⌁ CLI & Pipelines MIT
A prose linter that catches AI writing tells. Regex settles the 18 a pattern can settle. Jev takes the 15 that need reading, as 15 Nouls in one call, 604 ms median. It ships as a Claude Code `Stop` hook that scores Claude's own output after every turn and warns rather than blocks.
ϟ JEV · Decision point **Deleting a feature made it more accurate.** The first build made a second Jev call to pin each tell to a sentence. Removing it took precision from 0.80 to 0.95 and latency from 1,365 ms to 575 ms. Jev returns typed answers rather than text, so a quote has to come from a second round of typed questions about lines, and that round was where every defect lived. The README documents the two intermediate designs that were worse.
→Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
cli-git-gatestyped-decisions
A prose linter that catches AI writing tells. Regex settles the 18 a pattern can settle. Jev takes the 15 that need reading, as 15 Nouls in one call, 604 ms median. It ships as a Claude Code `Stop` hook that scores Claude's own output after every turn and warns rather than blocks.
ϟ JEV · Decision point**Deleting a feature made it more accurate.** The first build made a second Jev call to pin each tell to a sentence. Removing it took precision from 0.80 to 0.95 and latency from 1,365 ms to 575 ms. Jev returns typed answers rather than text, so a quote has to come from a second round of typed questions about lines, and that round was where every defect lived. The README documents the two intermediate designs that were worse.
→Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Stars / Forks
- 0 / 0
- Issues
- 0
- License
- MIT
- Last commit
- 2026-09-19
Source note Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.