Repo · Coding & code review

wellposed

Zero-dependency linter for TypeSafe Jev requests: catches broken state paths, missing Choice escape hatches, bundled judgments, and other structural…

Open github.com ↗

From the repository

Lints Jev requests before they are sent: offline checks for missing none-of-the-above options and broken state paths, then Jev itself for what structure cannot decide.

agent-skillsai-toolingclaude-codecodexjevlinterllmsystem-onetypesafe

How builders describe it

Lints Jev requests before they are sent: offline checks for missing none-of-the-above options and broken state paths, then Jev itself for what structure cannot decide.

Zero-dependency linter for TypeSafe Jev requests: catches broken state paths, missing Choice escape hatches, bundled judgments, and other structural smells before you call the API.

Offline linter and agent skill that checks Jev requests for 45 structural problems before you send them, so a badly designed Choice question fails locally instead of coming back as a confident wrong label.

Failure mode report: a Choice with no escape hatch answers at confidence 1.00 The jaggedness page asks for failure modes, so here's one — though it's a request-design failure rather than a model one, and I think that's what makes it worth flagging. A Choice whose options don't cover the input still…

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects