vibecut-auto-edit

vibecut-auto-edit is a skill for Claude Code from AX-Surfers/vibecut. It costs 153 tokens per session (5,983 once invoked), scanned D, original, MIT.

A video-editing workflow that transcribes speech with Whisper, asks Claude to identify unwanted sections, removes those sections, and updates the CapCut project. NG means a failed, repeated, or incomplete take.

In plain words
What is it for?
Use it to remove silent parts, failed takes, repeated speech, and incomplete phrases from videos before applying the cuts in CapCut.
Why use it?
It reduces the need to watch the entire recording and find mistakes by hand. The transcript is reviewed in context so repeated or unfinished speech can be identified.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the vibecut plugin — 4 skills shipped together

Good fit Use it to remove silent parts, failed takes, repeated speech, and incomplete phrases from videos before applying the cuts in CapCut.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ax-surfers/vibecut/vibecut-auto-edit
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 AX-Surfers/vibecut --skill vibecut-auto-edit
Clone the repo
git clone --depth 1 https://github.com/AX-Surfers/vibecut

Made for: Claude Code.

Or install vibecut, the plugin that ships this one along with the rest of its 4 skills.

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 vibecut-auto-edit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ax-surfers/vibecut/vibecut-auto-edit/github.svg)](https://agentmods.dev/skills/ax-surfers/vibecut/vibecut-auto-edit)
Your own site
<a href="https://agentmods.dev/skills/ax-surfers/vibecut/vibecut-auto-edit"><img src="https://agentmods.dev/badge/skills/ax-surfers/vibecut/vibecut-auto-edit/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 vibecut-auto-edit

Your own site · 80×15
<a href="https://agentmods.dev/skills/ax-surfers/vibecut/vibecut-auto-edit"><img src="https://agentmods.dev/badge/skills/ax-surfers/vibecut/vibecut-auto-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,983 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00153 $0.05983
Opus 5 $0.00077 $0.02991
Sonnet 5 $0.00031 $0.01197
Haiku 4.5 $0.00015 $0.00598

Measured 7d ago against content hash 1e1fcdf4ee59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

vibecut-auto-edit scanned grade D with 3 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 7d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

which uv || curl -LsSf https://astral.sh/uv/install.sh | sh

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

SCRIPTS=$(find "${HOME}/.claude/plugins/cache/vibecut" -name "capcut_editor.py" -maxdepth 8 2>/dev/null | head -1 | xargs dirname 2>/dev/null)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

which uv || curl -LsSf https://astral.sh/uv/install.sh | sh
plugins/vibecut/skills/vibecut-auto-edit/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibecut-auto-edit 스킬

영상 → Whisper 전사 → 정적 표시 transcript → Claude NG 판단 → 사용자 검토 → CapCut 적용 → 자막 파이프라인.

핵심 원리

Whisper가 전사한 단어 타임스탬프와 실제 오디오의 정적 구간을 함께 펼친 transcript를 Claude가 직접 읽고 NG 구간을 판단합니다.

  • 키워드/유사도 방식은 문장 내부 반복, 3~4회에 걸친 점진적 반복, 불완전 발화를 못 잡음
  • Whisper 대본만 읽으면 말이 멈춘 정적을 못 봄 — Whisper가 멈춘 시간을 앞 단어 길이에 흡수시키기 때문. 그래서 make_transcript.py가 ffmpeg로 정적을 재서 표시를 끼워 넣음

처리 흐름

영상 (.mov/.mp4)                     ※ 모든 중간 파일은 영상 옆에 {stem}_*.json 으로 저장
   │                                   (영상이 여러 개여도 섞이지 않고, 캐시 재사용도 안전)
   ├─ [0] 프로젝트·타임라인 찾기 (find_project.py) — 사용자에게 묻지 않고 자동 탐색
   ├─ [1] transcribe.py            → {stem}_words.json
   ├─ [2] make_transcript.py       → {stem}_transcript.txt (⏸ 정적 / 🔊 인식 안 된 소리 표시)
   │      Claude가 읽고 NG 판단   → {stem}_ng_log.json
   ├─ [2-D] 사용자 사전 검토        번호 리스트 → 승인/제외 반영
   ├─ [3] make_segments.py         → {stem}_segments.json
   ├─ [3-B] 프로젝트 상태 점검
   ├─ [4] capcut_editor.py --timeline <이름>   4개 파일 갱신 + 자동 백업
   ├─ [5] 자막 자동 연결            subtitles_from_cuts.py → 분할 → apply_subtitles.py
   └─ [6] vibecut app으로 열기

전제 조건 (모든 Bash 블록 앞에 한 번)

which uv || curl -LsSf https://astral.sh/uv/install.sh | sh

VIBECUT_CONFIG="${HOME}/.vibecut/config.json"
SCRIPTS=""
if [ -f "${VIBECUT_CONFIG}" ]; then
  SCRIPTS=$(python3 -c "import json; print(json.load(open('${VIBECUT_CONFIG}')).get('scripts_dir',''))" 2>/dev/null)
fi
if [ -z "${SCRIPTS}" ]; then
  SCRIPTS=$(find "${HOME}/.claude/plugins/cache/vibecut" -name "capcut_editor.py" -maxdepth 8 2>/dev/null | head -1 | xargs dirname 2>/dev/null)
fi
if [ -z "${SCRIPTS}" ]; then
  APP_DIR="${HOME}/.vibecut/app"
  if [ -d "${APP_DIR}/.git" ]; then
    git -C "${APP_DIR}" pull --ff-only >/dev/null 2>&1
  else
    git clone --depth 1 https://github.com/AX-Surfers/Vibecut.git "${APP_DIR}" >/dev/null 2>&1
  fi
  [ -f "${APP_DIR}/scripts/capcut_editor.py" ] && SCRIPTS="${APP_DIR}/scripts"
fi
[ -z "${SCRIPTS}" ] && echo "❌ vibecut-setup 먼저 실행" && exit 1

uv run "${SCRIPTS}/_platform.py" quit-capcut

Read the full file on GitHub · 386 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. 7d ago Changed · -1 lines · +48 tokens per session 1e1fcdf4ee59
  2. 10d ago First seen · 387 lines · 105 tokens per session scan D 7be3e3797c95

Subscribe to this mod's changes

vibecut-auto-edit is a skill published in the GitHub repository AX-Surfers/vibecut (2 stars, last pushed 7d ago), licensed MIT. It adds 153 tokens to every session and 5,983 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens