Cron'd Claude Agents: A Maintenance Log
Running a fleet of twenty Claude agents on a launchd schedule teaches you fast that scheduler guarantees are weaker than you expect. Each agent wakes, processes a slice of work, writes its results, and goes back to sleep until the next tick. The pattern is simple; the failure modes are not. Three months of nightly runs have turned up launchd timing quirks, session-end failures, and the quiet…
The article provides a candid maintenance log of running twenty Claude agents on a launchd schedule. It highlights several issues encountered, including launchd's weaker guarantees than expected, timing quirks leading to overlapping executions, and handling of environment variables. The author discovered that assigning distinct, fixed start times to each agent eliminated write-lock cascades and ensured independent job execution.
Additionally, the article emphasizes the importance of instrumenting instrumentation before enforcing limits on Claude agent turn counts, as setting ceilings without proper data calibration can cut legitimate work short. The maintenance log also covers session-end handling and data ownership, with agents saving session summaries at the end of each run.
Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
