Skills for coding agents

Session manager for Claude Code with automatic documentation and artifact tracking

Cursor Custom Slash Commands

Conditionally run actions based on files modified by PR, feature branch or pushed commits

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

Reusable setup prompts for optimizing Claude Code documentation. Achieve 90% token savings on any project in 5 minutes.

Intelligent token optimization for Claude Code - achieving 95%+ token reduction through caching, compression, and smart tool intelligence

One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.

The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% wall time, 0 losses across 96 tasks on Claude Opus 4.7. Structural code naviga…

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…

"Monitor your Cursor AI usage, token consumption, and costs in real-time with detailed breakdowns by model and session

Monitor Cursor IDE usage, detect spending anomalies, and alert your team. Self-hosted, open-source.

A command-line tool to extract and export chat sessions from Cursor

A cursor extension that exposes the usage of all your agents.

Markdown preview plugin for Neovim

🦀 Supercharge your Rust experience in Neovim! A heavily modified fork of rust-tools.nvim

🍿 A collection of QoL plugins for Neovim

Retrieval Assessment for Knowledge Impact — evaluate agentic RAG quality from session transcripts

Intuitive, easy CLIs based on python type hints.

The open agent skills tool - npx skills

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

"OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/

#1 Persistent memory for AI coding agents based on real-world benchmarks

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…

An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

Automated collection of Claude Code plugin adoption metrics across GitHub repositories using n8n workflows