Six agents were running and I could not tell you what any of them did
Six coding agents were running. I could not tell you what any of them had done. Not roughly. Not approximately. The output was there, the files had changed, and the honest answer to "which one did that" was a shrug. Three questions in particular had no answer: which run burned the tokens, whether they genuinely ran at the same time or merely started together, and whether two of them had quietly…
Six coding agents ran simultaneously, but the reporter could not determine which one caused specific changes in the files. The output, file modifications, and whether the runs overlapped were all questions without clear answers. However, the console tool "runlanes" was able to provide a record of what happened by reading transcripts from each agent automatically.
The tool revealed that four agents were actively running, with 91% of the elapsed time spent on parallel tasks. The console also displayed the usage, cost, and token counts for each run, excluding cache reads to avoid inflating the numbers. The package was published through GitHub Actions, with verified attestation and a Sigstore signature, ensuring the integrity of the tool.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
