Aios — Testing skill for Claude Code
Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.
How to install Aios
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open rexleimo/rex-cli and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Aios does
Local-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.
Alternatives in Testing
- Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★
- Spec Kit Zh — 💫 帮助你快速上手规格驱动开发的工具包💫 Toolkit to help you get started with Spec-Driven Development Works seamlessly across al 238 ★
- GAAI Framework — 95+ Drop-in governance layer (.gaai/ folder) -- backlog authorization, cross-session memory, decision tracking 113 ★
README
AIOS
[](https://github.com/rexleimo/aios/releases) [](https://cli.rexai.top) [](https://github.com/rexleimo/aios) [](https://nodejs.org)
**One sentence. Any complex task. Done.** AIOS makes your AI coding agent actually finish the job — memory, verification, and multi-agent collaboration, all from a single instruction. Works with `codex`, `claude`, `gemini`, `opencode`, `hermes`, and `grok`.
[Docs](https://cli.rexai.top) · [Quick Start](https://cli.rexai.top/getting-started/) · [Blog](https://cli.rexai.top/blog/) · [中文](README-zh.md)

Why AIOS
**One sentence. Any complex task. Done.** That's the promise.
Your AI coding agent (Codex, Claude Code, Gemini CLI, OpenCode, Hermes, Grok) is smart — but it forgets everything between sessions, can't coordinate complex multi-step work, and has no way to verify its own output. AIOS fixes all of that:
| You say | AIOS does | | —- | --- | | "Refactor the auth module" | Remembers last week's decisions, picks the right approach, makes the change, and verifies it works | | "Review this PR and update tests" | Splits the work across parallel agents, keeps coupled changes in order, collects evidence | | "Finish the release handoff overnight" | Runs the full objective with checkpoints, resumes if interrupted, delivers verified results | | "Fix the login bug" | Recalls relevant context, routes to the simplest fix path, checks the fix before showing you |
**Your data stays local.** Everything — memory, logs, verification — runs on your machine. Nothing leaves.
**You don't change how you work.** Keep using the coding client you already have. AIOS adds what it's missing
Related Skills
Vindicate
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP
Maxsimcli
Solve context rot in AI coding. Spec-driven development system for Claude Code, OpenCode, Gemini CLI, and Code
Prompthistory
CLI tool to search, replay, test, and compare your AI coding assistant prompts. Supports OpenCode, Claude Code
Spectoflow
Agent-agnostic spec-driven development framework with a real-time local dashboard — works with Claude Code, Gi
Agentic Code
Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor,
Dify MCP
The most complete Dify MCP server + CLI - 138 tools that let any AI agent build, test & ship Dify workflows au
Related Agents
Agent Of Empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and
Developer Overview
code-container (container) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode
Browser Testing
Browser automation and testing specialist. Uses playwright-cli (stateful Bash CLI) for deterministic scripted