced from upstream GitHub repos.
SkillCFreshness: CClaude Code +9 - 0.469score
domain
taowang1993
Domain name brainstorming and availability checking using tldx CLI.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 24, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/taowang1993/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from taowang1993
- 0.519score
dsh
taowang1993
Build, port, configure, test, package, or publish DeepSeek Harness plugins using Cordis.
SkillBFreshness: BClaude Code +9 - 0.519score
codex-security
taowang1993
Use the OpenAI Codex Security CLI to scan repositories or code changes for vulnerabilities, review scan coverage and findings, validate suspected issues…
SkillBFreshness: BClaude Code +9 - 0.515score
cleanmac
taowang1993
Find and safely clean large macOS developer/tooling junk: /private/var/folders code_sign_clone folders, pnpm store versions, Xcode/iOS simulator…
SkillBFreshness: BClaude Code +9 - 0.474score
design
taowang1993
Audit, redesign, and build web and product interfaces with strong design taste.
SkillCFreshness: CClaude Code +9 - 0.470score
codex
taowang1993
Check ChatGPT/Codex rate limit reset credit expiration dates.
SkillCFreshness: CClaude Code +9 - 0.469score
agent-browser
taowang1993
Use ONLY when agent-browser's unique capabilities are needed; otherwise default to playwright-cli.
SkillCFreshness: CClaude Code +9
Cite this page
beads skill. Agent Mart. https://agentmart.dev/skills/taowang1993-beads (last updated 2026-10-24)