commentcop
CLI that uses Jev to score JS/TS code comments for accuracy and usefulness and lists the weakest first.
Overview
commentcop is a small command-line tool that judges code comments. It reads comments in JavaScript and TypeScript files together with the surrounding code and asks Jev to rate each one for accuracy and usefulness out of 100, then prints the weakest comments first. It respects .gitignore and skips generated code and dependencies.
It is meant for developers cleaning up a codebase who want a quick list of misleading or redundant comments, such as "multiply by two" above `value * 2`. Jev is the scorer: each comment plus context is the state, and the rubric scores come back with a confidence. The README reports checking 159 comments for about $0.008 and recommends reading confidence alongside the score, since some comments need context beyond the nearby code.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | Is the comment accurate to the code around it?(inferred) | — |
| Score | Does the comment explain something useful?(inferred) | — |
How it works
- Scan JS/TS files, skipping ignored and generated code
- Send each comment with nearby code to Jev
- Receive accuracy and usefulness scores with confidence
- Sort and print the weakest comments, with an estimated cost
Strengths
- Very low cost per run (README reports about $0.008 for 159 comments)
- Dry-run mode previews without calling Jev
- Runs via bunx or npx with no project setup
Caveats
- Code and comments are sent to TypeSafe
- Only JS/TS supported
- Scores are a starting point; some comments need wider context
Getting started
bun x commentcop setup, then bun x commentcop (npx also works).At a glance
- Type
- Project
- Status
- beta
- Language
- TypeScript
- Runtime
- CLI (Bun or Node)
- Has code
- yes
Use cases and integrations
How curated lists describe it
Put your code comments on trial. Powered by Jev.
hellogumbo/awesome-jev
Frequently asked questions
What does commentcop decide?
It scores each code comment for accuracy and usefulness out of 100.
Does it need a TypeSafe key?
Yes; run setup to save it or set TYPESAFE_API_KEY.
Which languages does it check?
JavaScript and TypeScript comments.
Related projects
Rust 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.
HookbetaTypeScriptAdvisor for coding agents: git and Stop hooks flag test tampering, secrets and skipped hooks, with optional Jev review findings.
HookbetaRead-only Go CLI that checks files against your plain-language code rules with Jev, locally or in CI.
CLIbetaGoCLI and agent commands auditing a git diff against YAML standards packs, scoring each hunk with Jev so agents fix only flags.
Agent skillbetaTypeScriptClaude Code plugin that checks every reply and file edit against your CLAUDE.md rules with one Jev yes/no per rule.
PluginbetaTypeScript