CruxExperts

Localsetup — AI skill for Claude Code

AI community

Universal cross-platform repo-local workflow engine for AI agents: context-as-code, reusable skills, and one-command install for Cursor, Claude Code, OpenAI Codex CLI, and OpenClaw.

How to install Localsetup

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

What Localsetup does

Universal cross-platform repo-local workflow engine for AI agents: context-as-code, reusable skills, and one-command install for Cursor, Claude Code, OpenAI Codex CLI, and OpenClaw.

Alternatives in AI

  • Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
  • EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
  • Codesight — Universal AI context generator 979 ★

README

LocalSetup

LocalSetup: portable skills and deliberate workflows, with one package library serving selected agent hosts

License Agent Skills compatible Supported platforms

**Version:** 4.22.6

**LocalSetup gives coding agents a repo-local operating layer.**

Keep reusable agent skills in one managed library, expose the packages each project needs, and review the instructions alongside your code.

LocalSetup provides capability skills, executable workflow packages, explicit adapter selection, install planning, verification, and rollback records. It supports Cursor, Claude Code, OpenAI Codex CLI, OpenClaw, Kilo, and OpenCode. Custom project skills can live beside managed packages.

Start with the [quickstart](ls/docs/QUICKSTART.md), browse the [documentation](ls/docs/README.md), or read the [4.4.0 release guide](ls/docs/releases/4.4.0.md).

What's new in 4.4

  • Focused context: Platform templates use canonical catalogs and current-client discovery instead of repeating the package inventory. Optional templates remain distinct from installed adapters.
  • Clear workflow ownership: Audit, documentation, heartbeat, and transport entry points route to their owning capability packages. The generated registry lists the supported workflow packages.
  • Cleaner managed packages: Source materialization omits Python bytecode caches while retaining source files, hidden assets, and package data.
  • Isolated audit execution: Sandbox