The same work on a third of the tokens: tuning a fleet of coding agents
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Alexander Marquardt reports that over ten weeks of Claude Code transcripts, his fleet of parallel coding agents cut tokens per changed line 3.3x (about 2.5x when weighted by token price) and merged 4.4 times as many PRs a week on 19% fewer tokens. Most tokens were cache reads of re-sent context, so the gains came from one-task agents with a context ceiling and fewer cache expiries. It is one project run by one person with changes landing together, and rework per PR rose slightly.