Claude
Tools

38 engineering discipline skills for Claude Code & OpenAI Codex — research, quality gates, testing, deployment, gap analysis, and more. Born from real pain, not theory.

MCP server for BookStack — 56 tools covering the full API + semantic vector search. Rust/tokio/axum, dual transport (SSE + Streamable HTTP), OAuth 2.1, pluggable DB (SQLite/PostgreSQL+pgvector).

A collection of hooks and skills for Factory Droid and Claude Code that add planning automation, persistent memory, smart commits, and more. Drop them into your home directory and they work out of the box.

Safari Web Extension that lets Claude Code control Safari via MCP (Model Context Protocol)

CodeX / Claude Code 分级通知插件 — 11 个渠道，短通知即时触达，长通知异步兜底。人可以闲着，Agent 不可以。

Non-destructive Claude Code rules layer + the only published fix for Windows plugin hook startup failures

Token-level cost intelligence for AI coding tools — budget alerts, anomaly detection, and multi-tool tracking across Claude Code, Codex CLI, Cline, and Gemini CLI

Universal development discipline enforcement framework for Claude Code — hooks, rules, profiles, cross-project sync

A Claude skill for applying behavioral psychology and behavioral economics to product and UX design. Behavioral diagnosis, nudge design, intervention frameworks, workshop facilitation, and ethics review. Built for product designers, pms and cross-functional teams.

Multilingual AI Coding CLI — undo, safety hooks, session resume, thinking control, 12 MCP tools & i18n (zh/en/ja/ko...) | @aiai-go/claude

Run Claude Code as a headless AI agent over HTTP — hooks + ai + flow. Automate code generation, refactoring, bug triage via REST API using your existing Claude Code subscription.

Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs by 67%.

Cross-platform toolkit for running multiple Claude Code AI agents in parallel terminal panels. Includes automated setup scripts, SAND keybinding system, git worktree hooks for isolated agent work, and visual monitoring with lazygit and yazi. Supports macOS, Linux, and Windows.

Multi-agent social simulation as a Claude Code skill. Zero dependencies — predict anything with /crowdcast simulate.

Terminal buddy companion — a persistent ASCII pet that lives across Claude Code conversations. 18 species, 6 eyes, 8 hats, personality-driven replies, affection decay, and auto-trigger hooks.

Ultimate marketing plugin for Claude Code and Cowork — selling digital products (PDF guides, templates, printables) using Alex Hormozi complete methodology. 40+ skills, 6 slash commands /hook /offer /ads /proof /brand /retention. Based on coreyhaines31/marketingskills enriched with $100M Hormozi frameworks.

Claude Code skill health dashboard - security scan, token cost, budget analysis, hook conflicts, usage tracking. ~225ms full scan.

One local callback layer for Claude Code and Codex: a macOS-ready CLI for native permission dialogs and notifications, plus a FastAPI-like Python framework

Claude skill for official-first, dependency-ordered learning paths for technical topics.

AI coding plugin that gives you an entire engineering team — CTO, SRE, DBA, Security Engineer, and more — as AI skills.

Brain Drin (60+ Agents, 100+ Skills) — The ultimate tactical suite for Claude Code. Fusing best practices from Anthropics, wshobson, qdhenry, and BMAD into a high-performance force. Optimizing every token for SOTA results in Engineering, Infrastructure, and Business Strategy. Outperform the solo engineer. Scale with elite subagents. Portable. High-

Effect v4 bindings for Claude Code's plugin primitives — hooks, skills, settings, MCP servers, frontmatter

Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph. No cloud, no API keys. npx @studiomeyer/local-memory-mcp

Production-ready starter template for LLM-maintained wikis. Karpathy's 2026-04 three-tier pattern (raw/wiki/schema) + journal extension + lint hygiene. Clone, feed docs, let the LLM do bookkeeping.