A one-time setup guide for Beads, a command-line tool for tracking work items in a repository. It explains how to install the tool, choose an issue-ID prefix, and initialize the project.

Use it when starting Beads in a repository, including checking whether it is installed, installing it if needed, and initializing project tracking.

It removes the manual guesswork involved in preparing a repository for the Beads-based workflow. It asks for confirmation before running setup commands.

bds-setup — Skill for Claude Code by seungyeop-lee

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add seungyeop-lee/beads-starter --skill bds-setup

Clone the repo

git clone --depth 1 https://github.com/seungyeop-lee/beads-starter

Made for: Claude Code.

Or install beads-starter, the plugin that ships this one along with the rest of its 3 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/seungyeop-lee/beads-starter/bds-setup/github.svg)](https://agentmods.dev/skills/seungyeop-lee/beads-starter/bds-setup)

Your own site

<a href="https://agentmods.dev/skills/seungyeop-lee/beads-starter/bds-setup"><img src="https://agentmods.dev/badge/skills/seungyeop-lee/beads-starter/bds-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/seungyeop-lee/beads-starter/bds-setup"><img src="https://agentmods.dev/badge/skills/seungyeop-lee/beads-starter/bds-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,003 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.01003
Opus 5	$0.00012	$0.00502
Sonnet 5	$0.00005	$0.00201
Haiku 4.5	$0.00002	$0.00100

Measured 9d ago against content hash c3eebbdbb41c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

bds-setup scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash

on-demand/skills/bds-setup/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beads Setup

One-time per-repository setup for the beads-starter workflow.

On Activation

Walk the user through the steps below. For each command, show the command first, then ask "Run this?" before executing. Do not chain commands silently.

Steps

1. Check for bd

Show:

command -v bd && bd version

If bd is already installed and reports a version, skip to step 3. Otherwise proceed to step 2.

2. Install bd (if missing)

The beads team recommends Homebrew. Show the user the options and ask which they want:

Homebrew (macOS / Linux, recommended)

brew install beads

npm (Node.js users)

npm install -g @beads/bd

Install script (other platforms)

curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash

For Windows, Arch AUR, go install, or building from source, point them to https://github.com/steveyegge/beads/blob/main/docs/INSTALLING.md.

3. Determine the prefix

The prefix is used for issue IDs (e.g., MYPROJ-42). Default suggestion: the current directory's basename. Confirm with the user before proceeding.

4. Initialize

Show all five commands together, then ask "Run all five?":

bd init --shared-server --prefix <PREFIX> --skip-agents --skip-hooks
bd config set no-git-ops true
bd config set export.git-add false
bd config set dolt.local-only true
bd config unset sync.remote

Substitute <PREFIX> with the value from step 3.

5. Verify

Show:

bd ready --json

Run it after confirmation. A successful exit (even with empty JSON output) means setup is complete.

6. Brief the user on expected warnings

After setup, the following warnings are normal under this preset and should not trigger action:

From bd init:

Server host defaulted to 127.0.0.1 — correct for single-machine use.
Setup incomplete. No dolt database found — clears on the next bd command.

From bd doctor:

Git Hooks: No recommended git hooks installed — intentional (--skip-hooks).
Phantom Databases: beads_global — cosmetic, see beads GH#2051.
Dolt Status / Dolt Locks: Uncommitted changes — pending bd config writes auto-commit on the next bd command.
Git Working Tree: Uncommitted changes — files outside .beads/. Commit them separately from bd work.
Claude Plugin: beads plugin not installed / Claude Integration: Not configured — not part of this preset.

Read the full file on GitHub · 116 lines

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.

9d ago First seen · 116 lines · 23 tokens per session scan C c3eebbdbb41c

Subscribe to this mod's changes

bds-setup is a skill published in the GitHub repository seungyeop-lee/beads-starter (1 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,003 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code agentic-coding agents-md ai-agents beads installer

context-forge

Use when starting a brand-new project that needs AI-agent context (CLAUDE.md, AGENTS.md, skills, rules, MCP, spec workflow) set up from day one. Discusses goals → matches catalog know-how → creates a new GitHub repo with everything wired in. Keywords: harness engineering, bootstrap project, context engineering…

glowElephant/context-forge · 82 tokens

Agent Instruction Drift Check

Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.

niels-emmer/myace · 38 tokens

nv-context

Set up state-of-the-art context engineering for any repository. Analyzes codebase, generates multi-level CLAUDE.md/AGENTS.md hierarchy, hooks, session management, and token budgets. Based on 200+ sources including ETH Zurich, Anthropic, Google DeepMind, and Manus production data. For engineers who ship with AI agents.

johnnichev/nv-context · 73 tokens

bds-setup