sprite-gen
Generate clean 2D game sprites & animation atlases, component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.
Runssource: GitHubPythonApache-2.0commit b725baa5aad0
Python, Apache-2.0 licensed. The project labels itself: 2d game, ai tools, claude code, codex, game dev, gamedev, pixel art and sprite generation.
sprite-gen runs. An Argusic agent installed it in 1.2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
sprite-gen 2.11.0 installed in Python 3.12 venv with dev deps via pip; Pillow 12.3, NumPy 2.5 resolve; CLI responds with full help text; img2webp 1.5.0 with -exact support on PATH; 2020 tests all pass within 300s timeout
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 60 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.
- 7 video tests failed: img2webp not found on PATH (libwebp CLI tool for WebP output)2 minutes
- 1 pitch-crosscheck test timed out: pyproject.toml default pytest timeout 120s is too short for this test (~210s needed)1 minute
- Install time
- 1 minutes
- Cold machine to finish
- 75 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- python -m pytest collected 2020 tests; after placing img2webp, all 8 originally-failing tests pass individually (5 batch in 27s); sprite-gen --help exits 0
- Model tokens used
- 264,297
- Exact commit tested
- b725baa5aad0
- 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.
timeout method: signal timeout func_only: False collecting ... collected 1 item tests/video/test_motion_anchor.py::test_cli_writes_corrected_cycle_and_gates_rendered_cells PASSED … ========================= 1 passed in 99.20s (0:01:39) ========================= exec /bin/sh -lc "cat << 'ENDOFJSON' ENDOFJSON" in /work/repo succeeded in 0ms: 2026-10-03T23:43:21.694897Z ERROR codex_core::session: failed to record rollout items: thread 01a10… tokens used 264,297
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 1.2 minutes.
- Recovered from all 2 errors 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.32 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.02 |
Topics (from GitHub)
2d-gameai-toolsclaude-codecodexgame-devgamedevpixel-artsprite-generationsprite-sheet
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/sprite-gen)Questions
- Does sprite-gen run?
- Yes. sprite-gen runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test sprite-gen?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b725baa5aad0. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test sprite-gen?
- The run that produced this verdict cost $0.32: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does sprite-gen 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 sprite-gen need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing sprite-gen?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for sprite-gen?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.