claw-code
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex, developed and maintained with no human intervention.
Runssource: GitHubRustMITcommit 08106b0c3771
Rust, MIT licensed.
claw-code runs. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The claw CLI binary builds and runs at /work/repo/rust/target/debug/claw, the full Rust test suite (1416 tests) and Python test suite (47 tests) pass cleanly, the mock-anthropic-service starts, and all workspace crates compile without errors.
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 96 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.
- Install time
- 2 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- cargo test --workspace exited 0 with 1416 Rust tests passed + python -m unittest discover -s tests exited 0 with 47 Python tests passed; ./target/debug/claw --version printed Claw Code 0.1.3; ./target/debug/claw doctor reported 9 OK / 3 warnings (expected missing API key and sandbox); install.sh completed all 6 steps successfully
- Model tokens used
- 59,060
- Exact commit tested
- 08106b0c3771
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Ran 47 tests in 3.244s OK --- Python tests done --- --- Rust tests --- 1416 tests passed All verification complete. Let me compile the final result exec /bin/sh -lc 'start_time=$(stat -c %Y /work/repo/rust/Cargo.toml 2>/dev/null || echo 0); echo "times… succeeded in 0ms: timestamp check not critical, using elapsed time calculation tokens used 59,060
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 2 minutes.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 4 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 2 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.03 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.65 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claw-code)Questions
- Does claw-code run?
- Yes. claw-code runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test claw-code?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 08106b0c3771. 4 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test claw-code?
- 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 claw-code take to install?
- 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 claw-code need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claw-code?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for claw-code?
- All 4 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.