DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to refactor in scored steps until deltas plateau with Jev Review

Use previousEvaluation so the agent sees which dimensions improved or regressed.

Credentials. Every rescoring call sends the submitted context to the Jev API, so repeated loops repeat that disclosure and use the same API key.

Who it is forA developer or agent refactoring a module who needs evidence that each change helps.

The problemRefactors often trade one quality dimension for another, and a single snapshot does not show it.

The outcomeThe agent gets a baseline, makes small edits, rescores, and stops when changes no longer produce real gains.

What you need first

  • Node.js 20 or newer
  • A Jev API key from the TypeSafe console (https://console.typesafe.ai/)
  • Claude Code, Codex, Cursor, or OpenCode installed
  • Set JEV_API_KEY with export JEV_API_KEY="your-key" before starting the coding agent

Steps

  1. Run npx plugins add NiazMorshed2007/jev-review --target cursor or the matching command for your client, then restart it.
  2. Call jev_review with the task and focused diff to establish a baseline.
  3. Make the smallest justified change, run your own tests, and call jev_review again with previousEvaluation set to the baseline.
  4. Read the per-metric deltas, improvements, regressions, and unresolved weaknesses, then repeat or stop.

Prompt for your agent

Refactor <module path> with the jev_review tool from NiazMorshed2007/jev-review. Call it for a baseline, then after each change call it again with previousEvaluation set to the prior result. Report the per-dimension deltas and any regressions, and confirm that the project's existing tests still pass after each step.

Caveat. The README says the Jev API enforces its own token ceiling, so large refactors may need to be split into slices before scoring.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page