whatisgithub

What is architect-loop?

danmcinerney/architect-loop — explained in plain English

Analysis updated 2026-05-18

335HTMLAudience · developerComplexity · 3/5LicenseSetup · moderate

In one sentence

Two Claude Code skills that split coding and research work between Claude as planner and reviewer and Codex as builder, coordinated through files in the repo.

Mindmap

mindmap
  root((architect loop))
    What it does
      Fable plans and reviews
      Codex builds and researches
      Repo as shared memory
    Tech stack
      Claude Code skills
      Codex CLI
    Use cases
      Isolated builder lanes
      Cited research reports
      Gate checked merges
    Audience
      Developers using AI agents

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Split a coding task into isolated builder lanes with a planner checking the work before merge.

USE CASE 2

Run a scout-then-verify research loop that produces a cited, decision-oriented report.

USE CASE 3

Use acceptance gates written before coding starts so builders cannot edit their own pass criteria.

USE CASE 4

Keep a repo-based handoff file as shared memory across multiple agent sessions.

What is it built with?

Claude CodeCodex CLIPythonBash

How does it compare?

danmcinerney/architect-loopfastlane/docsopenmoss/awesome-wam
Stars335340295
LanguageHTMLHTMLHTML
Last pushed2026-07-01
MaintenanceActive
Setup difficultymoderateeasyeasy
Complexity3/51/51/5
Audiencedeveloperdeveloperresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires a paid Claude Code plan plus the Codex CLI signed into a ChatGPT plan, no separate API keys needed.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

So what is it?

architect-loop is a set of two Claude Code skills that split software development and research work between two AI models: Claude Fable handles planning and review, while GPT-5.5 Codex handles the actual building and searching. The split is intentional: the idea is that having a strong planner write the spec before any code is written produces better outcomes than having one model do everything in a single session. It runs on the subscriptions you already have for Claude Code and the Codex CLI, with no separate API keys required. The build loop is triggered by the /architect command. Claude Fable starts a short session to review the last completed work, write a spec for the next slice, and split that slice into one to four lanes where each lane owns a distinct set of files with no overlap. Acceptance gates (the criteria a lane must pass) are written to a folder in the repository before any builder starts, and builders cannot edit those files. Each lane then runs in its own isolated git working copy with a fresh Codex session. Builders are required to push back on the spec before building rather than silently comply, then report raw results without committing anything. Fable runs the gate commands itself, reads the actual code diff against the spec's intent, and only then commits and merges the lanes that pass. The research loop is triggered by /architect-research. A cheaper Codex session first scouts the topic to map terminology, key sources, and natural topic divisions. Fable then designs three to six research lanes specific to what was found. Parallel Codex sessions run the research under strict limits: search caps, a maximum number of subjects per lane, and a rule that findings must cite an actual URL with a date and a quote. Fable then verifies that load-bearing claims have at least two independent sources and writes a single decision-oriented report. The repository stores a short handoff file that acts as shared memory across sessions, along with the gate and lane files. The design choices are documented with citations in a DESIGN.md file. The license is MIT.

Copy-paste prompts

Prompt 1
Set up architect-loop in this repo so Claude plans and Codex builds the next slice.
Prompt 2
Run /architect-research on this topic and give me a cited, decision-oriented report.
Prompt 3
Explain how architect-loop's acceptance gates and lane isolation prevent unmergeable work.
Prompt 4
Walk me through what happens when a builder lane fails its gate checks.

Frequently asked questions

What is architect-loop?

Two Claude Code skills that split coding and research work between Claude as planner and reviewer and Codex as builder, coordinated through files in the repo.

What language is architect-loop written in?

Mainly HTML. The stack also includes Claude Code, Codex CLI, Python.

What license does architect-loop use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is architect-loop to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is architect-loop for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.