grep-and-read

What problem does it solve?

Exploring a codebase often involves repeatedly searching for a pattern, then individually reading each matching file. This sequential process is slow and token-inefficient, requiring multiple LLM round-trips. This Skill combines these steps into a single, efficient operation.

Core Features & Use Cases

• Atomic Search & Read: Combines grep and read operations into a single, efficient step, drastically reducing round-trips.
• Performance Boost: Achieves 50-70% time savings and significant token savings compared to manual sequential reading.
• Flexible Filtering: Supports regex patterns, file type globs, and path specifications for targeted searches.
• Contextual Output: Limits output per file (context_lines) and provides clear summaries, even for many matches.
• Use Case: When you need to understand how a specific API (FormattingRule) is implemented across your Java codebase, use this Skill to find all relevant files and read their contents in one go, giving you a comprehensive overview without tedious manual steps.

Quick Start

To explore how "FormattingRule" is implemented in Java files: Skill: grep-and-read pattern="FormattingRule" path="/workspace/main" glob="*.java" max_files=5