xiaolai

One plugin to bridge and delegate across Claude Code, Codex CLI, and Gemini CLI — single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, and full Claude↔Codex bidirectional delegation.

TDD Guardian — enforces strict test-driven development discipline in Claude Code with quality gates, coverage enforcement, and mutation testing

Mine past Claude Code conversations for decisions, mistakes, patterns, and wisdom

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 that forces rigorous, actionable analysis

Documentation quality and freshness enforcer — detect staleness, check accuracy, measure coverage, and auto-generate docs

Natural-Language Programming Manager — score, check, fix, and test NL artifacts across Claude Code, Codex CLI, and Antigravity. Tier-aware scoring with per-tool overlays.

English language coach for non-native speakers — auto-corrects prompts, translates non-English, refines with :: prefix, tracks improvement over time

Auto-preview Mermaid diagrams in the browser on Write/Edit/MultiEdit/NotebookEdit. Inlined Mermaid bundle (offline-safe), dark-mode aware, auto-reload on source change, per-file preview with LRU retention, opens the tab once per file (MERMAID_PREVIEW_ALWAYS_OPEN=1 to force-open every write).

Block hardcoded UI values; enforce design tokens with rewrite-first hooks and a closed-loop control system

Advisory responsive-design coach — flags non-responsive patterns post-write; never blocks tool calls

A 260-token system prompt that overrides three structural presumptions every RLHF-trained LLM inherits from training: that you want confirmation, that old scarcity still applies, that best practices are ceilings.

Auto-updated multi-skill reference for the whole Anthropic doc ecosystem. 8 skills covering claude-code, claude-agent-sdk, anthropic-api, anthropic-platform-features, claude-connectors, claude-cowork, mcp-spec, and anthropic-pulse (news + research digests). Pipeline refreshes daily.

Recursive governance for Executable Operating Units (EOUs). Faceted classification, generating-EOU constraints, ECP-governed change, no-self-approval. Install in any project that needs to turn messy workflows into auditable, retirable operating units.

Turn AI sessions into a maintained, inspectable canon. Capture each session to append-only logbooks, compile them into a consistency-checked knowledge base (cabinets) gated by a human review tier, and render it as a navigable offline gazette (built by the bundled press). Karpathy LLM-wiki pattern + session provenance. Self-contained — no separate install.