claude-video
Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
Runssource: GitHubPythonMITcommit 03ceb42f7fa2
Python, MIT licensed.
claude-video runs. An Argusic agent installed it in 1.2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python venv with pytest and yt-dlp installed, all 249 tests pass, watch.py processes local videos producing frames and markdown reports, setup.py detects all tools, and dist/watch.skill bundle builds correctly.
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, refreshed . 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- unzip not in container; build-skill.sh fails at line 23 but dist/watch.skill is created correctly by git archive
- Install time
- 1 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest -q exited 0 with 249 passed; watch.py --engine local --detail efficient --no-whisper /tmp/test_vid.mp4 printed markdown report with valid JPEG frames; ffmpeg -v error -i each frame -f null - exited 0
- Model tokens used
- 203,953
- Exact commit tested
- 03ceb42f7fa2
- 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.
**Summary of what was verified:**
- **Test suite**: `pytest -q` → 249 passed, 0 failed (includes the yt-dlp integration test after PA…
- **watch.py entry point**: invoked `--engine local` against ffmpeg-synthesized clips (static blue …
- **setup.py**: `--json` mode reports all binaries found when PATH includes the venv; `--check` exi…
- **build-skill.sh**: produces `dist/watch.skill` with 13 valid entries including 1 SKILL.md and al…
The only minor gap is that `unzip` is not installed in the container, so the build script would fai…
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 1…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 1.2, "errors": [{"msg": "u…
tokens used
203,953Replay 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.
- Installed in 1.2 minutes, faster than the median of the 7 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 8 Python projects Argusic has installed and timed, claude-video was the 3rd fastest to reach a running state, and 5 of 8 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.
- A quick evaluation: it was running 1.2 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-video)Questions
- Does claude-video run?
- Yes. claude-video runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test claude-video?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 03ceb42f7fa2. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test claude-video?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-video take to install?
- 1.2 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 claude-video need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-video?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does claude-video compare with the alternatives?
- Of the 8 Python projects Argusic has installed and timed, claude-video was the 3rd fastest to reach a running state, and 5 of 8 reached one at all.
- Where is the evidence for claude-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.