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.
npx skills add b3rys/b3rys-team-os --skill b3os-schedulergit clone --depth 1 https://github.com/b3rys/b3rys-team-osWrote 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.
[](https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-scheduler)<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-scheduler"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-scheduler/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.
<a href="https://agentmods.dev/skills/b3rys/b3rys-team-os/b3os-scheduler"><img src="https://agentmods.dev/badge/skills/b3rys/b3rys-team-os/b3os-scheduler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00128 | $0.02759 |
| Opus 5 | $0.00064 | $0.01380 |
| Sonnet 5 | $0.00026 | $0.00552 |
| Haiku 4.5 | $0.00013 | $0.00276 |
Grade A, and why
b3os-scheduler 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
b3os-scheduler — b3os durable 스케줄러
팀원이 세션과 무관하게(durable) 시각에 맞춰 발화하는 반복/예약 잡을 등록하는 절차 스킬이다. 런타임별 세션 cron(claude CronCreate, openclaw/hermes 자체 예약)은 그 세션이 죽으면 유실된다. 팀 정본 반복작업(야간 사이클·주기 리마인드·정기 점검)은 이 스케줄러에 등록해 team.db에 durable 저장하고, b3os 서버 안의 워커가 발화한다.
언제 쓰나
- "매일 03:04에 X 해라", "평일 09시에 Y 깨워라", "매월 1일 리포트" 같은 반복 잡을 durable하게 걸 때
- "N분 뒤 나한테 알려줘" 같은 1회성 리마인드를 턴에서 sleep 없이 예약할 때 (dex/에이전트 in-turn sleep 금지)
- 세션 죽어도 살아남아야 하는 팀 정본 스케줄을 등록/이관할 때
- launchd per-job 플리스트를 durable 스케줄러 잡으로 이관할 때
세션 한정 임시 점검(몇 분 뒤 한 번 확인)은 런타임 세션 cron으로도 충분하다 — 이 스킬은 유실되면 안 되는 잡에 쓴다.
b3os-task-loop(작업루프)과 구분: workloop = 정해진 코디네이터 루프(매일 칸반 PM·주간 self-learning 등 고정 프로그램)를 깨우는 기본 인프라. scheduler(이 스킬) = 임의의 durable 반복·예약 잡을 자유롭게 등록하는 범용 도구. workloop의 스케줄 자체도 이 스케줄러로 이관 가능(launchd per-job → scheduled_job).
개념 (실제 구현)
- 정본 저장:
team.db의scheduled_job테이블 (id·kind·schedule_kind·next_run_at(UTC)·schedule_expr·payload_json·enabled·lock_until…). 실행 이력=scheduled_job_run. - 워커: b3os 서버가
startSchedulerWorker로 틱마다(기본 60초, envB3OS_SCHEDULER_INTERVAL_MS로 조정·최소 5초)next_run_at<=now인 잡을 lease-claim → 발화 → 재계산. 코드=src/server/scheduler/core.ts(runDueSchedulerJobsOnce)·workers/schedulerWorker.ts. - 발화 = 2종 페이로드: ①
inbox—payload_json의 인박스 봉투를acceptInbound로 삽입(실제 wake/라우팅은 wakeDispatcher, 신규 라우팅 0). ②exec— allowlist된 ops 스크립트를 spawn(에이전트 안 깨우고 결정적 작업 직접 수행, 옛 launchd 대체). inbox는 emit+재계산이 단일 트랜잭션(at-most-once), exec는 async라 실행 후 재계산(at-least-once). - 잡 종류(kind × schedule_kind):
recurring×cron(시·분·요일·월) /recurring×interval(N분 간격) /oneshot×once(1회 리마인드). - 안전: claim은 원자적 조건부 UPDATE(lease)로 이중발화 차단.
dedupe_key=job_id+scheduled_for+acceptInbound창으로 크래시 재발화 시에도 이중게시 0. 한 잡 throw가 워커 안 죽임(격리) — 잘못된 cron 잡은failed로 파킹돼 재발화 루프 없음.
cron 문법 (표준 5필드, KST)
분 시 일(月) 월 요일 — 예 4 3 * * * = 매일 03:04.
- 필드:
*/a/a,b,c/a-b/*/n/a-b/n/N/n(N..최대 step n, Vixie) - 요일: 0-7 (0·7=일요일)
- 일(dom)·요일(dow) 둘 다 지정 시 = 둘 중 하나 맞으면 발화(Vixie 시맨틱)
- 타임존 = 잡의
timezone(기본 Asia/Seoul). 고정 오프셋 존만 지원 — DST 존(America/New_York 등)은 등록 시 throw(오발화 방지). KST는 DST 없어 정확.
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.
- 11d ago First seen · 91 lines · 128 tokens per session scan A ab2f90762b24
b3os-scheduler is a skill published in the GitHub repository b3rys/b3rys-team-os (13 stars, last pushed 2d ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,759 once invoked, about $0.0006 per session on Opus 5. 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.
Other skills, from other repositories
automation
Instructions for managing scheduled tasks through the host's structured automation tool, including reminders, delayed work, recurring checks, and result delivery.
ai-interview-preparation-coaching
When user asks for interview prep, mock interview, practice questions, behavioral questions, technical interview, HR round, salary negotiation, STAR method, common interview questions, company research, interview tips, confidence building, answer feedback, body language tips, fo…
ai-agent-tools
This library provides ready-to-use Python functions that AI agents can leverage to perform various tasks including file operations, text analysis, data transformation, memory management, and validation.
agent-social-networking-chat
ClawGang social skill — lets your agent socialize on clawgang.ai: post updates, chat 1:1 or in groups, manage friends, poll for new messages and reply automatically.
adhd-founder-daily-planner
This skill should be used when the user asks to 'plan my day', 'help me plan today', 'morning planning', 'what should I work on today', 'daily planner', 'evening reflection', 'reflect on my day', 'migrate tasks', 'carry tasks forward', 'rapid log', 'brain dump my tasks', or ment…
ai-phone-call-assistant
Make phone calls via KallyAI API - an AI phone assistant that calls businesses on your behalf. Use when users want to make restaurant reservations, schedule appointments, or inquire at businesses by phone.