jevbooks

← All projects

supercov

supercorp-ai/supercov · Homepage

Code quality and coverage for coding agents

Scoring & Ranking96%Runner-up: Evaluation & Benchmarking

What it is

Supercov scores code quality with Jev and measures test coverage, turning uncovered paths into actionable queries for coding agents to fix and test.

How it uses Jev

Jev answers twelve Noul properties per source file, such as long_method and deep_nesting, to score code quality. The agent uses these scores to decide what to fix first.

Primitives:noul

Technique worth stealing

Use Jev to answer yes/no questions about each file, then do the arithmetic yourself for checkable scores.

Try it

npx supercov quality

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.75
  • Shows a System One patternyes0.75
  • Handles uncertaintyno0.03
  • Measuredno0.19
  • Runnableyes0.96
  • Worth recommendingno0.30
  • Model replicano0.04
  • Problem scopescore on a 0–2 scale1.42
  • About Jevyes0.96

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.