Search files by regex pattern and read matching contents in parallel.
npx skills add https://github.com/cowwoc/styler --skill grep-and-read
Please help me install this Agent Skill. Skill: grep-and-read Source: https://github.com/cowwoc/styler/tree/main/.claude/skills/grep-and-read Command: npx skills add https://github.com/cowwoc/styler --skill grep-and-read
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.
grep and read operations into a single, efficient step, drastically reducing round-trips.context_lines) and provides clear summaries, even for many matches.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.To explore how "FormattingRule" is implemented in Java files: Skill: grep-and-read pattern="FormattingRule" path="/workspace/main" glob="*.java" max_files=5
High-intent search queries and answers about installing and using this skill.
grep-and-read combines pattern search and file reading into a single operation. Specify a regex pattern, optional path, and glob filter—the Skill finds all matching files and returns their contents consolidated, eliminating sequential grep-then-read workflows that waste tokens and round-trips.
Yes. Search for the API name or class across your repository with regex patterns and file type filters. The Skill returns all matching files with context, giving you a complete implementation overview without manually reading each file individually.
Pattern search with file-type filtering pinpoints all occurrences instantly. Set max_files to control output scale, use context_lines to see surrounding code, and case_sensitive matching for precise queries—all results return in a single consolidated output.
Combining grep and read achieves 50-70% time savings and significant token reduction compared to sequential manual searching and reading. Parallel execution of both operations eliminates multiple LLM round-trips on large codebases.
Yes. Use max_files to cap the number of matching files returned and context_lines to truncate output per file. These controls keep responses focused and manageable even across repositories with thousands of matches.
Yes. grep-and-read supports full regex pattern input, optional path specification, and glob filters like *.java or *.py for targeting specific file types. Combine these with case_sensitive controls for exact or flexible matching.
marcoguillermazDetect and report documentation drift in repository docs as structured markdown reports.
parcadeiRender code trees, search with context, and extract signatures via RepoPrompt CLI.
dtsongSearch codebases for text patterns and files using grep and glob.
minhtri2710Search AI coding agent histories with filtering and context expansion.