no-mistakes
git push no-mistakes
Runssource: GitHubhomepageGoMITcommit ac8e342c54b9
Go, MIT licensed.
no-mistakes runs. An Argusic agent installed it in 37 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The repository builds into a 30MB Go binary that prints its version and help, and all 45+ Go packages pass their race-detector tests including the previously-failing eval replay tests. Go was installed on-the-fly; the one code fix was a guard to skip upstream git fetch during eval replay isolation.
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.
- 9 tests in `internal/eval` failed: `resolveBranchBaseSHA` tried to `git fetch --no-tags +refs/heads/main:refs/remotes/origin/main` with an empty remote URL, because the eval replay sandbox is an isolated local bare repo with no upstream remote configured.5 minutes
- Go 1.27.1 was not present in the container environment (no go binary anywhere).2 minutes
- `make build` failed: `neither GOMODCACHE nor GOPATH is set` because no GOPATH was configured after installing Go.
- Install time
- 37 minutes
- Cold machine to finish
- 41 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- `./bin/no-mistakes --version` returned 'no-mistakes version ac8e342 (ac8e342) 2026-09-28T10:17:49Z'; `go test -race ./...` exited 0 with all ~45 packages passing; `make lint` passed; `go build -o /dev/null ./cmd/no-mistakes` passed
- Model tokens used
- 275,197
- Exact commit tested
- ac8e342c54b9
- 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.
/bin/sh -lc 'echo "Start: 1790590588 (approx 10:16:28 UTC)"; echo "Now: 1790592833"; echo "Elapsed … succeeded in 0ms: Start: 1790590588 (approx 10:16:28 UTC) Now: 1790592833 Elapsed minutes (approx): 37 ERROR: Reconnecting... 1/5 All results are in. Here's the complete report: 2026-09-28T10:57:10.639066Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… 2026-09-28T10:57:10.639103Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 275,197 All results are in. Here's the complete report:
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 37 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.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/no-mistakes)Questions
- Does no-mistakes run?
- Yes. no-mistakes runs. Argusic installed and launched it on a clean machine in 37 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test no-mistakes?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ac8e342c54b9. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test no-mistakes?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does no-mistakes take to install?
- 37 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 no-mistakes need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing no-mistakes?
- 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 no-mistakes?
- 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.