beads

A system for tracking complicated work across multiple conversations using tasks and dependency links. A dependency link records when one task relies on another, and its saved context can persist between sessions.

In plain words
What is it for?
Managing multi-session projects, tracking tasks and dependencies, and preserving project context between conversations.
Why use it?
It helps prevent lost context and makes work with many connected tasks easier to resume and organize.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ynulihao/agentskillos/beads
Any agent
npx skills add ynulihao/AgentSkillOS --skill beads
Clone the repo
git clone --depth 1 https://github.com/ynulihao/AgentSkillOS

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.05775
Opus 5 $0.00043 $0.02887
Sonnet 5 $0.00017 $0.01155
Haiku 4.5 $0.00009 $0.00577

Measured 2d ago against content hash 758fc6ab1224, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

beads 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 2d 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 -fsSL 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 -fsSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash
data/skill_seeds/beads/SKILL.md · 825 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 2d ago First seen · 825 lines · 85 tokens per session scan C 758fc6ab1224

Subscribe to this mod's changes

beads is a skill published in the GitHub repository ynulihao/AgentSkillOS (607 stars, last pushed 5mo ago), with no licence file. It adds 85 tokens to every session and 5,775 once invoked, about $0.0004 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 2026-08-30.