b3os

b3os is a skill for Claude Code, Codex from b3rys/b3rys-team-os. It costs 0 tokens per session (4,234 once invoked), scanned A, original, Apache-2.0.

An onboarding workflow for b3os, a local system for creating and managing a team of AI agents.

In plain words
What is it for?
It helps clone and install the system, start its local dashboard, set team details, check runtime authentication, recruit the first team member, and hand over ongoing conversations.
Why use it?
It guides a user from installation through setting up a team and adding the first agent, while leaving tokens and activation approvals to the user.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; built for openclaw.

Good fit It helps clone and install the system, start its local dashboard, set team details, check runtime authentication, recruit the first team member, and hand over ongoing conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/b3rys/b3rys-team-os/b3os
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 b3rys/b3rys-team-os --skill b3os
Clone the repo
git clone --depth 1 https://github.com/b3rys/b3rys-team-os

Made for: Claude Code, Codex.

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 b3os

README.md
[![agentmods](https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os.svg)](https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os)
Your own site
<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,234 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. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04234
Opus 5 $0.00000 $0.02117
Sonnet 5 $0.00000 $0.00847
Haiku 4.5 $0.00000 $0.00423

Measured 8d ago against content hash aeff9b72e5f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

b3os 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 8d 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.

skills/b3os/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

b3os — b3rys TEAM OS 온보딩 스킬

여러 AI를 한 명씩 따로 쓰지 말고, 한 팀으로. 공개 저장소 github.com/b3rys/b3rys-team-os를 clone → 설치 → 대시보드 기동 → 팀 기본정보 세팅 → 첫 팀원 1명 영입 까지 몰아주고, 그 팀원에게 넘긴다.

이 스킬의 목표 = 사용자를 "첫 팀원"까지 데려다주고 손을 뗀다(handoff). 첫 팀원이 응답하면 추가 영입·운영은 그 팀원이 이어받는다.

핵심 디자인 — ①대화로 진행: 팀 기본정보도 화면에 미루지 않고 채팅으로 묻는다 ②사람 게이트 존중: 봇 토큰·활성화 승인·페어링은 사람 몫, 대신 만들거나 우회하지 않는다 ③인증은 런타임을 고른 그 순간에만 점검하고 구독을 미리 캐묻지 않는다 ④인증은 구독(OAuth)이 기본 — API 키는 사용자가 명시적으로 원할 때만.

⚠️ 시작 전 안전 고지 (사용자에게 먼저 보여줄 것)

b3os는 본인 전용 장비(personal machine)에만 설치하세요. 대시보드·API는 127.0.0.1 로컬 단독 사용을 전제로 하며 앱 레벨 인증이 없습니다. 공용/공개 서버에 그대로 노출하지 마세요. 외부 접근이 필요하면 Cloudflare Access 같은 엣지 인증을 반드시 앞단에 두세요.

macOS 권장(팀원 활성화가 launchd 기반이라 현재 macOS 전용, Linux는 대시보드까지만).

전체 흐름 (위에서 아래로 실행)

[0] 안전 고지 + 설치 위치 확인
[1] Prerequisites (brew·git — 공통만. 런타임별 인증은 [5]에서)
[2] clone → bash install.sh                                  ← 사람: 활성화 y/n
[3] bun run start → http://localhost:7878/team
[4] 팀 기본정보 = 채팅으로 물어봄 (팀명·팀장ID·팀장이름)      ※ 안 하면 영입이 400
[5] 첫 팀원 영입 (런타임 선택 → preflight → recruit)          ← 사람: 봇 토큰·페어링
[6] 1:1 DM 확인 — 응답 오면 합류 완료
[7] ★HANDOFF — "이제 팀원과 대화하세요"                        ← 여기서 이 스킬의 일은 끝
[8] (선택) 팀원 더 추가 · 팀방(그룹) 협업 · 런타임 교체

첫 영입 팀원은 자동으로 팀 coordinator + full context 를 받는다 — 담당 미배정·모호 메시지의 기본 담당(라우팅 fallback·PM 조율)이자 팀방 최근 맥락 수신자다. 그래서 [7] handoff 대상이 된다. (이후 팀원엔 기본 미부여, 첫 리드 퇴사 시 자동 승계.)

[0] 설치 위치

기본은 홈 폴더다. 클론 전에 먼저 알린다 — "📁 ~/b3rys-team-os 에 설치합니다. 다른 위치를 원하면 알려주세요."

[[ "$(uname)" == "Darwin" ]] || echo "⚠ macOS 아님 — 대시보드까지만 됩니다."
export B3OS="$HOME/b3rys-team-os"

[1] Prerequisites — 공통만

command -v brew >/dev/null || /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
command -v git  >/dev/null || brew install git
# bun·tmux 는 install.sh 가 자동 준비. 수동이 필요하면: curl -fsSL https://bun.sh/install | bash

[2] Clone + 설치

: "${B3OS:=$HOME/b3rys-team-os}"
if [ -d "$B3OS/.git" ]; then echo "이미 clone됨 — 재사용"; else git clone https://github.com/b3rys/b3rys-team-os.git "$B3OS"; fi
cd "$B3OS" && bash install.sh

Read the full file on GitHub · 191 lines

Files

What ships with it

6 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. 8d ago First seen · 191 lines · 0 tokens per session scan E aeff9b72e5f6

Subscribe to this mod's changes

b3os is a skill published in the GitHub repository b3rys/b3rys-team-os (12 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,234 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.