Four-phase plan hardening for Claude Code: recon → interrogate → adversarial Codex review → cross-model build & inspection. Two AI models harden your plan before a line of code exists — then swap jobs to build it, and whoever built it never grades it. Includes claudex-loop (formerly crucible), codex-review, and…
AI code reviews grounded in twelve classic engineering books — decay risk diagnostics with book citations, severity labels, and six analysis modes (PR review, architecture audit, tech debt, test quality, health dashboard, full-sweep auto-fix).
Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
Complete Spring Boot development template with agents, skills, and best practices for enterprise Java applications. Includes JPA patterns, code quality checks, and Spring Boot 3.x support.
1.3k 4mo agoA
tokens not measured
originalApache-2.0
Taiwan knowledge for your AI, plus the skill that turns your machine into a Taiwan.md working node. The MCP server answers from 860+ curated, citation-backed articles in 12 languages — free, no API key, queries stay on your machine. The node skill picks up one open task a day and returns it as a pull request.
Cavekit — compressed spec-driven dev. Full loop (grill → spec → research → review → build) over one SPEC.md file: three core commands + four reach-for. Caveman encoding. Bug-to-spec backprop.