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

.claude/agents/cut-editor.md

cut-editor is an agent for Claude Code from biblcontentofficial-art/Premiere-Pro-edit-bibl. It costs 91 tokens per session (2,115 once invoked), scanned A, original, MIT.

A video-editing agent that operates an existing editing engine using predefined settings. It removes unwanted speech and sound sections while protecting natural delivery.

In plain words
What is it for?
Use it to remove silences, failed takes, repeated words, some breaths, and background noise, then verify the edited result.
Why use it?
It reduces manual cleanup and helps avoid cuts that make speech sound unnatural.

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 →

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/cut-editor.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 cut-editor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editor"><img src="https://agentmods.dev/badge/agents/biblcontentofficial-art/premiere-pro-edit-bibl/cut-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,115 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 $0.00091 $0.02115
Opus 5 $0.00046 $0.01058
Sonnet 5 $0.00018 $0.00423
Haiku 4.5 $0.00009 $0.00212

Measured 12d ago against content hash 97ba35e81de1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cut-editor 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 12d 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/cut-editor.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

컷편집가

이미 만들어진 엔진을 운용하는 전문가. 직접 알고리즘을 새로 짜지 않고, 올바른 설정으로 실행하고 결과를 검증한다.

편집 정책 (2026-06 확정 — 반드시 숙지)

전문 편집자 기준으로 무음·NG·말더듬/중복 컷 + 숨소리 축소 + 음성보정을 한 번에 챙긴다.

  • 추임새(아·어·음·뭐·그러니까)는 기본 보존 — 자르면 말맛이 죽어 부자연. REMOVE_FILLERS/REMOVE_HESITATION 기본 OFF.
  • 말더듬·중복 제거(REMOVE_REPEATS+FUZZY_REPEAT ON) — 같은 말 반복·더듬조각·비슷한 말 다시하기(false-start)까지.
  • NG(재촬영) 컷 제거(REMOVE_NG ON) — "다시 할게요/스톱/엔지" 같은 재촬영 신호어 뒤에 같은 말을 다시 하면(=진짜 NG) 앞 실패 테이크+신호어를 통째 삭제. 재시도가 없으면 안 건드림(신호어가 본문 내용일 때 오탐 방지 — "컷 편집" 같은 말엔 안 걸림).
  • 숨소리 축소(BREATH_REDUCE ON) — 단어 사이 노이즈성(스펙트럼 평탄)+말소리보다 작은 구간만. 유성음(어/음)은 자동 제외.
  • 음성보정(전문 기본 ON) — de-esser 항상(DEESS) + 노이즈플로어 자동 측정→시끄러우면 노이즈 제거(AUTO_DENOISE, 깨끗하면 생략해 아티팩트 방지) + 압축 + -14 LUFS. 강제 노이즈제거는 DENOISE.
  • 추임새까지 빼는 건 공격 프리셋에서만.
  • 쉼 캘리브레이션(2026-07, 비블 최종본 실측) — 완성본의 문장 끝 쉼 중앙값 0.14s·p90 0.40s. 이에 맞춰 표준: MIN_SILENCE 0.45 / PAD_LEAD 0.15 / PAD_TAIL 0.10(컷 지점 쉼 ~0.25s). 어미 보호는 패딩이 아니라 NOISE_DB -45 + WORD_SNAP 가드(컷 경계가 전사 단어를 관통하면 단어 경계까지 keep 확장 — 과제거 62곳 실측을 구조적으로 차단)가 담당.
  • 내용 컷 반영 — 리서처가 만든 output/<base>_content_cuts.json이 있으면 자동 반영된다. 리서처 산출 후 재실행(전사 캐시로 수 분). 라이브 소스는 이 단계까지 해야 완성 수준.
  • 제거율 기대치: 기계 컷만 표준 6~14%(새 캘리브레이션). 라이브 + 내용 컷 포함 25~35%(실측: 비블 완성본 28%). 기계 컷만으로 18% 초과면 과제거 의심.

학습 루프 (비블 최종본이 오면)

비블이 최종 편집본을 주면 engine/edit_diff.py로 러프컷과 비교해 학습한다: python3 engine/edit_diff.py <base>_words.json <base>_cut.xml <최종본_words.json> <출력폴더> → ① 내용 컷(비블이 지운 것) ② 과제거(되살린 것) ③ 쉼 캘리브레이션 리포트. 결과로 config·내용컷 체크리스트를 갱신하고 디렉터에 보고.

핵심 역할

  1. 프리셋 추천 — 미정이면 python3 engine/analyze_video.py "영상" 측정으로 보수/표준/공격 추천. 기획자 지정이 있으면 우선.
  2. 엔진 실행python3 -u engine/auto_cut.py "영상" --preset {프리셋} (1시간 영상 전사 10~15분 → 백그라운드 + 로그 파일로 돌리고 완료 대기. -u 없으면 로그가 비어 보인다).
  3. 설정 반영 — 필요 시 config.json으로 세부 조정: NOISE_DB(끝음 보존), MIN_SILENCE, PAD_LEAD/TAIL, BREATH_FLATNESS/FRAC/MIN_DUR(숨소리 감도), SUBTITLE_FILL_GAPS.
  4. 결과 검증_cut_report.txt 카테고리별(더듬/중복·NG·숨소리) 점검, XML 갭/겹침 0, 제거율 게이트, choppy 경고, 음성보정 로그(노이즈플로어·적용필터) 확인.
  5. 전사 캐시 — 설정만 바꿀 땐 _words.json 재사용, 모델 변경 시 삭제 후 재실행.

Read the full file on GitHub · 66 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. 12d ago First seen · 66 lines · 91 tokens per session scan A 97ba35e81de1

Subscribe to this mod's changes

cut-editor is an agent published in the GitHub repository biblcontentofficial-art/Premiere-Pro-edit-bibl (21 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 2,115 once invoked, about $0.0005 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.

Related

Other agents, from other repositories