vibecut: Instructions file for Codex

AGENTS.md

vibecut AGENTS.md is an instructions file for Codex, OpenCode from AX-Surfers/vibecut. It costs 1,882 tokens per session, scanned C, original, MIT.

Project instructions for Vibecut, a tool that edits CapCut video-project files to automate cuts and subtitles. CapCut is a video-editing application, and the instructions describe Korean speech transcription, error correction, silence removal, and project updates.

In plain words
What is it for?
It is for adding Korean subtitles, correcting recurring transcription errors, removing silent sections, and applying the resulting edits to CapCut projects.
Why use it?
It documents how to use the project's scripts and how they change CapCut projects. This helps keep subtitle generation and automated editing consistent.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions Claude Code; reads ~/.codex paths.

This is AX-Surfers/vibecut's own configuration. It tells Codex and OpenCode how to work on vibecut 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 vibecut configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AX-Surfers/vibecut. 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/AX-Surfers/vibecut/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/AX-Surfers/vibecut

Made for: Codex, OpenCode.

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 AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ax-surfers/vibecut/agents-md"><img src="https://agentmods.dev/badge/instructions/ax-surfers/vibecut/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,882 This file is loaded in full into every session.
When invoked 1,882 The same file — it is already loaded in full.
Security scan C 2 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 $0.01882 $0.01882
Opus 5.5 $0.00753 $0.00753
Sonnet 5.5 $0.00376 $0.00376
Haiku 4.5 $0.00188 $0.00188

Measured 2mo ago against content hash 8ee81bc5cd13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

vibecut AGENTS.md scanned grade C with 2 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 2mo 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.

# 의존성 자동 설치 + 실행 (uv가 없으면: curl -LsSf https://astral.sh/uv/install.sh | sh)

Makes network callslowCapability

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

# 의존성 자동 설치 + 실행 (uv가 없으면: curl -LsSf https://astral.sh/uv/install.sh | sh)
AGENTS.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Vibecut

이 파일은 Codex CLI 및 기타 AGENTS.md 호환 도구에서 자동으로 읽힙니다.
Claude Code 사용자는 .claude-plugin/plugin.json을 통해 더 풍부한 에이전트/스킬을 사용할 수 있습니다.

Codex CLI에서 스킬로 사용하기

plugins/vibecut/skills/*/SKILL.md는 Claude Code 전용이 아니라 Codex CLI가 지원하는 표준 Agent Skills 포맷입니다. ~/.codex/skills/에 각 스킬 폴더를 두면 이 AGENTS.md 없이도 자연어 트리거로 바로 호출됩니다. 설치 방법은 README.md의 "설치 — Codex CLI (Agent Skills)" 섹션 참고.

프로젝트 개요

Vibecut은 CapCut(macOS) 영상 프로젝트의 JSON을 직접 수정하여 컷편집과 자막을 자동화하는 도구입니다.

제공 기능

기능 스크립트 설명
Whisper 자막 생성 scripts/add_subtitles.py faster-whisper로 한국어 자막 + 단어 타임스탬프 추출
한국어 오인식 자동 교정 data/corrections.json 누적 사전으로 매번 같은 오인식 자동 처리
Whisper 전사 scripts/transcribe.py 단어 타임스탬프 포함 {stem}_words.json
NG 판단용 transcript scripts/make_transcript.py 정적(⏸)·미인식 소리(🔊) 표시 → LLM이 NG 구간 판단
컷편집 구간 생성 scripts/make_segments.py Whisper 문장 경계 + NG 제거
자막 (기존 프로젝트) scripts/subtitles_from_cuts.py → scripts/apply_subtitles.py 자막 경계 == 컷 경계, 다른 트랙 보존
CapCut JSON 적용 scripts/capcut_editor.py 4개 파일 동시 갱신, .locked 자동 삭제, 30fps 정렬

Codex CLI 사용법

# 1. 자막 생성 + CapCut 프로젝트 자동 생성
codex --exec "Vibecut을 사용해 ~/Movies/test.mov에 자막을 자동으로 추가해줘. \
  scripts/add_subtitles.py를 호출하고, Whisper 모델은 small을 사용해."

# 2. 검증된 자막으로 적용
codex --exec "before.srt를 검증해서 한국어 오인식을 교정한 뒤 \
  CapCut 0531 프로젝트에 자막 트랙을 추가해줘. \
  corrections.json 사전을 활용해서 같은 패턴은 자동 처리."

# 3. 무음 제거 컷편집
codex --exec "transcribe.py → make_transcript.py로 NG 구간을 찾아 ng_log.json을 만들고 \
  make_segments.py → capcut_editor.py로 CapCut JSON에 적용해줘."

직접 스크립트 호출 (uv 사용)

스크립트들은 uv inline 메타데이터를 포함합니다. 별도 가상환경 불필요:

# 의존성 자동 설치 + 실행 (uv가 없으면: curl -LsSf https://astral.sh/uv/install.sh | sh)
uv run scripts/add_subtitles.py <video.mov> --model small
uv run scripts/transcribe.py <video.mov>
uv run scripts/make_transcript.py <video>_words.json
uv run scripts/make_segments.py --words-json <video>_words.json --ng <video>_ng_log.json
uv run scripts/capcut_editor.py <video>_segments.json --project <CapCut 프로젝트> [--timeline "타임라인 02"]

Read the full file on GitHub · 147 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. 2mo ago Changed · +6 lines · +208 tokens per session 8ee81bc5cd13
  2. 2mo ago First seen · 141 lines · 1,674 tokens per session scan C b444ce0b1b80

Subscribe to this mod's changes

vibecut AGENTS.md is an instructions file published in the GitHub repository AX-Surfers/vibecut (2 stars, last pushed 8d ago), licensed MIT. It adds 1,882 tokens to every session, about $0.0075 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,719 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,516 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,313 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 3,037 tokens