X · by moub.dev
jev-check
The database, not the agent, decides whether the work is done.
moub.dev
@emoubarak_
Agent: "done" ✅ UI: looks fine ✅ Database: the free plan just published a 2nd project and took the 1st one offline ❌ I stopped trusting my AI agent's "done". Now the database is the judge. jev-check, an open-source skill for Claude Code and Codex 👇
Oct 4, 2026 · 1 likesOpen on X
moub.dev stopped trusting the agent's "done". In the example, the agent reported done and the UI looked fine, but the database showed that the free plan had published a second project and taken the first one offline. jev-check is an open-source skill for Claude Code and Codex that makes the database the judge.
Open the source
