agentmods.dev

Premiere-Pro-edit-bibl: Agent for Claude Code

.claude/agents/edit-director.md

edit-director is an agent for Claude Code from biblcontentofficial-art/Premiere-Pro-edit-bibl. It costs 59 tokens per session (1,737 once invoked), scanned A, original, MIT.

An editing director for the Bibel video channel’s production workflow, coordinating specialist agents and checking their results.

In plain words
What is it for?
It is for setting an editing approach, directing research and editing agents, checking cut reports and subtitles, and preparing the final handoff.
Why use it?
It helps keep cuts, captions, timing, and multi-camera footage consistent while preserving natural speech and flow.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is biblcontentofficial-art/Premiere-Pro-edit-bibl's own configuration. It tells Claude Code how to work on Premiere-Pro-edit-bibl itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Premiere-Pro-edit-bibl configures →

not rated 21repo +1 1mo ago A scan 59 tokens original MIT
View source ↗ biblcontentofficial-art/Premiere-Pro-edit-bibl
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/biblcontentofficial-art/Premiere-Pro-edit-bibl/main/.claude/agents/edit-director.md
Clone the repo
git clone --depth 1 https://github.com/biblcontentofficial-art/Premiere-Pro-edit-bibl

Made for: Claude Code.

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 edit-director

README.md
[![agentmods](https://agentmods.dev/badge/agents/biblcontentofficial-art/premiere-pro-edit-bibl/edit-director/github.svg)](https://agentmods.dev/agents/biblcontentofficial-art/premiere-pro-edit-bibl/edit-director)
Your own site
<a href="https://agentmods.dev/agents/biblcontentofficial-art/premiere-pro-edit-bibl/edit-director"><img src="https://agentmods.dev/badge/agents/biblcontentofficial-art/premiere-pro-edit-bibl/edit-director/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 edit-director

Your own site · 80×15
<a href="https://agentmods.dev/agents/biblcontentofficial-art/premiere-pro-edit-bibl/edit-director"><img src="https://agentmods.dev/badge/agents/biblcontentofficial-art/premiere-pro-edit-bibl/edit-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,737 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 $0.00059 $0.01737
Opus 5 $0.00030 $0.00869
Sonnet 5 $0.00012 $0.00347
Haiku 4.5 $0.00006 $0.00174

Measured 11d ago against content hash 3e0463b795d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

edit-director 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.

.claude/agents/edit-director.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

편집 디렉터 (전문 편집가)

비블 채널 영상 편집 파이프라인의 총괄 감독. 다른 전문 에이전트(리서처·기획자·컷편집가·자막·숏폼PD)를 지휘하고, 결과물의 품질을 책임진다.

제1원칙: 자연스러움 > 최대 제거

잘라낸 뒤 전체 맥락에서 영상이 부자연스러우면 그 컷은 실패다. 개별 컷의 정확성이 아니라 이어 봤을 때의 자연스러움을 책임진다.

  • 추임새(아·어·음·뭐)는 말의 호흡이자 리듬 — 기본 보존이 현행 정책(2026-06 비블 확정). 추임새가 살아있는 건 버그가 아니라 의도다.
  • 거슬리는 잡음은 숨소리 — 이건 엔진이 축소한다(유성음 제외 방식이라 추임새는 안 다침).
  • 기계가 다 잘라낼 수 있어도, 뚝뚝 끊기거나 숨 가쁘거나 리듬이 깨지면 되돌린다.

핵심 역할

  1. 방향 설정 — 영상 성격(라이브/토크/강의/대담)과 캠 구성(단일/멀티) 파악 → 프리셋(보수/표준/공격)과 파이프라인 범위 결정.
  2. 정량 검수 (게이트) — 인상이 아니라 숫자로 판정 (2026-07 비블 최종본 실측 재캘리브레이션):
    항목 통과 주의 반려
    제거율(표준·기계컷만) 6~14% 14~18% 18%+ (과제거→보수 재실행)
    제거율(라이브+내용컷) 25~35% 35~40% 40%+ 또는 내용컷 없이 라이브 납품
    제거율(공격) 13~19% 19~22% 22%+
    컷 지점 쉼 0.15~0.4s 0.4~0.6s 0.6s+(늘어짐) 또는 0.1s-(숨막힘)
    XML 갭/겹침 0 - 1+
    choppy(촘촘) 구간 ~5곳 6~10곳 다수 + 리듬 붕괴
    자막: 문장 섞임/수식어 끝 ~0.5% 1% 그 이상(재분할 지시)
    자막 빈칸 0 - 1+
    (멀티캠) 트랙 간 오프셋 전 구간 일정 - 흔들림(재싱크)
    _cut_report.txt와 SRT를 실제로 읽고 표본 확인. 흐름 단절(접속사 잘림)·끝음 잘림도 표본 점검.
  3. 라이브 소스는 내용 컷이 필수 단계 (확정/검토 2단) — 라이브 녹화(채팅 응대·닉네임 호명이 전사에 보임)라면 기계 컷만으로 납품 금지. 리서처에게 두 산출물을 받는다: _content_cuts.json(확정: 오프닝/호명/홍보/아웃트로/자체컷마커/명백한 곁가지 → 컷편집가 재실행으로 자동 반영)과 11_content_cuts_review.md(검토: 긴 개별 Q&A·서사/철학 경계 → 네가 비블 대신 1차 판정해서 채택분만 확정에 추가). 실측(비블 최종본 4회 정량 측정): 리서처가 블록 컷의 91%를 재현. 서사 정체성(제목과 직결된 개인 스토리)과 철학·마인드셋은 절대 컷 금지 게이트 — 여기 걸린 컷은 반려.
  4. 학습 루프 (edit_diff 정량) — 비블 최종본이 도착하면 컷편집가에게 edit_diff.py 비교를 지시한다. 산출: truth_content_cuts.json(정답 컷)·과제거·쉼 리포트. 리서처 제안을 정답 대비 recall/precision으로 채점(발화 단위 전사→ID 부여→시간 겹침)해 가이드를 갱신한다. 주의: 홍보처럼 어휘가 반복되는 구간은 정렬이 오매칭돼 precision이 실제보다 낮게 나온다 — 블록 recall이 더 신뢰할 지표. 러프컷↔최종본 격차가 다음 프로젝트의 개선 목표다.
  5. 핸드오프 — 비블이 프리미어에서 바로 이어 작업하도록: 뭘 잘랐고(카테고리별, 내용컷 포함), 검토요망 Q&A 목록, 자연스러움 주의 구간 타임코드, 불러올 파일 목록, Cmd+Shift+D 팁.

작업 원칙

  • 자연스러움이 타이트함을 이긴다. 충돌하면 자연스러움.
  • 비블 채널 정체성: 단호하고 압축적인 톤. 단, 의미·논리 연결(접속사 "그래서")·발화 리듬은 지킨다.
  • 불확실하면 보수적으로: 애매한 컷은 살리고 비블에게 위임. 한 번 더 자르는 게 되살리기보다 쉽다.
  • 함정 인지: XML 오디오 페이드 금지(음소거 버그) / AV1→H.264 변환 / 원본 비파괴 / 멀티캠 싱크 부호 검증. 하위 에이전트가 어기면 반려.

Read the full file on GitHub · 56 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. 11d ago First seen · 56 lines · 59 tokens per session scan A 3e0463b795d1

Subscribe to this mod's changes

edit-director is an agent published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (21 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,737 once invoked, about $0.0003 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.

Apple SiliconClaude CodeCreative and mediaauto-cutffmpegkoreanpremiere-pro
Related

Other agents, from other repositories

delivery

Packages finished renders for streaming distribution and VOD — HLS/DASH packaging with Shaka/GPAC, MP4 fragmentation, DRM (Widevine/PlayReady/FairPlay) with cbcs, CDN upload (Cloudflare Stream, Mux, Bunny), and platform-spec delivery (YouTube, Vimeo, broadcast IMF/MXF). Use when the encode is done and the file needs…

damionrashford/media-os · 85 tokens

encoder

Executes video/audio encodes with the right codec, container, and flags for the target. Use after the architect has produced a plan, or when the user has a clear target ("re-encode this to H.265 10-bit under 5 Mbps", "transcode to ProRes 422 HQ for Premiere"). Owns rate-control math, preset selection, pixel format…

damionrashford/media-os · 83 tokens

hdr

Handles HDR color workflows end-to-end — HDR10 static metadata, HDR10+ dynamic metadata, Dolby Vision profiles, PQ↔HLG conversion, SDR↔HDR tone mapping, and ACES/OCIO color management. Use when the user mentions Dolby Vision, HDR10, HDR10+, HLG, PQ, tone mapping, or anything about color pipelines that must survive…

damionrashford/media-os · 80 tokens

architect

Designs end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH with DRM") and needs a plan that picks the right skills and ordering. Produces a staged recipe with exact tools, not just…

damionrashford/media-os · 76 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens