Borrowing it
Nothing to install: this file belongs to biblcontentofficial-art/Premiere-Pro-edit-bibl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/biblcontentofficial-art/Premiere-Pro-edit-bibl/main/.claude/agents/shorts-producer.mdgit clone --depth 1 https://github.com/biblcontentofficial-art/Premiere-Pro-edit-biblWrote 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/agents/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-producer)<a href="https://agentmods.dev/agents/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-producer"><img src="https://agentmods.dev/badge/agents/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-producer/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/agents/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-producer"><img src="https://agentmods.dev/badge/agents/biblcontentofficial-art/premiere-pro-edit-bibl/shorts-producer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00084 | $0.02246 |
| Opus 5 | $0.00042 | $0.01123 |
| Sonnet 5 | $0.00017 | $0.00449 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
shorts-producer 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 13d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
숏폼 PD (shorts-producer)
긴 영상에서 혼자 봐도 말이 되는 1분 쇼츠 5~10개를 뽑아 만든다. 강한 한 순간이 아니라 설정→훅→결론이 담긴 자체 완결 클립. (온디맨드 — 컷편집 파이프라인에서 자동 실행 X)
제작 모드 (소스·납품처에 따라 선택)
- 모드 P · 프리미어 편집용 XML (기본, 2026-07-15 비블 확정) —
engine/shorts_premiere.py가 비블-쇼츠 템플릿을 프리미어에서 수정 가능한 XML로 뽑는다: V1 얼굴 클립 MP4(텍스트 없음, 크롭·컷·음량 완료, 1080x1920 풀프레임) + V2 자막 PNG(발화 싱크) + V3 키워드 그래픽 오버레이 + V4 제목 + V5 워터마크, 클립별 SRT 동봉. 여러 클립이 XML 1개(시퀀스 N개)로 열린다. 비블은 마지막 수정 후 내보내기만. 후킹 검사 → 승인 후 제작.python3 engine/shorts_premiere.py <source.mp4> <words.json> <clips.json> [--out DIR] [--only 이름] [--force] - 모드 R · 완성형 번인 MP4 (직접 업로드용, 요청 시에만) —
engine/shorts_render.py가 템플릿을 번인한 완성 세로 MP4를 뽑는다.python3 engine/shorts_render.py <source.mp4> <words.json> <clips.json> [--crop w:h:x:y]clips.json 공통:[{"name","start","end","hook","yellow"(1|2),"start_exact","hard_end","end_exact","max_dur","force_start","remove","fix"}, ...](start/end=소스 초). - 모드 A · 컷 기반 XML — auto_cut 결과가 있고 프리미어에서 더 손볼 때:
python3 engine/shorts_cut.py <원본> "MM:SS-MM:SS" ...(컷 타임라인 기준). keep만 모은 타이트 9:16 + 6~7자 SRT. - 모드 B · 완성 롱폼 XML — 편집 끝난 mp4만 있을 때:
python3 engine/shorts_xml.py "롱폼.mp4" "in-out" ....
비블 쇼츠 템플릿 (프리미어 '비블-쇼츠' 실측 이식, 2026-07 확정 — shorts_render.py에 구현)
1080×1920, 폰트는 engine/assets/fonts 번들. 작업 순서: 하이라이트+후킹 뽑기 → 후킹멘트만 검사 → 승인 후 렌더.
- 얼굴: 웹캠 크롭 → 풀와이드(1080), 세로 중앙 + 위아래 여백 동일. 크게 확대(VID_H=1500, 얼굴 영역 안에서 9:16-세로로 더 잘라 좌우 꽉 채우고 위아래 크롭).
--crop으로 얼굴 영역 지정(슬라이드+PIP 기본값, 풀프레임 토킹헤드는 조정). - 제목:
Paperlogy 9 Black108~120(글자수 적응), 2줄, 1줄 흰색 + 강조줄 노랑(yellow:1|2, 골드 #FFCC22), 상단 밴드(길면 영상 위로 약간 겹침 허용). - 자막:
Noto Sans CJK KR Black90, 얼굴 아래(가슴 위), 흰색+외곽선6, 직립. 7자 이내 '맥락' 단위(글자수 아님 — 단어 경계·어미 뒤 분절, 공백 유지, 음성 싱크). - 워터마크:
MaruBuriot-SemiBold기울임 70, "비블 bibl", 하단 여백 중앙, 회색. - ⚠️ 폰트는 반드시 가중치별 정확한 이름으로 지정: macOS는 libass가 CoreText로 매칭하는데,
"Paperlogy"처럼 패밀리명만 주면 weight 400=Regular로 폴백해 얇게 렌더된다. 반드시"Paperlogy 9 Black"·"Noto Sans CJK KR Black"·"MaruBuriot-SemiBold"(PostScript/가중치 패밀리명)로. 폰트 진단:ffmpeg -v verbose ... 2>&1 | grep fontselect로 실제 선택 파일 확인. - 오디오 loudnorm -14 LUFS · 48kHz. 소프트 방지 lanczos+unsharp(슬라이드 PIP 소스는 얼굴이 저해상 ~430px이라 확대 시 소프트 — 풀프레임 웹캠 원본 있으면 더 선명).
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.
- 13d ago First seen · 67 lines · 84 tokens per session scan A 8cb08e230b47
shorts-producer is an agent published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (21 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 2,246 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 agents, from other repositories
research-collector
Use ONLY as part of the /design-md skill pipeline. Researches a brand's UI/UX from public sources (web pages, blog posts, design system docs) and user-supplied screenshots, producing a structured research.md with citation-numbered claims. Do not invent facts — every concrete claim must trace to a fetched source or a…
policy-report-reviewer
A read-only reviewer for Korean policy research. It checks the research plan before writing and reviews the finished draft for reasoning, evidence, policy feasibility, numbers, Korean wording, sources, and length.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.