User repository on GitHub
Put your code comments on trial. Powered by Jev.
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
Commentcop
A CLI that reads the comments in your JS/TS files with the code around them and scores each one for accuracy and usefulness out of 100, weakest first, using Jev.
- Stars
- 1
- Language
- TypeScript
- License
- MIT
- Published by
- Community
- Author
- ntedvs
- Last verified
- Oct 2026
About this project
A little CLI that judges your code comments with Jev. Is the comment accurate? Does it explain something useful? Or is it just "multiply by two" above value 2? Commentcop reads your JS/TS comments with the code around them and scores accuracy and usefulness out of 100. The weakest comments show up first. It respects .gitignore and skips generated code and dependencies. Grab an API key from TypeSafe, then:
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- TypeScript
Highlights
- Scores accuracy and usefulness out of 100 and sorts the weakest comments first, so cleanup starts where it hurts most.
- Reads comments together with the surrounding code and skips generated files, dependencies and anything matched by .gitignore.
- A dry-run flag previews what it would rate without calling Jev, and an ignore flag or a .commentcopignore file narrows the scan.
- The README's own check rated 159 comments for about $0.008, and the CLI prints an estimated cost once it finishes.
Watch out
A score of 100 on accuracy does not mean the comment is complete, only that Jev read it as consistent with the nearby code, and the README is explicit that some comments need context beyond that. Read the confidence alongside the score rather than acting on the number alone, and treat the ratings as a starting point for review. Every comment and the code around it is sent to TypeSafe, so anything private left in a comment leaves your machine. The key is stored in plain config at ~/.config/commentcop/config.json unless you set XDG_CONFIG_HOME, and a setup step or the TYPESAFE_API_KEY environment variable will store it for you. Runtime needs are Bun, Node 22.18+ on the 22.x line, or Node 24.11+. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
That is the limitation the README names, and it points at the mitigation: every rating carries a confidence value, and a low one is the signal that the nearby code was not enough context. Nothing in the tool goes and fetches callers, types or history to close the gap, so for a comment encoding an invariant defined elsewhere expect a low-confidence rating rather than a confidently wrong one. The intended workflow is triage, weakest first, then read and fix by hand.
The README reports checking 159 comments for about $0.008, and the CLI shows progress as ratings arrive plus an estimated cost at the end. That figure is the author's own run rather than a measured average, so read it as an order of magnitude for JS and TS files with similar comment density. Cost scales with the number of comments rather than repository size, since generated code and dependencies are skipped.
It respects .gitignore and the README states it skips generated code and dependencies; anything beyond that goes through the ignore flag or a .commentcopignore file. The scope is comments in JS and TS files, and for each one it sends the comment plus the surrounding code to TypeSafe for rating. A secret pasted into a comment in a tracked file is still transmitted.
Either. The stated requirements are Bun, Node 22.18+ on the 22.x line, or Node 24.11+, and the README says npx works for everything the bun x examples do. The setup subcommand stores your TypeSafe key so you only do it once, and TYPESAFE_API_KEY works instead if you would rather keep it in the environment. You can pass another repository path as an argument and ask for every rating rather than only the weakest.
Grab a TypeSafe API key, then run bun x commentcop setup to save it once, or set TYPESAFE_API_KEY, and run bun x commentcop. Point it at another repo with bun x commentcop ~/code/your-project, or see every rating with --all.
Each comment and the code around it is sent to TypeSafe for rating. The setup key is stored at ~/.config/commentcop/config.json unless you have set XDG_CONFIG_HOME.
Yes. --dry-run previews what it would rate without calling Jev, and you can add exclusions with --ignore or a .commentcopignore file. It already respects .gitignore and skips generated code and dependencies.
More Jev resources like this
38GitHub stars
Python memory filter that judges every stored memory against the current request with one calibrated yes/no per memory in a single Jev request, keeping everything above a threshold.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
samdotmak/jev-recallTypeScript
samdotmak/jev-recallTypeScript36GitHub stars
Stock decision terminal that gathers Valyu market evidence across five categories and uses Jev for a typed 30-day outlook with probability, signals, and timing.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
unicodeveloper/jevocksTypeScript
unicodeveloper/jevocksTypeScript4GitHub stars
Playful chat demo that makes Jev hold a conversation one word at a time by picking from a compact 979-word vocabulary through repeated Choice calls.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
mkotlikov/jev-grugTypeScript
mkotlikov/jev-grugTypeScript4GitHub stars
Shell CLI that sends state plus noul, choice, and score questions to Jev in one request and prints probabilities, choices, and rubric positions for pipes and scripts.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
y0usaf/typesafe-cliTypeScript
y0usaf/typesafe-cliTypeScript5GitHub stars
Local-first app that extracts document text on the machine and files it into configured category folders using typed Jev decisions for category, confidentiality, prompt-injection risk and subject, with a per-run audit that previews and undoes every move.
Jev Tools & CLIs#community#jevbest#catalog-import
7GitHub stars
PDF search that asks Jev one noul per line, does this line answer the query, and ranks the lines by the returned probability, so matches highlight without embeddings, a vector index or a chunking strategy. Text is extracted locally with pdf.js and the key stays on the server.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
kylemclaren/jevpdfTypeScript
kylemclaren/jevpdfTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.