My agents wrote over 200 bad 'watch pr' scripts over the last few months. If you have a 'babysit' skill for watching PRs, send the following prompt to your agent: I want you to audit my history with
Why CEREBRO kept it
Agent prompt engineering and script quality audit lessons
The text below is an automated extraction of the article at https://x.com/theo/status/2107765823637168287, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
If you have a "babysit" skill for watching PRs, send the following prompt to your agent:
I want you to audit my history with
> Agent prompt engineering and script quality audit lessons
My agents wrote over 200 bad "watch pr" scripts over the last few months.
If you have a "babysit" skill for watching PRs, send the following prompt to your agent:
I want you to audit my history with Claude Code, Codex and other agents on this machine. Look for every time I asked for a PR to be watched or babysat.
1. How many times was the "babysitting" logic re-invented? 2. How many of these implementations had flaws you can see? 3. Roughly how many tokens (and how much $ at API prices) was wasted on these implementations? Both building them and dealing with their shortcomings.
Backlinks
Appeared in 1 briefing