Conductor-Beads: Skill for Claude Code

.claude/skills/beads/SKILL.md

beads is a skill for Claude Code from NguyenSiTrung/Conductor-Beads. It costs 38 tokens per session (1,239 once invoked), scanned A, a copy of beads, Apache-2.0.

A Git-backed task tracker for coding work that keeps issues, dependencies, blockers, and project context across sessions. Git is the version-control system commonly used to sync changes between developers.

In plain words
What is it for?
Use it for work spanning multiple days, tasks with dependencies, blocked work, exploratory projects, or team-synced task history.
Why use it?
Short-lived checklists disappear with a conversation or work session, while this information needs to survive interruptions, collaboration, and context limits.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool; mentions AGENTS.md.

This is NguyenSiTrung/Conductor-Beads's own configuration. It tells Claude Code how to work on Conductor-Beads itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Conductor-Beads configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NguyenSiTrung/Conductor-Beads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NguyenSiTrung/Conductor-Beads/main/.claude/skills/beads/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NguyenSiTrung/Conductor-Beads

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for beads

README.md
[![agentmods](https://agentmods.dev/badge/skills/nguyensitrung/conductor-beads/beads/github.svg)](https://agentmods.dev/skills/nguyensitrung/conductor-beads/beads)
Your own site
<a href="https://agentmods.dev/skills/nguyensitrung/conductor-beads/beads"><img src="https://agentmods.dev/badge/skills/nguyensitrung/conductor-beads/beads/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for beads

Your own site · 80×15
<a href="https://agentmods.dev/skills/nguyensitrung/conductor-beads/beads"><img src="https://agentmods.dev/badge/skills/nguyensitrung/conductor-beads/beads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01239
Opus 5 $0.00019 $0.00620
Sonnet 5 $0.00008 $0.00248
Haiku 4.5 $0.00004 $0.00124

Measured 11d ago against content hash c41ee99936bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

beads scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to beads — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/beads/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

bd (persistent) TodoWrite (ephemeral)
Multi-session work Single-session tasks
Complex dependencies Linear execution
Survives compaction Conversation-scoped
Git-backed, team sync Local to session

Decision test: "Will I need this context in 2 weeks?" → YES = bd

When to use bd:

  • Work spans multiple sessions or days
  • Tasks have dependencies or blockers
  • Need to survive conversation compaction
  • Exploratory/research work with fuzzy boundaries
  • Collaboration with team (git sync)

When to use TodoWrite:

  • Single-session linear tasks
  • Simple checklist for immediate work
  • All context is in current conversation
  • Will complete within current session

Prerequisites

bd --version  # Requires v0.56.0+
  • bd CLI installed and in PATH
  • Git repository (bd requires git for sync)
  • 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

v0.56+: Beads now requires a running Dolt SQL server. Start with bd dolt start before using bd commands.

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)

Advanced Features

Feature CLI Resource
Molecules (templates) bd mol --help MOLECULES.md
Chemistry (pour/wisp) bd pour, bd wisp CHEMISTRY_PATTERNS.md
Agent beads bd agent --help AGENTS.md
Async gates bd gate --help ASYNC_GATES.md
Worktrees bd worktree --help WORKTREES.md
Messaging bd mail --help MESSAGING.md
Graph links bd relate --help GRAPH_LINKS.md
Dolt management bd dolt --help
SQL access bd sql --help
Graph visualization bd graph --help

Read the full file on GitHub · 110 lines

Files

What ships with it

49 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 110 lines · 38 tokens per session scan A c41ee99936bb

Subscribe to this mod's changes

beads is a skill published in the GitHub repository NguyenSiTrung/Conductor-Beads (24 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,239 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to beads, differing in 20 lines, and is treated as a copy.