A candidate-scoring head returns distributions for gates, routes and scores without decoding prose or JSON answers. The README compares a benchmark-trained AgentJev specialist with Jev 1.13.0 evaluated zero-shot; these use different training conditions.
claude-jev: Claude Code plugin
buchmark/claude-jev
VerifiedResearchDocumented
claude-jev (buchmark): Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev. See Jev references and source code.
Repository description: Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.
What you can build with it
Get started
Clone the repository and follow its README for install and usage. JevHunt has not run this project.
git clone https://github.com/buchmark/claude-jev.gitProject facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- TypeScript
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-18
- Last code update
- 2026-09-21
- GitHub stars
- 7
- Evidence checked
- Sep 28, 2026
- Metadata checked
- Sep 28, 2026
- Check status
- Up to date
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
2 of 3 findings survive · jev-1.13.0 · 1 request · state ~1714 tok · 2616 input tok
Evidence commit: 06fe407f2894bc5c44f2dfc41e05d3592e5215a5
Discovered through: awesome-jev.
How we review →Suggest a correction · Claim this listing · Submit a project