Architect-Loop: A cross-vendor AI agent loop combining Claude Code and GPT Codex for automated development
By
DanMcInerney
Pulled from the oven just right. Trustworthy, fact-dense, deeply satisfying.
Summary
A GitHub repository (architect-loop) that implements a cross-vendor AI agent loop using Claude Code (as the architect/planner) and GPT-5.5 Codex (as the builder/researcher). The system splits development work between two AI models: one designs and validates, the other executes engineering and research tasks in parallel. It runs on existing flat-rate subscriptions without requiring API keys or per-token billing. The tool installs in 30 seconds and uses two commands (/architect and /builder) to orchestrate the workflow.
Key quotes
· 3 pulledClaude Fable is the architect — it designs every slice, freezes the acceptance gates, and judges the results.
GPT-5.5 Codex is the builder and researcher — it does all the engineering and all the web research, in parallel, unattended, for hours.
Two Claude Code skills that run this cross-vendor loop on the flat-rate subscriptions you already have — no API keys, no token bills.
You might also wanna read
Building a Software Factory with Claude Code: From AI-Assisted Coding to Agentic Development
This article provides a comprehensive guide on building a software factory using Claude Code and other AI coding tools. It covers the evolut
freecodecamp.org·15d agoBuilding a Software Factory with Claude Code: From AI-Assisted Coding to Agentic Development
This article provides a comprehensive guide on building a software factory using Claude Code and other AI coding tools. It covers the evolut
freecodecamp.org·15d ago
GitHub Adds Claude and Codex AI Coding Agents to Platform
GitHub is introducing Claude by Anthropic and OpenAI's Codex AI coding agents directly into its platform as part of a public preview. These
The Verge·4mo ago
Claude Code Launches Multi-Agent AI Code Review System for Bug Detection
Anthropic's Claude Code now offers a multi-agent AI code review system that analyzes pull requests to catch bugs, security issues, and logic
Product Hunt·3mo ago
Production-Tested Reference Architecture for Autonomous Claude Agents
A production-tested reference architecture for building autonomous Claude agents, consisting of 9 modules (~40 files) including wake-cycle p
Product Hunt·1mo ago
Claude Code's dynamic workflows tested: Parallel subagents vs. single-agent performance
Anthropic released Claude Opus 4.8 on May 28, introducing dynamic workflows in Claude Code — a research preview feature that allows Claude t
bit.ly·2d ago
Claude Code Desktop App Redesigned for Parallel Agentic Coding
Claude Code has redesigned its desktop application to enable parallel agentic coding, allowing developers to run multiple coding sessions ac
Product Hunt·1mo ago