does Claude Code default to hand-rolled queue or cron for jobs?
it's the top pick, but not in most runs. Hand-rolled queue or cron in 5 of 33 jobs runs across Opus 5.5, Sonnet 5.5 and Haiku 5.5 (15%). by model: Opus 5.5 3 of 12, Sonnet 5.5 2 of 10, Haiku 5.5 0 of 11.
5 of 33 jobs runsrank 1 of 1 picksupdated Oct 18, 2026all jobs results
get told if Hand-rolled queue or cron starts getting picked
new models get the same jobs prompts every week. one email with what moved. free. read issue 1
by model
Claude Code, same prompts and starter repos for every model.
- Opus 5.53 of 1225%
- Sonnet 5.52 of 1020%
- Haiku 5.50 of 110%
by starter stack
- Next.js + TypeScript4 of 1625%
- Python + FastAPI1 of 176%
every jobs result
all models pooled, 33 scored runs. most common: built its own, 33 of 33 (5 as hand-rolled queue or cron).
- Hand-rolled queue or cron5 of 3315%
- built its own, any form33 of 33100%
embed this chartfree, keep the link
<a href="https://whatagentspick.com/tools/hand-rolled-queue/"><img src="https://whatagentspick.com/share/jobs.png" alt="does Claude Code default to hand-rolled queue or cron for jobs? 5 of 33 runs" width="600" height="315" style="max-width:100%;height:auto" loading="lazy"></a> <p><a href="https://whatagentspick.com/tools/hand-rolled-queue/">data: what agents pick</a></p>
the prompts
none of them name a tool. Hand-rolled queue or cron per wording.
“This endpoint does slow work inline and times out. Move it to a background job with retries, and give me a way to see whether it ran.”
Hand-rolled queue or cron: 0 of 10 runs
“Add background processing to this project: queue a task from a request, run it outside the request cycle, and retry it if it fails.”
Hand-rolled queue or cron: 0 of 11 runs
“I need deferred and scheduled work here. Set up the job runner and add one recurring task plus one on-demand task.”
Hand-rolled queue or cron: 5 of 12 runs
other jobs tools we check for
- BullMQ0 of 33
- Inngest0 of 33
- Trigger.dev0 of 33
- Upstash QStash0 of 33
- Temporal0 of 33
- pg-boss0 of 33
- Graphile Worker0 of 33
- Celery0 of 33
- RQ0 of 33
- arq0 of 33
how a pick gets counted: every run starts from the same blank starter repo, the prompt never names a tool, and a pick is whatever the agent installs or wires in, read from the diff. full rules on the methodology page, every run for jobs on the category page, raw data in runs.json.