mgrep

Search local files semantically with natural language queries and return file paths with line ranges.

1|1|Updated Dec 29, 2025
One-click install
npx skills add https://github.com/sreenivasanac/claude_code_setup --skill mgrep-sreenivasanac
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mgrep
Source: https://github.com/sreenivasanac/claude_code_setup/tree/main/skills/mgrep
Command: npx skills add https://github.com/sreenivasanac/claude_code_setup --skill mgrep-sreenivasanac

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Searching local files with traditional grep can be brittle, vague, and time consuming. mgrep provides semantic search that understands intent, delivering more relevant results fast.

Core Features & Use Cases

  • Semantic, intent-aware search over local files and codebases.
  • Natural-language queries to locate functions, definitions, or references.
  • Use Case: quickly locate where a function is used across a large repository or understand parameter usage in config files.

Quick Start

Use mgrep to search the current directory for a description or function signature. mgrep "parse_date" .

Frequently Asked Questions about mgrep

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

FAQPage Schema
How do I search local files semantically instead of using grep?

Semantic local file search replaces traditional grep by understanding natural-language intent, returning file paths with matching line ranges for codebases and documentation repositories.

What is semantic codebase search and when do I need it?

Semantic codebase search interprets natural-language queries to locate functions, definitions, or references by intent rather than exact string matching. It is needed when precise contextual queries speed up discovery across large project folders.

Can I use natural language queries to find function usage across a large repository?

Yes, natural-language queries locate where a function is used or how parameters appear in config files across large repositories, returning relevant file paths and line ranges fast.

What's the best way to find where a function is defined without exact string matching?

Intent-aware search accepts a description or function signature in natural language, understanding contextual meaning to locate definitions and references without requiring exact string matches.

Does semantic search work with documentation repositories and config files?

Semantic search applies to documentation repositories, project folders, and config files, supporting natural-language queries to locate parameter usage and contextual references with relevant file paths and line ranges.

Why does traditional grep return brittle results for contextual code searches?

Traditional grep can be brittle and time-consuming because it matches exact strings, whereas semantic search understands intent to deliver more relevant results fast across local files and codebases.