Aiworks — AI skill for Claude Code
Manager for AI coding agents that runs on your own PC: hands each step of an agreed plan to Claude Code, Codex or Cursor, has a second AI verify the result, and delivers pull requests to GitHub.
How to install Aiworks
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open netbka/aiworks and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Aiworks does
Manager for AI coding agents that runs on your own PC: hands each step of an agreed plan to Claude Code, Codex or Cursor, has a second AI verify the result, and delivers pull requests to GitHub. Keeps going through crashes, restarts and usage limits; asks you only for real decisions. Windows, early preview.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Claude Hub — by Claude Did This - A webhook service that connects Claude Code to GitHub repositories, enabling AI-powered c 393 ★
- Context Attachment Manager — Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your nex 221 ★
README
The problem · What it does · Results · How you use it · Production & roadmap · Technical details
**AIWorks is a manager for AI coding agents that runs on your own computer.** You agree on a plan once. AIWorks gives each step to an AI agent (Claude, Codex or Cursor), has a second, separate AI check the result, and delivers the finished work to GitHub as a pull request. It keeps going through crashes, restarts and usage limits, and asks you only when a real decision is needed.
The problem
AI agents write good code. Keeping them working is a job of its own.
- They stop. An agent finishes one step and waits for someone to type "continue".
- "Done" is not proof. You still have to find out what changed and whether it actually works.
- Limits waste hours. An agent hits its usage limit late at night, and nothing moves until you notice in the morning.
- Projects blur together. With several products going, you lose track of what is finished, what is stuck and what is waiting for you.
You end up as a full-time project manager for your AI helpers instead of working on your pr
Related Skills
Sherwanis Claude Md
Drop-in AGENTS.md / CLAUDE.md that keeps AI coding agents honest: ask before assuming, keep it simple, change
Brain Kit
Second brain kit: an OKF markdown vault curated by AI agents through pull requests, as an npm CLI and a Claude
Lich
A terminal-first harness for coding with AI agents — real PTYs, git worktrees, diffs and pull requests in one
Review System
You are a code review agent. Your job is to review pull requests created by AI agents.
Webhook Collector
Simple API for creating a webhook endpoint to capture webhook requests. Built for AI agents that cannot receiv
Devintern
Turn tracker tickets into pull requests with the coding agent and model you choose. FSL source-available.
Related Agents
Wireframer
Second step after the jtbd-critic. Takes an AGREED jobs review (reviews/ /jtbd.md) and draws its mockup brief
Git
Isolated executor for the /playbook:commit-and-push and /playbook:create-pull-request commands. Delivers signe
Delivery Tpm
Delivery control (code: tpm). Reconciles the board with branches, worktrees, pull requests, and gates; keeps o