Who it is forA developer or CI-minded engineer who wants a script or pipeline to run a behavior search over selected directories and act on the result.
The problemPipelines need machine-readable output and a reliable way to tell a complete result from a partial one.
The outcomeA validated JSON response limited to the chosen directories, with coverage information and an exit code that shows whether the result is complete.
What you need first
- Node.js 24
- npm
- An API key for TypeSafe AI, Vercel AI Gateway or OpenRouter
- Permission to send eligible source excerpts from the target repository to the chosen provider
Steps
- Run
npm install -g @nassim-arifette/jevgrepand completejevgrep init --globalandjevgrep initfor the repository - Run
jevgrep inspectto confirm the eligible scope - Run
jevgrep search --query "How are permissions checked?" --scope src --scope tests --json(inferred, check the README) - Read the exit code:
0means complete,3means partial, and2or4mean a problem to handle - Only add
--allow-partialif a partial deterministic scan is acceptable for your workflow
Prompt for your agent
Run `jevgrep search --query "<behavior question>" --scope <folder> --json` in the repository at <repo path> and parse the JSON output. Verify that you check the exit code and report whether the result is complete or partial before drawing any conclusion.
Caveat. Results are scored by a remote provider, so a complete JSON result still depends on that provider's scoring and an empty result is not proof that code does not exist.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for nassim-arifette/jevgrep and "Run scoped searches that return JSON for scripts"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer