jev-where
Claude Code plugin that finds fuzzy decision points in an app and ranks where a Jev question could replace them, with precedents.
Overview
JEV WHERE? is a Claude Code plugin that seeks out fuzzy decisions buried in an application, such as a regex that routes tickets, a keyword list that sets priority, an LLM call that only ever answers yes or no, or a filter that holds messages for review. For each decision point it reports where it is (file, line and function), what the code does today and where it breaks, the exact typed Jev question with its options or levels, starting confidence cutoffs with a safe fallback, what kind of data would be sent to Jev and how to send less, git-history footprints such as a rule edited many times, and an honest case for and against.
Each idea cites one or two real projects that already do something similar, linked to the exact lines where they call Jev, drawn from the project's own verified sightings list and rechecked live, with newer projects pulled from the awesome-jev list. Reports also flag hardcoded secrets and unguarded API calls. It only analyses and suggests and never edits code. A plain-Python radar script can also be run directly, and re-running shows what changed since the last map.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Where in this codebase could a fuzzy rule become a Jev Choice, Score or Noul question? | — |
How it works
- Scan the app's code and git history
- Identify fuzzy decision points
- Propose typed questions, cutoffs and fallbacks with data-sensitivity notes
- Rank ideas and cite verified precedents
Strengths
- Never edits code
- Links to real precedent code
- Flags secrets and data exposure along the way
Caveats
- Suggestions still need human evaluation
- Depends on external lists for precedents
Getting started
claude plugin marketplace add cesarroger/jev-where && claude plugin install jev-where@jev-where, then run /jev-where.At a glance
- Type
- Project
- Status
- beta
- Language
- Python
- Runtime
- Claude Code plugin
- Has code
- yes
Use cases and integrations
How curated lists describe it
JEV WHERE? A seek-and-find for the decisions hiding in your code.
wh000wh000/awesome-jev-live
Frequently asked questions
Does it change my code?
No, it only analyses and suggests.
How does it justify suggestions?
Each idea cites real projects linked to the exact lines where they call Jev.
Does it check for security issues?
It flags hardcoded secrets and unguarded API calls it finds along the way.
Related projects
- Building with Jev★ 155
Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.
Agent skillproduction Portable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.
MCP serverbetaTypeScriptIndependent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.
Agent skillbetaAgent skill that guides you in finding, designing and testing Jev decision loops, including when to keep logic in code.
Agent skillbetaClaude Code and Codex skills plus a study course for building with Jev, including Jevaluate, which rates how well projects use Jev.
ProjectbetaCommunity Jev skill for Claude Code and Codex: a guide, a dependency-free Python CLI and 5 measured question sets.
Agent skillbetaPython