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 agentmods add skills/whitetowerai/cut-as-code/video-edit-comparenpx skills add WhiteTowerAI/cut-as-code --skill video-edit-comparegit clone --depth 1 https://github.com/WhiteTowerAI/cut-as-codeWrote 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/whitetowerai/cut-as-code/video-edit-compare)<a href="https://agentmods.dev/skills/whitetowerai/cut-as-code/video-edit-compare"><img src="https://agentmods.dev/badge/skills/whitetowerai/cut-as-code/video-edit-compare.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00666 |
| Opus 5 | $0.00019 | $0.00333 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
video-edit-compare 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Edit Compare
Render the single V1 comparison mode: original-vs-final-source-time.
The left panel plays the original continuously. The right panel projects actual final-delivery pixels back onto the original source clock. Dropped ranges are black, kept final ranges are stretched to their source duration, and audio is copied from the original.
Dependencies
Require ffmpeg/ffprobe on PATH and Python with Pillow. Check them before processing media.
Inputs
work/timeline.json: canonical chronological source-to-program mappinginput/original-video.mp4: original sourcefinal/final-video.mp4: actual delivery after all selected edits
Do not compare against a cut plan or an intermediate render. The final pixels are required so the review includes grade and cards.
Render
python scripts/make_compare.py TIMELINE.json SOURCE.mp4 FINAL.mp4 OUT.mp4 [--filter-only]
Project example:
python skills/video-edit-compare/scripts/make_compare.py `
work/timeline.json `
input/original-video.mp4 `
final/final-video.mp4 `
review/04-edit-compare/original-vs-final-source-time.mp4
The script always writes the durable work/edit-compare/compare-plan.json. It writes PIL
label images and the generated filtergraph under disposable work/cache/.
--filter-only creates the plan and inspectable cache files without rendering the video.
Mapping Rules
- Keep source clips chronological, non-overlapping, and single-source.
- Trim each clip's
program_rangefrom the final video. - Stretch it by the clip speed to recover its
source_rangeduration. - Insert black for every source-time gap.
- Map the original audio without retiming it.
- Derive every part's start and end frame from its absolute source-time boundaries, then trim to that frame count and rebuild PTS at the timeline's rational FPS. Never round each part duration independently; cumulative concat rounding causes source-time drift.
Reordered, duplicated, overlapping, nonlinear-speed, or multi-source timelines are unsupported in V1 and must fail validation.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 73 lines · 38 tokens per session scan A 345f4e621d77
video-edit-compare is a skill published in the GitHub repository WhiteTowerAI/cut-as-code (11 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 666 once invoked, about $0.0002 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.
Other skills, from other repositories
smart-video-editor
把多段原始素材剪成一条成片——先用视觉模型看懂每段画面拍了什么、哪几秒可用，再决定取舍、顺序、时长、调色和 BGM，最后用 ffmpeg 渲染。适用于"我给你几段视频，帮我剪一条小红书/朋友圈/vlog"这类需求。当用户提供视频文件并希望剪辑、拼接、配乐、调色、转成竖屏时使用。不做 AI 生成视频。.
openstoryline-use
Use this skill when OpenStoryline is already installed and the user wants to start the local MCP/Web services, create or continue a session, send editing instructions, perform multi-turn re-editing, and verify rendered video outputs, as well as Chinese requests like “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “用…
create_profile_style_skill
【META SKILL】分析当前剪辑逻辑与风格，总结并生成一个新的可复用 Skill 文件，存入剪辑技能库。Analyze the current editing logic and style, summarize and generate a new reusable Skill file, and store it in the editing skill library.
subtitle_imitation_skill
【CAPABILITY SKILL】基于用户提供的参考文案样本，对视频素材内容进行深度文风仿写，生成风格化脚本。Based on user-provided reference text samples, the video material is deeply rewritten in terms of writing style to generate a stylized script.
premiere-pro-mcp
Install, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues.
ai_transition_editing_skill
【WORKFLOW SKILL】使用 AI 生成的转场将用户素材串联起来。.