skills.rest
tmcfarlane
tmcfarlaneCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

mgrep-code-search

Indexes large repositories and performs semantic searches across codebases using natural language queries.

105|12|Updated Feb 7, 2026
Search Tags:#indexing#nlp#semantic-search#code-search#mgrep#large-codebases
One-click install
npx skills add https://github.com/tmcfarlane/oh-my-cursor --skill mgrep-code-search-tmcfarlane
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mgrep-code-search
Source: https://github.com/tmcfarlane/oh-my-cursor/tree/main/skills/mgrep-code-search
Command: npx skills add https://github.com/tmcfarlane/oh-my-cursor --skill mgrep-code-search-tmcfarlane

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Semantic code search helps developers quickly locate where and how features are implemented across large codebases, reducing time spent on manual file inspection.

Core Features & Use Cases

  • Semantic search across code, text, PDFs, and images to find intent and context beyond exact strings.
  • Indexing large repositories with a watcher to keep search results up-to-date.
  • Use Case: Quickly locate where a function is defined, used, or related to a behavior across nested directories.

Quick Start

Install and run the watcher to index your repository, then perform a semantic search with natural language queries.

Frequently Asked Questions about mgrep-code-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find where a feature is implemented across a large codebase?▼

Semantic search helps you locate where and how features are implemented across large codebases using natural language queries, moving beyond exact string matches to find intent and context.

What is the best way to search for code concepts beyond exact string matches?▼

Semantic code search enables you to find concepts and features beyond exact strings by indexing large repositories and running natural language queries to discover implementation context.

How do I index a repository for semantic code search?▼

You index repositories for semantic search by running the mgrep watcher, which keeps search results up-to-date across nested directories and large file structures.

Does semantic code search work with PDFs and images?▼

Semantic search supports indexing and searching across code, text, PDFs, and images to find intent and context beyond exact strings within large repositories.

Can I use semantic code search for small repositories?▼

Semantic code search is designed for codebases with 30 or more non-gitignored files and nested directories, ensuring there is enough structure to justify indexing and discovery.

How do I run a semantic search query after indexing my codebase?▼

You run semantic search queries using the bunx @mixedbread/mgrep search command with optional flags to control results and synchronization after the watcher indexes your repository.

Related Skills

Explore More Software Engineering Skills→
juanjaragavijuanjaragavi

mgrep-code-search

Perform semantic search across large codebases using natural language queries.

Community
Advanced
mixedbread-aimixedbread-ai
4.3k

mgrep

Enforce mgrep for local and web searches with mgrep --web.

Official
Intermediate
hellitonsmhellitonsm

pdf

Consolidate PDF processing tasks into a unified automation workflow.

Community
Advanced
scooter-lacroixscooter-lacroix
8

search-router

Route search queries to TLDR Search, AST-grep, or Grep based on query type.

Community
Intermediate