{"slug": "jevgrep-find-code-by-asking-what-it-does", "title": "jevgrep: Find Code by Asking What It Does", "summary": "Jevgrep, an MIT-licensed command-line tool from developer dzhng that has 2.3k GitHub stars, lets coding agents find source files by semantic intent rather than literal string matching, returning files that match what code does instead of a pattern it contains. Installing the CLI via npm is not sufficient on its own: the separate `jg skill` command detects coding agents such as Claude Code, Codex and OpenCode and installs a skill explaining how to invoke jg and interpret its returned context, a pattern also used by huashu-art-motion through `npx skills add`. Semantic search requires a provider key for embeddings or inference that the skill installer does not configure, and provider selection needs version 0.3.0 or newer.", "body_md": "# jevgrep: Find Code by Asking What It Does\n\ngrep has one assumption baked in: you already know a string the code contains. Most of the time, on an unfamiliar codebase, you don’t. You know what the code *does* — “where do we validate the webhook signature?” — but not what it’s called. [jevgrep](https://github.com/dzhng/jevgrep) (2.3k stars, MIT) is built for exactly that gap.\n\n## What it does\n\njevgrep — `jg` on the command line — is a CLI for coding agents that **discovers relevant files and source context by semantic intent**. You ask what the code does; it returns the files and context that match the meaning, not a literal pattern. For an agent working through an unfamiliar repo, that is often the difference between finding the right file on the first try and grepping blindly through twenty candidates.\n\nIt is not a grep replacement. ripgrep is still faster and exact when you know the token. jevgrep is the tool for the *other* half of code search — the exploratory half, where you’re reasoning about behavior instead of strings.\n\n## The interesting part: it ships a skill, not just a binary\n\nHere’s the pattern worth highlighting. Installing the CLI alone does **not** teach your agent to use it:\n\n```\nnpm install --global @dzhng/jevgrep@latest   # the CLI\njg skill                                       # the agent skill — required\n```\n\nThat second command is the point. `jg skill` detects your coding agents (Claude Code, Codex, OpenCode, and others) and installs a skill that explains *how to invoke jg and what the returned context means* — then gets out of the way, leaving research and implementation decisions to the calling agent. You can also pull it through the skills registry:\n\n```\nnpx skills add dzhng/jevgrep --skill jevgrep\n```\n\n## Why this matters beyond one tool\n\nWe’re watching a convention form in real time: **ship the CLI and the skill that teaches the agent to use it, in the same package.** jevgrep does it with `jg skill`. huashu-art-motion does it with `npx skills add`. It’s the same instinct behind packaging our own tools as Claude Code plugins — a tool an agent can’t figure out how to call is a tool that doesn’t get used.\n\nSemantic code search is a natural agent primitive, and it rhymes with work we do constantly: RAG over codebases, where the retrieval quality determines whether the model grounds on the right file or hallucinates one. jevgrep pushes that capability down to the command line, where any agent can reach it.\n\n## The caveat\n\nSemantic search needs a provider key (embeddings/inference) — the skill installer does **not** configure credentials, so budget for that setup step. Provider selection needs version 0.3.0 or newer. And as with any embedding-based retrieval, results are only as good as the index and the model behind it; treat it as a strong first-pass locator, then confirm with exact tools.\n\n**Repo:** [github.com/dzhng/jevgrep](https://github.com/dzhng/jevgrep)", "url": "https://wpnews.pro/news/jevgrep-find-code-by-asking-what-it-does", "canonical_source": "https://themenonlab.blog/blog/jevgrep-semantic-code-search-agents/", "published_at": "2026-10-08 00:00:00+00:00", "updated_at": "2026-10-26 02:12:02.683407+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-search"], "entities": ["jevgrep", "dzhng", "Claude Code", "Codex", "OpenCode", "huashu-art-motion", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/jevgrep-find-code-by-asking-what-it-does", "markdown": "https://wpnews.pro/news/jevgrep-find-code-by-asking-what-it-does.md", "text": "https://wpnews.pro/news/jevgrep-find-code-by-asking-what-it-does.txt", "jsonld": "https://wpnews.pro/news/jevgrep-find-code-by-asking-what-it-does.jsonld"}}