xiaolai

OpenAI Codex MCP integration for Claude Code

Enforces strict TDD discipline — test-first workflow, coverage gates, mutation testing, behavior-driven test quality audits

Mine past Claude Code conversations for decisions, mistakes, patterns, and wisdom. Manage memory lifecycle: audit staleness, extract knowledge, prune waste.

Enforce per-file pure LOC limits with automated optimization strategies — counts, flags violations, and provides opus-powered extraction plans

Deep codebase interrogation — multi-angle architecture review with 6 specialized agents, 5 review styles (including Paranoid Mode), and 8 add-on pressure tests

Documentation quality and freshness enforcer — detect staleness, check accuracy, measure coverage, and auto-generate docs across any language and doc framework

Natural-Language Programming Manager — scan, lint, score, fix, test (TDD), and trend-track NL artifacts with Claude-native quality scoring and the 50 Rules

Agent Workflow Framework Using Labels — design, generate, and audit agent workflows driven by GitHub events

OpenAI Codex MCP integration for Claude Code — audit, implement, verify, review, and debug via Codex

Process EPUB books into summaries, knowledge extractions, Obsidian notes, and RAG databases