All ideasMore in Work

An agent’s hourly self-wake-up loop ran 89 times over 9.5 days on an idle draft pull request and burned $285

After a short session troubleshooting an iOS widget, about $1.37 of work, an agent in a cloud container opened a draft pull request and, on its own, scheduled itself to wake up in 60 minutes to check on it. Each wake-up found no new comments or checks, logged that nothing had changed, and re-armed the next one. It repeated 89 times across 9.5 days with nobody present. Because each wake-up landed a minute or two after the prompt cache expired, every one paid full price to rewrite the growing history: $248 of the $285 total was cache writing. His entire $250 credit balance drained to zero.

$285.12at stake
This one went wrong. Read what happened so you don’t hit the same problem.

How it works

  1. Short session ends with a draft PR opened
  2. Agent schedules its own wake-up in 60 minutes
  3. Each wake finds nothing changed and re-arms
  4. 89 wake-ups across 9.5 days with no user present
  5. Each lands just after the cache expiry and pays full history rewrites
  6. $285.12 total, $248 of it cache writing
  7. His $250 credit balance drains to zero

Why it’s worth knowing

The timing was the trap: wake-ups at 61 to 62 minutes against a 60-minute cache meant every single check paid the maximum price.

Where it’s from

Summarized from a public post on github.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.