firstmate
Talk to one agent. Ship with a crew.
Runssource: GitHubShellMITcommit 3c2a91d70e07
Shell, MIT licensed.
firstmate runs. An Argusic agent installed it in 0 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Firstmate repo checked out at 3c2a91d, session-start script completes lock-bootstrap-wake-fleet cycle, 23 unit tests pass with zero failures across pure-contract-unit, standalone, backend-dispatch, and watcher-wake-lock families.
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
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.
- No .ts file extension handler found in node v18 for Calm Pi/Claude extension tests (fm-calm-claude-mod.test.sh, fm-calm-pi-extension.test.sh)
- ci-workflow test requires ruby to parse .github/workflows/ci.yml YAML
- tmux not available (hampered session-bootstrap and backend tests)
- Install time
- under a minute
- Cold machine to finish
- 40 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- bin/fm-session-start.sh completed all stages (LOCK/BOOTSTRAP/WAKE QUEUE/FLEET STATE); bin/fm-test-run.sh batch of 23 tests returned FM_TEST_SUMMARY total=23 failed=0
- Model tokens used
- 149,446
- Exact commit tested
- 3c2a91d70e07
- 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 2, run , the attempt that decided the verdict above. 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.
Test runner: 43 tests available Script syntax: all parse Git state: 3c2a91d Now I have a complete picture. Let me compile the final result. `fm-session-start.sh` acquires the session lock and completes all four stages successfully — the re… tokens used 149,446 Now I have a complete picture. Let me compile the final result. `fm-session-start.sh` acquires the session lock and completes all four stages successfully — the re…
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 0 minutes.
- 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.
- 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 0 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/firstmate)Questions
- Does firstmate run?
- Yes. firstmate runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test firstmate?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3c2a91d70e07. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test firstmate?
- The run that produced this verdict cost $0.55: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does firstmate take to install?
- 0 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 firstmate need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing firstmate?
- 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.
- Where is the evidence for firstmate?
- 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.