Hello PH!

Code just became cheaper with AI but review and verification is as hard as it was. Tests are great, but current AI slop needs much more exhaustive testing.

I built a test coverage tool for coding agents so they could work in a loop and keep writing tests where it makes sense.

Here’s Supercov:
- Wraps any JavaScript/TypeScript/Python/Rust test suite
- Provides MC/DC code coverage (NASA uses this)
- Free and open source

Easiest way is just to give your agent a prompt: Measure coverage with npx supercov and write one test.

Goal is building the deepest code coverage suite for coding agents thats works automagically in any language and any test suite. I feel code verification is the missing piece for software factories to actually work.

I’d particularly be interested in feedback on compatibility and if your agent ran into any problems.

Contributions and bug reports are very welcome: https://github.com/supercorp-ai/...

Supercov

Coverage so coding agents can work overnight

Coverage so coding agents can work overnight