AkashPriyadarshii

Rustygrep — AI skill for Claude Code

AI community

Fast grep with token-compressed, AI-native output for LLM coding agents.

How to install Rustygrep

This entry records only its repository, not the path inside it, so there is no exact command to give. Open AkashPriyadarshii/rustygrep and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Rustygrep does

Fast grep with token-compressed, AI-native output for LLM coding agents. --llm cuts context-window tokens 60-95%. Built-in MCP server wires rustygrep into Claude Code, Cursor, and OpenCode. SIMD-parallel, gitignore-aware, zero config. Install: cargo install rustygrep.

Alternatives in AI

Pixel Agents — Compressed Reference — VS Code extension with embedded React webview: pixel art office where AI agents (Claude Code terminals) are an 6.5k ★
Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★

README

rustygrep

**The token-efficient grep for AI coding agents.** Compressed output, fewer tokens, more context room.

[![crates.io](https://img.shields.io/crates/v/rustygrep?color=%23CE422B&style=flat-square&logo=rust)](https://crates.io/crates/rustygrep) [![Downloads](https://img.shields.io/crates/d/rustygrep?color=%23CE422B&style=flat-square)](https://crates.io/crates/rustygrep) [![Downloads/month](https://img.shields.io/crates/drv/rustygrep?color=%23CE422B&style=flat-square)](https://crates.io/crates/rustygrep) [![CI](https://img.shields.io/github/actions/workflow/status/AkashPriyadarshii/rustygrep/ci.yml?color=%23CE422B&style=flat-square)](https://github.com/AkashPriyadarshii/rustygrep/actions) [![License: MIT](https://img.shields.io/badge/license-MIT-green?style=flat-square)](LICENSE-MIT) [![Rust](https://img.shields.io/badge/rust-2021-blue?style=flat-square&logo=rust)](https://www.rust-lang.org/)

Why

AI coding agents run thousands of grep calls per session. Each result eats context-window tokens. `rustygrep --llm` keeps the file paths, line numbers, and matching content, and cuts the token count 60-95%.