notification-hub

notification-hub is a skill for Claude Code, Codex from mupengi-bot/mupengism. It costs 33 tokens per session (1,676 once invoked), scanned A, original, MIT.

A notification system that collects alerts from different automation tools and groups them by urgency.

In plain words
What is it for?
It is for reporting security problems, system failures, cost warnings, new messages, trends, pending Git pushes, statistics, and completed workflows through the configured channels.
Why use it?
It reduces the need to check many separate alert sources and helps distinguish emergencies from routine updates.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit It is for reporting security problems, system failures, cost warnings, new messages, trends, pending Git pushes, statistics, and completed workflows through the configured channels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mupengi-bot/mupengism/notification-hub
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 mupengi-bot/mupengism --skill notification-hub
Clone the repo
git clone --depth 1 https://github.com/mupengi-bot/mupengism

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 notification-hub

README.md
[![agentmods](https://agentmods.dev/badge/skills/mupengi-bot/mupengism/notification-hub/github.svg)](https://agentmods.dev/skills/mupengi-bot/mupengism/notification-hub)
Your own site
<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/notification-hub"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/notification-hub/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 notification-hub

Your own site · 80×15
<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/notification-hub"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/notification-hub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,676 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 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 $0.00033 $0.01676
Opus 5 $0.00016 $0.00838
Sonnet 5 $0.00007 $0.00335
Haiku 4.5 $0.00003 $0.00168

Measured 10d ago against content hash 16831e1ae82a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

notification-hub 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 10d 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/notification-hub/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

notification-hub

알림 통합 — 모든 스킬의 알림을 하나로 모아 우선순위별로 형님에게 효율적으로 전달합니다.

🎯 목적

각 스킬이 생성하는 다양한 알림을 중앙에서 관리하고, 중요도에 따라 적절한 타이밍과 채널로 전달하여 알림 피로도를 줄입니다.

📥 알림 소스

events/ 디렉토리의 모든 이벤트 파일을 수집:

events/
  ├── health-2026-02-14.json         (health-monitor)
  ├── scrape-result-2026-02-14.json  (data-scraper)
  ├── dm-check-2026-02-14.json       (insta-post)
  ├── competitor-2026-02-14.json     (competitor-watch)
  └── workflow-2026-02-14.json       (skill-composer)

🚦 우선순위 필터

1. urgent — 즉시 Discord DM

조건:

  • 보안 이슈 (비정상 로그인, 의심스러운 접근)
  • 시스템 에러 (OpenClaw 다운, 브라우저 연결 끊김)
  • 비용 초과 (API 사용량 90% 이상)
  • 중요 멘션

전송:

  • Discord DM (채널 ID는 TOOLS.md에 설정)
  • 즉시 전송 (1분 이내)

예시:

🚨 긴급: 브라우저 연결 끊김
포트 18800 응답 없음. 자동 복구 시도했으나 실패.
수동 확인 필요: openclaw browser start

2. important — 다음 heartbeat에 포함

조건:

  • 새로운 인스타 DM (읽지 않음)
  • 트렌드 급상승 키워드 발견
  • 경쟁사 신규 서비스 출시
  • Git push 필요 (unpushed commits 10개 이상)

전송:

  • 다음 heartbeat 응답에 포함 (~30분 간격)
  • 여러 알림을 묶어서 한 번에 전송

예시:

📢 업데이트 3건

📩 인스타 DM 2건 (iam.dawn.kim, partner_xyz)
📈 트렌드: "AI 에이전트" 급상승 (+150%)
🔄 Git: 12개 커밋 push 대기중

3. info — daily-report에만 포함

조건:

  • 정기 통계 업데이트
  • 일일 토큰 사용량
  • 완료된 워크플로우
  • 일반 시스템 로그

전송:

  • daily-report 스킬 실행 시 포함
  • 하루 1회 요약 전송

예시:

📊 일일 리포트 (2026-02-14)

✅ 워크플로우 3건 완료
📊 토큰 사용: 45,230 / 100,000 (45%)
📝 메모리 사용: 3.2 GB
🔧 헬스 체크: 정상

🔕 중복 알림 방지

동일한 이벤트에 대해 2번 이상 알림을 보내지 않습니다.

중복 판정 기준

{
  "event_id": "health-check-2026-02-14-07:00",
  "fingerprint": "sha256(source + type + key_data)",
  "notified_at": "2026-02-14T07:05:00+09:00"
}

히스토리 저장

memory/notifications/
  ├── sent-2026-02-14.json
  ├── sent-2026-02-13.json
  └── ...

sent-YYYY-MM-DD.json 구조:

{
  "date": "2026-02-14",
  "notifications": [
    {
      "id": "health-check-2026-02-14-07:00",
      "priority": "info",
      "sent_at": "2026-02-14T07:05:00+09:00",
      "channel": "discord_dm",
      "source": "health-monitor"
    }
  ]
}

Read the full file on GitHub · 240 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.

  1. 10d ago First seen · 240 lines · 33 tokens per session scan A 16831e1ae82a

Subscribe to this mod's changes

notification-hub is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,676 once invoked, about $0.0002 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 2026-08-31.