rea-video
Reverse-engineer any video, shot by shot: tells whether each shot was filmed, AI-generated or coded, how the captions, cuts and audio were made, and how to remake it. 逆向一切视频，逐镜拆出制作方式并给出复刻方案。
Runssource: GitHubPythonApache-2.0commit c6cbc9185bae
Python, Apache-2.0 licensed. The project labels itself: agent skills, ai video, aigc detection, claude code, codex, douyin, ffmpeg and prompt engineering.
rea-video runs. An Argusic agent installed it in 22 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
All 88 pytest tests pass, the rea-video CLI is fully installed in a Python venv, and all core subcommands (decompose, probe, stems, summary, review, tiles, correct, memory) work on real input video. The decompose pipeline successfully detects shots, classifies production methods, generates breakdown.json and report.html, and extracts stems via onnxruntime (UVR model auto-downloaded).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- 22 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- rea-video --help returned usage (CLI installed); pytest -q: 88 passed in 237s; rea-video decompose on dual_role.mp4: 10 shots, report.html generated; rea-video probe returned video metadata; rea-video summary printed full verdict; rea-video stems extracted valid vocals/music WAVs; rea-video review/apply-review/correct workflows exercised; rea-video tiles generated 5 tile images
- Model tokens used
- 58,661
- Exact commit tested
- c6cbc9185bae
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/bin/sh -lc 'cd /work/repo && /home/runner/venv/bin/rea-video memory 2>&1' in /work/repo succeeded in 98ms: 记忆目录: /home/runner/.rea-video 偏好: （未设置） 纠正: 1 条，涉及 1 条视频 工具「代码/模板渲染」→ 用户「AI 生成视频」 1 个镜头 / 1 条视频 备注（dual_role.mp4 shot_001）: test correction 把纠正过的视频导出为评测样本：rea-video memory --export-labels eval/user_labels.yaml All done. Here's the full report: tokens used 58,661 All done. Here's the full report:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 22 minutes to install, slower than the median of the 108 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 109 agent-skills projects Argusic has installed and timed, rea-video was the 97th fastest to reach a running state, and 80 of 109 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- Following its own README: the documented path worked with nothing to fix.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsai-videoaigc-detectionclaude-codecodexdouyinffmpegprompt-engineeringremotionreverse-engineeringshort-videoshot-detectionsubtitlestiktokvideo-analysisvideo-breakdownvideo-editingvideo-generationvlm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/rea-video)Questions
- Does rea-video run?
- Yes. rea-video runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test rea-video?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c6cbc9185bae. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test rea-video?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does rea-video take to install?
- 22 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does rea-video need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing rea-video?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does rea-video compare with the alternatives?
- Of the 109 agent-skills projects Argusic has installed and timed, rea-video was the 97th fastest to reach a running state, and 80 of 109 reached one at all.
- Where is the evidence for rea-video?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.