GameDesignOS

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory, Human Gates and rollback.

Runssource: GitHubPythonMITcommit ada4bf9e60c2

Python, MIT licensed. The project labels itself: agent skills, ai agents, decision support, game analysis, game design, game design tools, game development and game research.

GameDesignOS runs. An Argusic agent installed it in 1 minute and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

gamedesignos 1.3.0.dev0 is installed in a virtualenv, its 89-test unittest suite passes, and a complete decision-to-accept workflow (evidence, experiment, review, Human Gate accept, VOI, gates, graph, pack) runs successfully on a created workspace

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.07 (measured)
recorded runs
1
last tested
stars
451
forks
58
open issues
1
watchers
0
size
43 MB
created
last push

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.

Time lost to each failure while testing GameDesignOS, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • PEP 668 externally-managed environment blocked system-wide pip install2 minutes
  • scripts/validate_agent_skills.py failed: agentskills not found because venv bin was not on PATH2 minutes
  • `python` is not on PATH in this container (only `python3`)1 minute
Install time
1 minutes
Cold machine to finish
5 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
python -m unittest discover -s scripts/tests exited 0 with 89/89 tests OK; coverage report 83%; gamedesignos --version printed 'gamedesignos 1.3.0.dev0'; demo and start created workspaces; full decision accept/gate/voi/workflow/validate/pack cycle on /tmp/lighthouse-designos all returned success; run_behavior_evals.py --all-packaged printed 'OK: 11 packaged suites, 72 behavior evals'; validate_agent_skills.py printed 'OK: 7 Agent Skills packages validated'
Model tokens used
310,403
Exact commit tested
ada4bf9e60c2
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.

310,403
All verification complete. The project installs, its full test suite runs, and the core CLI workflo…
**Summary of work**
- Install: `python3` (not `python` on PATH) → PEP 668 blocked system-wide pip → fixed with a virtua…
- Fresh-user entry points: `gamedesignos --version` → `gamedesignos 1.3.0.dev0`; `demo` created a s…
- CI parity checks: 89/89 unit tests pass, coverage 83% (baseline 80), `validate_repo.py` passes, 1…
- Real end-to-end: `start "Lighthouse Tactics"` created a workspace; a full decision cycle ran — ev…
- No real credentials required: the Argusic-compatible host was exercised with its shipped offline …
**Errors recorded**
1. `python: not found` — only `python3` on PATH. Fix: use `python3` for all commands.
2. PEP 668 `externally-managed-environment` blocked system-wide `pip install`. Fix: created a virtu…
3. `validate_agent_skills.py` printed "`agentskills` is not installed" although the venv contains i…

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 minute, faster than the median of the 118 comparable projects Argusic has measured.
  • Recovered from all 3 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 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 119 agent-skills projects Argusic has installed and timed, GameDesignOS was the 27th fastest to reach a running state, and 90 of 119 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 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.07

Topics (from GitHub)

agent-skillsai-agentsdecision-supportgame-analysisgame-designgame-design-toolsgame-developmentgame-researchhuman-in-the-loopindie-gamelocal-firstpythonworkflow-automation

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/GameDesignOS.svg)](https://argusic.com/subject/gamedesignos)

Questions

Does GameDesignOS run?
Yes. GameDesignOS runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test GameDesignOS?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ada4bf9e60c2. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test GameDesignOS?
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 GameDesignOS take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does GameDesignOS need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing GameDesignOS?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does GameDesignOS compare with the alternatives?
Of the 119 agent-skills projects Argusic has installed and timed, GameDesignOS was the 27th fastest to reach a running state, and 90 of 119 reached one at all.
Where is the evidence for GameDesignOS?
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.

Discussion