osgrep

Search source files by natural language queries and return ranked code matches.

Updated Jan 12, 2026
One-click install
npx skills add https://github.com/hasparus/claude-skills-dotfiles --skill osgrep-hasparus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: osgrep
Source: https://github.com/hasparus/claude-skills-dotfiles/tree/main/osgrep
Command: npx skills add https://github.com/hasparus/claude-skills-dotfiles --skill osgrep-hasparus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Semantic code search uses natural language queries to locate relevant source files by intent, returning file paths with line numbers and code snippets.

Core Features & Use Cases

  • Conceptual code search that matches intent across large codebases.
  • Returns file paths with line numbers and code snippets for quick context.
  • Supports targeted searches with optional path constraints to narrow results.

Quick Start

Ask osgrep to locate where a concept is implemented using a natural-language query.

Frequently Asked Questions about osgrep

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

FAQPage Schema
How do I find where a feature is implemented in a large codebase using natural language?

Semantic code search locates relevant source files by concept or behavior using natural language queries. It returns file paths, line numbers, and code snippets ranked by semantic relevance across large codebases.

What is semantic code search and how does it match intent?

Semantic code search matches natural language queries to source code by underlying concept rather than exact string matching. It surfaces file paths and line numbers to show where specific behaviors are implemented.

Can I narrow semantic code search results to a specific directory path?

Yes, semantic code search supports targeted searches with optional path constraints. Applying path constraints narrows the search scope to return file paths and code snippets only within the specified directories.

How do I search for how a component works without knowing the exact function name?

Use natural language to describe the component's behavior or concept. The search matches your query to the underlying intent and returns ranked file paths with line numbers and code snippets for context.

Does semantic code search work across large codebases with multiple source files?

Yes, semantic code search is designed to apply across large codebases. It ranks results by semantic relevance and returns file paths with line numbers to help you locate concepts across many source files.

What results should I expect from a natural language code search?

Code search returns file paths with line numbers and code snippets. These results are ranked by semantic relevance to your natural language query, providing quick context for how a feature works.