Agent skill

Beads Task Memory

by gastownhall in gastownhall/beads

Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

MITAuto-check passedAgent Workflows

Install Beads Task Memory

skills CLI
$ npx skills add gastownhall/beads --skill beads -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gastownhall/beads beads --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gastownhall/beads.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/beads/skills/beads .claude/skills/beads && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
beads
GitHub stars
28k
Token cost
~1.2k tokens
SKILL.md length
370 words
Files
50
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

  • Works in 6 steps: bd ready — Find unblocked work → bd show — Get full context → bd update --claim — Claim and start work… → …
  • Work that spans several sessions and has blocked or dependent tasks
  • SKILL.md covers bd vs TodoWrite, Prerequisites, CLI Reference and Session Protocol, plus 6 more sections
  • Calls git

What it does

Beads is a graph-based issue tracker backed by Dolt, and this skill teaches the agent to use its `bd` CLI as persistent task memory. A simple decision test separates it from the agent's built-in task list: if the context will still matter in two weeks, use bd, and for single-session linear tasks use the ephemeral list. Prerequisites are the `bd` CLI (version 0.60.0 or newer) on PATH and a one-time `bd init`, which humans run rather than agents; a Git repository is optional.

The session protocol is to run `bd ready` for unblocked work, `bd show` for context, claim a task with `bd update --claim`, add notes as you go because they are what survive compaction, close with a reason and push to the Dolt remote if one is configured. Adding `--json` gives structured output, and the examples show creating an epic with dependent tasks, listing in-progress work to recover after compaction and filing a bug discovered mid-task. An error table covers a missing database, a missing Git repository, disk I/O errors on cloud-synced folders and lagging status updates.

When your agent uses it

  • Work that spans several sessions and has blocked or dependent tasks
  • Recovering context after a conversation is compacted
  • Finding which tasks are ready to start

Example prompts

  • “Track the OAuth integration as an epic and add token storage as a dependent task.”
  • “What's ready to work on right now?”
  • “Resume after compaction: list what was in progress and show the details.”

Requirements

  • The `bd` CLI, version 0.60.0 or newer, on PATH
  • A one-time `bd init` in the project, run by a human
  • Pre-approved tools (allowed-tools): Read, Bash(bd:*)

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. bd ready — Find unblocked work
  2. bd show — Get full context
  3. bd update --claim — Claim and start work atomically
  4. Add notes as you work (critical for compaction survival)
  5. bd close --reason "..." — Complete task
  6. bd dolt push — Push to Dolt remote (if configured)

What it can do on your machine

Read from SKILL.md and the folder at commit b3cdbf9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash(bd:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Beads Task Memory loads about 1.2k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gastownhall/beads at commit b3cdbf9, republished under its MIT licence (© gastownhall). 370 words, ~1,210 tokens.

Download SKILL.mdSave it as .claude/skills/beads/SKILL.md (or your agent's skills folder). This skill also uses 49 other files; get the full folder from GitHub.
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 "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.
allowed-tools
Read, Bash(bd:*)
version
0.60.0
author
Steve Yegge <steve.yegge@gmail.com>
license
MIT
compatible-with
claude-code, codex
tags
issue-tracking, task-management, multi-session, dependencies

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 survivalSingle-session linear tasks
Dolt-backed team syncConversation-scoped

See 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)

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

ErrorFix
database not foundbd init <prefix> in project root
not in a git repositorygit init first
disk I/O error (522)Move .beads/ off cloud-synced filesystem
Status updates lagUse server mode: bd dolt start

See TROUBLESHOOTING.md for full details.

Show full SKILL.md (129 more words)Show less

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

FeatureCLIResource
Molecules (templates)bd mol --helpMOLECULES.md
Chemistry (pour/wisp)bd pour, bd wispCHEMISTRY_PATTERNS.md
Agent beadsbd agent --helpAGENTS.md
Async gatesbd gate --helpASYNC_GATES.md
Worktreesbd worktree --helpWORKTREES.md

Resources

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).

© gastownhall, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 49 other files in plugins/beads/skills/beads of gastownhall/beads.

  • SKILL.md
  • CLAUDE.md
  • README.md
  • adr/0001-bd-prime-as-source-of-truth.md
  • agents/openai.yaml
  • commands/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
  • … and 32 more

Open the folder on GitHubat commit b3cdbf9

Compare with similar skills

Beads Task Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Beads Task Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Beads Task Memory this skillgastownhall/beads28k—~1.2kAutomated safety check: PassMIT
Session History Searchslopus/happy24k—~3.1kAutomated safety check: PassMIT
Session Handoff Writercodewhale-hq/Codewhale41k—~1.2kAutomated safety check: PassMIT
Beadsmatthiasn/lotti1.2k—~589Automated safety check: PassGPL-3.0
File-Based Planning in ArabicOthmanAdi/planning-with-files27k—~3.2kAutomated safety check: NotesMIT
Context Savegarrytan/gstack136k—~9.8kAutomated safety check: NotesMIT

Similar skills

  • Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

    24k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Session Handoff Writer

    codewhale-hq/Codewhale

    Writes a compact handoff note from real git and CI state so the next session or a teammate can pick up the work without rebuilding the context.

    41k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Beads

    matthiasn/lotti

    A skill your agent uses for authorized Lotti maintainer work that needs private durable task tracking, issue dependencies, blocker management, multi-session handoff, or shared agent memory.

    1.2k GitHub stars~589 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • File-Based Planning in Arabic

    OthmanAdi/planning-with-files

    Arabic edition of a file-based planning skill that keeps task_plan.md, findings.md and progress.md on disk so multi-step agent work survives lost context.

    27k GitHub stars~3.2k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check: notes
  • Context Save

    garrytan/gstack

    Captures git state, decisions made and remaining work so that a later session can resume the task without losing context.

    136k GitHub stars~9.8k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Gcc

    davila7/claude-code-templates

    Git Context Controller (GCC) - Manages agent memory as a versioned file system under .GCC/.

    33k GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from gastownhall/beads

  • Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.

    28k GitHub stars~3.2k tokensUpdated today
    Auto-check passed

Works with

Questions about Beads Task Memory

What does Beads Task Memory do?

Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction. Beads is a graph-based issue tracker backed by Dolt, and this skill teaches the agent to use its `bd` CLI as persistent task memory. A simple decision test separates it from the agent's built-in task list: if the context will still matter in two weeks, use bd, and for single-session linear tasks use the ephemeral list.

When should I use Beads Task Memory?

Beads Task Memory fits situations like: work that spans several sessions and has blocked or dependent tasks; recovering context after a conversation is compacted; finding which tasks are ready to start.

How do I install Beads Task Memory in Claude Code?

Run `npx skills add gastownhall/beads --skill beads -a claude-code`. Or copy the skill folder (plugins/beads/skills/beads in gastownhall/beads) into .claude/skills/beads in your project. Claude Code loads it when a task matches its description.

How do I install Beads Task Memory in Codex?

Run `npx skills add gastownhall/beads --skill beads -a codex`. Or copy the skill folder (plugins/beads/skills/beads in gastownhall/beads) into .agents/skills/beads in your project. Codex loads it when a task matches its description.

Can I use Beads Task Memory in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gastownhall/beads --skill beads -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/beads, .gemini/skills/beads, .github/skills/beads and .opencode/skills/beads in your project.

What does Beads Task Memory need to run?

Going by SKILL.md and its folder, Beads Task Memory needs the command-line tools its instructions call (git). Our summary lists: The `bd` CLI, version 0.60.0 or newer, on PATH; A one-time `bd init` in the project, run by a human. Its frontmatter pre-approves these tools: Read, Bash(bd:*).

Does Beads Task Memory access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Beads Task Memory safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Beads Task Memory use?

Beads Task Memory is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Beads Task Memory use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Beads Task Memory?

Skills that share tags, products or a category with Beads Task Memory: Session History Search (slopus/happy, 24k stars), Session Handoff Writer (codewhale-hq/Codewhale, 41k stars), Beads (matthiasn/lotti, 1.2k stars) and File-Based Planning in Arabic (OthmanAdi/planning-with-files, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Beads Task Memory?

gastownhall (a GitHub organization) maintains it in gastownhall/beads, which has 27,776 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

Source: gastownhall/beads on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.