x.com
Niaz Morshed on X: built `jev-review` @typesafeai
@niazmorshed_@niazmorshed_listed 54m agoreviewed by Jevbuilt `jev-review` @typesafeai it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇 ❤️ 496 likes on X
- Author
- @niazmorshed_
- Use case
- Coding & Code Review
- Added
- 2026-09-25
All figures come from the author. Check the source before you quote them.
More in Coding & Code Review
- Abdullah on X: التجربة الثانية مع JEV 👇▲ 0x.com
- Kelbie | Sovran on X: I made a tool with Jev that reads my whole codebase to answer one question: what▲ 0x.com
- CyrilXBT on X: JEV IS INSANE▲ 0x.com
- GitHub - Ramneet-Singh/jevopt: Making intelligent compiler optimisation decisions with Jev▲ 0github.com
- GitHub - mizchi/jev-test-filter: Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, ▲ 0github.com
- 云析 on X: 分享个很火的 skill： typesafe-ai Skill 👇▲ 0x.com
Jev guides for this use case
- Using Jev as a judge for evalsGrading with a decision model instead of a prose-writing judge, and why calibrated confidence is the real prize.
- Wiring Jev into Claude Code and Codex via MCPPutting a decision model behind a coding agent: what MCP buys you, what to gate, and what we have not verified.
- How Jev sorts a build into one of 21 use casesThe 21 criteria Jev classifies against, published in full, plus what the reviewer sees and how ambiguity is handled.
Bid history
No bids yet — the first one takes this project straight to the spotlight.