XGP-save-extractor
Python script to extract savefiles out of Xbox Game Pass for PC games
Runs with mockssource: GitHubPythonMITcommit 3e1bf319a976
Python, MIT licensed. The project labels itself: a plague tale requiem, atomic heart, backup, celeste, control, epic games store, final fantasy xv and game saves.
XGP-save-extractor runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python 3.12.3 script runs with zero external dependencies. Parses mock XGP binary container format (containers.index + container.N + GUID files) and produces correct ZIP archives for 1c1f, forza, and state-of-decay-2 handlers with the -- add -- and regular noninteractive mode support.
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 56 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.
- UTF-16 decode with BOM fails on XGP container data (uses UTF-16-LE without BOM)2 minutes
- os.path.expandvars does not expand Windows %VAR% on Linux1 minute
- input() raises EOFError in CI/headless environments1 minute
- Backslash path separators cause Path.exists() to fail on Linux0.5 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- XGP_NONINTERACTIVE=1 LOCALAPPDATA=/tmp/xgp_root python3 main.py exited 0 and created 4 ZIP files. Atomic Heart -> savegame.sav (31B), Hi-Fi RUSH -> slot1.sav+slot2.sav (26B each), Forza Horizon 5 -> profile.profile+settings.settings (33B+34B), State of Decay 2 -> file1.sav+file2.sav+file3.sav (21-25B). Also verified no-games path: XGP_NONINTERACTIVE=1 LOCALAPPDATA=/nonexistent python3 main.py exited 1 with 'No supported games installed'.
- Model tokens used
- 257,439
- Exact commit tested
- 3e1bf319a976
- 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
- Behaviour against real services
- this run was verified against stand-in services only
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 && echo "=== No games (clean path) ===" && XGP_NONINTERACTIVE=1 LOCALAPP… succeeded in 0ms: === No games (clean path) === Xbox Game Pass for PC savefile extractor ======================================== No supported games installed Press enter to quit Exit: 1 Now let me register the final JSON result. 2026-10-11T13:30:13.524188Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce… tokens used 257,439
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
- Installed in 12 minutes.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
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 | Did not run | 20.00 | 0.01 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.07 |
Topics (from GitHub)
a-plague-tale-requiematomic-heartbackupcelestecontrolepic-games-storefinal-fantasy-xvgame-saveshadesjust-cause-4lies-of-pmigrationoctopathtravelerpalworldpython3starfieldsteamtotally-accurate-battle-simulatorxbox-game-passyakuza-0
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/xgp-save-extractor)Questions
- Does XGP-save-extractor run?
- XGP-save-extractor runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test XGP-save-extractor?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3e1bf319a976. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test XGP-save-extractor?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does XGP-save-extractor 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 XGP-save-extractor need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing XGP-save-extractor?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for XGP-save-extractor?
- 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.