Claude Code Plugin zwingt KI-Coding-Agenten, Tests vor dem 'Fertig' zu bestehen
Coding-Agenten wie Claude Code oder Cursor melden oft Aufgaben als erledigt, ohne Tests ausgeführt zu haben. Das kostenlose Plugin proof-of-done blockiert den Abschluss, bis Tests und Builds erfolgreich durchlaufen sind.
You ask Claude Code, Codex, Cursor, etc. for a quick fix. It changes the code and says "Fixed ✅". Later you find out it never ran a single test, or ran them through | tail and missed 58 failures.
So I built proof-of-done, a free Claude Code plugin: Claude simply can't finish until the tests, build or lint have passed after its last edit.
Try it inside Claude Code (free, source on GitHub ):
/plugin marketplace add WST2002/claude-code-skills /plugin install proof-of-done@claude-code-skills Enter fullscreen mode Exit fullscreen mode
A real Claude Code session, shortened: Claude said "fixed" without testing, the plugin made it run the tests, and they found a second bug.
1. It watches every edit and every check
2. When Claude tries to stop, it asks: is there proof?
5. New code with no test? It asks you once
Has your AI ever told you "done" when it wasn't? What did it skip?