Sangkwun/sandy

Deterministic MCP scenario replay for AI agents — create once, replay without LLM inference

1 file for Claude Code: sandy CLAUDE.md — 1,435 tokens loaded in every session.

Open on GitHub

14Stars on the repository

1Files it configures its agents with

1,435Tokens loaded in every session

1Agent configured

Instructions

sandy CLAUDE.md CLAUDE.md A 1,435 tok

These files are Sangkwun/sandy's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.