Supercov
Coverage, security and quality CLI where Jev answers yes/no property questions per file so agents know what to fix first.
Overview
Supercov tells a coding agent what to fix and what to test. It scores code quality and flags security risks with Jev, runs the test command you already use, and turns uncovered paths into small, actionable targets, so the agent can write a focused test or refactor, prove what improved, and continue. Coverage needs no account or configuration and supports JavaScript, TypeScript, Rust, Python, Ruby, Go, Java and Kotlin. It also installs as a plugin in Claude Code, Codex and Gemini CLI.
For quality, it asks Jev a set of yes/no questions about each file (list summaries say twelve quality and twelve security properties, such as long methods, deep nesting and complex conditionals) and does the arithmetic itself, so every part of a score can be checked against the file. Output ranks the weakest files with the properties that fired, and commands narrow to gaps, a single file or an uncommitted patch with GitHub annotations. Jev charges for input only, so the README estimates a little over a cent per megabyte of source, and answers are cached by content so reruns pay only for changes. It is local, open source and MIT licensed.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this file contain an overly long method? | — |
| Yes / no | Does this file have deep nesting or complex conditionals? | — |
| Yes / no | Does this file expose a security risk (e.g. a dangerous sink)?(inferred) | — |
How it works
- Find source files and run the existing tests for coverage
- Ask Jev quality and security yes/no questions per file
- Compute scores in code and rank weakest files
- Agent picks a target, writes a focused test or refactor, and re-measures
Strengths
- About a cent per megabyte of source per the README
- Content-hash caching for cheap reruns
- Every score traceable to specific properties
Caveats
- Scoring sends source to TypeSafe
- Requires a TypeSafe key for quality and security
Getting started
export TYPESAFE_API_KEY=..., then npx supercov quality (or paste 'Measure code quality with npx supercov.' to your agent).At a glance
- Type
- CLI
- Status
- production
- Language
- Rust
- Runtime
- CLI (npm, pip, gem, cargo) + agent plugins
- Has code
- yes
- Has tests
- yes
- License
- MIT
- Stars
- 154
Use cases and integrations
How curated lists describe it
Code quality for coding agents: Jev answers twelve `Noul` properties per source file so the agent knows what to fix first.
yibie/awesome-jevCode quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first
AnotiaWang/awesome-decision-modelsA quality and coverage CLI for coding agents: Jev assesses source properties while local coverage highlights testing targets.
logicrw/awesome-jev-projectsCoverage, security and code quality for coding agents
wh000wh000/awesome-jev-liveScores source files so coding agents can prioritize code-quality work.
cobanov/awesome-jevCode quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.
hellogumbo/awesome-jevCoverage, security and code quality for coding agents. Jev answers twelve quality and twelve security questions about each source file, and the CLI ranks the files so the agent knows what to fix first.
MrJev/awesome-jev
Frequently asked questions
What does Jev decide?
Yes/no quality and security properties for each source file, which code turns into scores.
What does it cost?
A little over a cent per megabyte of source, with caching for unchanged files.
Does coverage need an account?
No; coverage is local and free.
Related projects
CLI that scores every test against a git diff with Jev and emits filter arguments for vitest, jest, node, Playwright, cargo, go and rspec.
ProjectbetaTypeScriptSemantic grep for code, diffs and CSV rows that packs 16 chunks per Jev request and prints file:line hits with CI-friendly exit codes.
Agent skillbetaTypeScriptRust code-review gate asking Jev small typed questions about functions and tests, failing CI only on rules measured 80% right.
CLIproductionRustCoding-agent hook that asks Jev one yes/no per project rule on every edit or turn and makes the agent fix any violation.
HookbetaTypeScriptPR reviewer where Jev answers a Clean Code question set for every changed file and a writing model turns the verdicts into review prose.
ServicebetaTypeScriptAdvisor for coding agents: git and Stop hooks flag test tampering, secrets and skipped hooks, with optional Jev review findings.
Hookbeta