Deterministic MCP scenario replay for AI agents — create once, replay without LLM inference
How to install sandy?
sangkwun/sandy
$claude plugin marketplace add sangkwun/sandyInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install sandy by running `claude plugin marketplace add sangkwun/sandy`, then use it for the current task and follow its documentation at https://github.com/sangkwun/sandy.
Related
6 picksType
- superpowersCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniquesJul 2026
- eccHarness-native ECC plugin for engineering teams - 67 agents, 281 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnessesJul 2026
- everything-claude-codeHarness-native ECC plugin for engineering teams - 67 agents, 281 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnessesJul 2026
- skillsAnthropic example skillsJul 2026
- agent-skillsProduction-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.Jul 2026
- ruflo🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more IntegratedJul 2026
