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 team-attention/plugins-for-claude-natives --skill youtube-digestgit clone --depth 1 https://github.com/team-attention/plugins-for-claude-nativesWrote 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/team-attention/plugins-for-claude-natives/youtube-digest)<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/youtube-digest"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/youtube-digest/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/team-attention/plugins-for-claude-natives/youtube-digest"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/youtube-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 114 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00089 | $0.00947 |
| Opus 5 | $0.00044 | $0.00474 |
| Sonnet 5 | $0.00018 | $0.00189 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
youtube-digest 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.
What it actually says
YouTube Digest
YouTube 영상 분석 → 요약/인사이트/번역 문서 생성 → 퀴즈 테스트.
워크플로우
1. 메타데이터 수집
scripts/extract_metadata.sh "<URL>"
추출: title, description, channel, upload_date, duration, tags
2. Transcript 추출
scripts/extract_transcript.sh "<URL>" [output_dir]
우선순위: 수동 자막(ko→en) > 자동 생성 자막(ko→en)
3. 맥락 파악 (WebSearch)
웹 검색으로 고유명사 정확한 표기 수집:
"{영상 제목}" {채널명} summary"{발표자명}" {주제 키워드}
4. Transcript 교정
자동 자막의 고유명사 오인식을 웹 검색 결과로 대체:
- Kora → Cora, cloud code → Claude Code, every → Every.to
5. 문서 생성
---
title: {영상 제목}
url: {YouTube URL}
channel: {채널명}
date: {업로드 날짜}
duration: {영상 길이}
processed_at: {처리 일시}
---
# {영상 제목}
## 요약
{3-5문장 요약 + 주요 포인트 3개}
## 인사이트
### 핵심 아이디어
### 적용 가능한 점
## 전체 스크립트 (한글 번역)
[00:00] ...
6. 파일 저장
위치: research/readings/youtube/{YYYY-MM-DD}-{sanitized-title}.md
7. 학습 퀴즈
3단계 × 3문제 = 총 9문제. AskUserQuestion으로 각 단계 3문제 동시 출제.
| 단계 | 난이도 | 출제 기준 |
|---|---|---|
| 1 | 기본 | 핵심 인사이트, 주요 개념 |
| 2 | 중급 | 인사이트 + 세부 내용 연결 |
| 3 | 심화 | 세부 내용, 적용/분석 |
문제 유형 상세: references/quiz-patterns.md
결과 처리
틀린 문제에 대해 정답과 해설 제공 후, 문서 끝에 퀴즈 결과 추가:
## 퀴즈 결과
총점: 7/9 (78%) | 1단계 3/3 ✅ | 2단계 2/3 | 3단계 2/3
### 오답 노트
**Q5**: {질문}
- 선택: B → 정답: C
- {1-2문장 해설}
8. 후속 선택
퀴즈 완료 후 AskUserQuestion:
- 한 번 더 퀴즈: 다른 문제로 재테스트
- Deep Research: 웹 심층 조사 (
references/deep-research.md참조) - 종료: 마무리
참고사항
자막 언어 우선순위
- 한국어 수동 → 2. 영어 수동 → 3. 한국어 자동 → 4. 영어 자동
불완전한 자막 처리
- 고유명사 오인식: 4단계에서 일괄 대체
- 이해 불가 부분:
[불명확]표시
yt-dlp 옵션
--list-subs: 자막 목록 확인--cookies-from-browser chrome: 로그인 필요 시
리소스
scripts/extract_metadata.sh- 메타데이터 추출scripts/extract_transcript.sh- 자막 추출references/quiz-patterns.md- 퀴즈 문제 유형 상세references/deep-research.md- Deep Research 워크플로우
What ships with it
4 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.
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 · 122 lines · 89 tokens per session scan A 0cd74f11b7af
youtube-digest is a skill published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 947 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.