claude-code-video-toolkit
AI-native video production toolkit for Claude Code
Runssource: GitHubPythonMITcommit f91608aa3750
Python, MIT licensed. The project labels itself: ai video generator, claude code, developer tools, elevenlabs, open source, openclaw, playwright and programmatic video.
claude-code-video-toolkit runs. An Argusic agent installed it in 12 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Hello-world, sprint-review template, render-baseline test, and concept-explainer-short template all render valid MP4 videos; migration script fixed and installs all 27 skills/commands; verify_setup.py confirms all prerequisites met.
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 90 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.
- scripts/migrate_to_codex.py: write_text function referenced but not defined in _migrate_common.py, causing NameError2 minutes
- product-demo template render fails: missing public/audio/background-music.mp3 (expected — template needs user assets)
- Install time
- 12 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- Model tokens used
- 165,961
- Exact commit tested
- f91608aa3750
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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.
3. **Ran `npm install` in hello-world example** — installed Remotion 4.0.518 and dependencies 4. **Rendered hello-world video** — produced a valid 25s H.264+AAC MP4 5. **Ran `npm install` in render-baseline test** — installed test dependencies 6. **Rendered render-baseline video** — produced a valid 6s H.264+AAC MP4 7. **Ran `npm install` in sprint-review template** — installed dependencies 8. **Rendered sprint-review video** — produced a valid 120s H.264+AAC MP4 at 1920x1080 9. **Ran `npm install` in product-demo template** — install succeeded; render failed due to missing… 10. **Built concept-explainer-short Python template** — rendered a valid 49.7s H.264 MP4 using movi… 11. **Fixed `scripts/migrate_to_codex.py`** — the `write_text` function was referenced but not defi… 12. **Ran migration script successfully** — installed 12 toolkit skills + 14 command wrappers + 1 o… 13. **Ran `verify_setup.py`** — confirmed Node.js, Python, FFmpeg all present; cloud GPU services p… The product-demo template failed to render because it expects user-provided audio assets (`public/a…
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.
- Installed in 12 minutes.
- 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
- Hit 2 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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)
ai-video-generatorclaude-codedeveloper-toolselevenlabsopen-sourceopenclawplaywrightprogrammatic-videoqwen-ttsremotiontext-to-speechvideo-editingvideo-production
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-code-video-toolkit)Questions
- Does claude-code-video-toolkit run?
- Yes. claude-code-video-toolkit runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test claude-code-video-toolkit?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f91608aa3750. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test claude-code-video-toolkit?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-code-video-toolkit take to install?
- 12 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-code-video-toolkit need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-code-video-toolkit?
- 2 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for claude-code-video-toolkit?
- 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.