ldomaradzki/xcsift

A Swift command-line tool that parses xcodebuild output into token-efficient JSON for coding agents.

What it solves

xcsift addresses the problem of verbose, human-centric Xcode build and Swift Package Manager (SPM) output. While tools like xcbeautify make logs readable for people, they are not optimized for Large Language Models (LLMs) or coding agents, which can be overwhelmed by noise and consume excessive tokens when processing raw build logs.

How it works

It acts as a command-line pipe that consumes xcodebuild or swift build output. It parses the raw logs and transforms them into structured, machine-readable formats. It offers a specialized "TOON" format designed specifically to reduce token usage by 30-60% compared to standard JSON, making it more efficient for LLMs to process.

Who it’s for

This tool is primarily for developers using AI coding assistants (such as Claude Code, Cursor, or Codex) and CI/CD pipeline engineers who need structured build data for automated analysis.

Highlights

  • LLM-Optimized Formats: Provides JSON and a high-density TOON format to minimize token costs and maximize agent efficiency.
  • Structured Error Reporting: Extracts errors, warnings, and linker failures with precise file and line locations.
  • Automated Coverage: Converts .profraw and .xcresult files into JSON format.
  • Agent Integration: Includes built-in installers for popular coding assistants like Claude Code and Cursor.
  • CI-Ready: Features GitHub Actions integration for inline PR comments and modes for treating warnings as errors.

Related

  • Project
    github/CopilotForXcode

    An AI coding assistant for Xcode that provides intelligent code completions, chat, and an agentic mode for Swift and Objective-C development.

  • Project
    AvdLee/Xcode-Build-Optimization-Agent-Skill

    A collection of AI agent skills for benchmarking and optimizing Xcode build performance, providing an automated analyze-approve-fix workflow to reduce build times.

  • Project
    edouard-claude/snip

    A CLI proxy that filters verbose shell output before it reaches AI coding assistants, reducing token usage by 60-90% through declarative YAML pipelines.

  • Project
    AvdLee/SwiftUI-Agent-Skill

    A specialized knowledge base and performance toolset for AI agents to provide expert-level SwiftUI guidance on state management, view composition, and Instruments trace analysis.

  • Project
    jfrog/boost

    Boost is a command wrapper that compresses noisy shell output into structured context for AI coding agents, reducing token costs without sacrificing task performance.