My Claude Code workflows ran for days. Headless workers finished in minutes.
I run four projects with Claude Code. For a while, my long multi-agent jobs went through Claude Code's Workflow tool, and they kept running for days. Some never finished. Part of it was effort. Every agent in a workflow runs at the effort level of the session that started it, and a workflow script has no documented per-agent effort setting. So I kept switching model and effort by hand, trying to…
The author uses Claude Code workflows for multiple projects but found long-running multi-agent jobs to be problematic, often taking days or failing to finish. To address this issue, the author implemented a headless worker system that runs each task as an independent process with its own settings, model, effort level, and budget.
This new setup allowed all 7 research tasks to complete in about 7 minutes, compared to 73 minutes for the same tasks when run as a single workflow. The author also noted that the headless workers used less of their usage limits, likely because each role runs at the required effort rather than maximum. The author provides 10 observations about the challenges faced while setting up and running these headless workers, including issues with tool restrictions, sandbox configurations, environment inheritance, and usage limit handling.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
