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 AX-Surfers/vibecut --skill vibecut-auto-editgit clone --depth 1 https://github.com/AX-Surfers/vibecutWrote 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/ax-surfers/vibecut/vibecut-auto-edit)<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.
<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>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 | $0.00153 | $0.05983 |
| Opus 5 | $0.00077 | $0.02991 |
| Sonnet 5 | $0.00031 | $0.01197 |
| Haiku 4.5 | $0.00015 | $0.00598 |
Grade D, and why
vibecut-auto-edit scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
which uv || curl -LsSf https://astral.sh/uv/install.sh | sh Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SCRIPTS=$(find "${HOME}/.claude/plugins/cache/vibecut" -name "capcut_editor.py" -maxdepth 8 2>/dev/null | head -1 | xargs dirname 2>/dev/null) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
which uv || curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibecut-auto-edit 스킬
영상 → Whisper 전사 → 정적 표시 transcript → Claude NG 판단 → 사용자 검토 → CapCut 적용 → 자막 파이프라인.
핵심 원리
Whisper가 전사한 단어 타임스탬프와 실제 오디오의 정적 구간을 함께 펼친 transcript를 Claude가 직접 읽고 NG 구간을 판단합니다.
- 키워드/유사도 방식은 문장 내부 반복, 3~4회에 걸친 점진적 반복, 불완전 발화를 못 잡음
- Whisper 대본만 읽으면 말이 멈춘 정적을 못 봄 — Whisper가 멈춘 시간을 앞 단어 길이에
흡수시키기 때문. 그래서
make_transcript.py가 ffmpeg로 정적을 재서⏸표시를 끼워 넣음
처리 흐름
영상 (.mov/.mp4) ※ 모든 중간 파일은 영상 옆에 {stem}_*.json 으로 저장
│ (영상이 여러 개여도 섞이지 않고, 캐시 재사용도 안전)
├─ [0] 프로젝트·타임라인 찾기 (find_project.py) — 사용자에게 묻지 않고 자동 탐색
├─ [1] transcribe.py → {stem}_words.json
├─ [2] make_transcript.py → {stem}_transcript.txt (⏸ 정적 / 🔊 인식 안 된 소리 표시)
│ Claude가 읽고 NG 판단 → {stem}_ng_log.json
├─ [2-D] 사용자 사전 검토 번호 리스트 → 승인/제외 반영
├─ [3] make_segments.py → {stem}_segments.json
├─ [3-B] 프로젝트 상태 점검
├─ [4] capcut_editor.py --timeline <이름> 4개 파일 갱신 + 자동 백업
├─ [5] 자막 자동 연결 subtitles_from_cuts.py → 분할 → apply_subtitles.py
└─ [6] vibecut app으로 열기
전제 조건 (모든 Bash 블록 앞에 한 번)
which uv || curl -LsSf https://astral.sh/uv/install.sh | sh
VIBECUT_CONFIG="${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
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.
- 7d ago Changed · -1 lines · +48 tokens per session 1e1fcdf4ee59
- 10d ago First seen · 387 lines · 105 tokens per session scan D 7be3e3797c95
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.
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.
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…
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.
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.