Fast and accurate code statistics tool written in Rust. Counts lines of code, comments, and blanks across 200+ languages, with output in JSON, YAML, or CBOR for programmatic analysis of codebase composition.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "tokei Code Statistics Counter"
slug: "tokei-code-statistics-counter"
description: "Fast and accurate code statistics tool written in Rust. Counts lines of code, comments, and blanks across 200+ languages, with output in JSON, YAML, or CBOR for programmatic analysis of codebase composition."
github_stars: 14169
verification: "security_reviewed"
source: "https://github.com/XAMPPRocky/tokei"
category: "Code Quality & Review"
framework: "Claude Code"
tool_ecosystem:
github_repo: "XAMPPRocky/tokei"
github_stars: 14169
---
# tokei Code Statistics Counter
Fast and accurate code statistics tool written in Rust. Counts lines of code, comments, and blanks across 200+ languages, with output in JSON, YAML, or CBOR for programmatic analysis of codebase composition.
## Installation
Use the upstream install or setup path that matches your environment:
- cargo install tokei
- conda install -c conda-forge tokei
- brew install tokei
- cargo install --git https://github.com/XAMPPRocky/tokei.git tokei
Requirements and caveats from upstream:
- You can also build and install from source (requires the latest stable [Rust] compiler.)
- Tokei is available in a small alpine-based docker image, buildable through [earthly](https://github.com/earthly/earthly):
Basic usage or getting-started notes:
- ## Example
- reused in tokei combining a previous run's statistics with another set.
- ### Package Managers
- Source: https://github.com/XAMPPRocky/tokei
- Extracted from upstream docs: https://raw.githubusercontent.com/XAMPPRocky/tokei/HEAD/README.md
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/tokei-code-statistics-counter/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.