Last commit on August 24, 2026·Created on June 5, 2026
chaseai-yt/claudex-loop
“Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.”
Combined rank
#170
across all skills
Stars
1.2k
7d change unavailable
Forks
123
Watchers
12
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.
WHO IT'S FOR
Technical leads / architects
stress-test high-stakes design plans before implementation
Backend / infrastructure engineers
harden database migrations and concurrency models
AI agent power users
orchestrate multi-model adversarial plan reviews
Software engineers
resolve decision tree branches for complex features
Want to install it?
Claude Marketplace · Claude Plugin · CLI Installer · Clone to Claude · Manual CopyRepository instructions