What is sandy CLAUDE.md?

Project instructions for Sandy, a tool that records sequences of MCP tool calls as reusable scenarios. MCP is a standard way for an AI agent to use external tools and services.

Creating and replaying fixed tool-call workflows, especially in automated build checks and regression tests. It also documents Sandy's Python project structure and setup.

It lets repeated workflows run again without asking an AI model to reason through every step, which can reduce repeated work and token use.

How Sangkwun/sandy configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Sangkwun/sandy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Sangkwun/sandy/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Sangkwun/sandy

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sangkwun/sandy/claude-md/github.svg)](https://agentmods.dev/instructions/sangkwun/sandy/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sangkwun/sandy/claude-md"><img src="https://agentmods.dev/badge/instructions/sangkwun/sandy/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sangkwun/sandy/claude-md"><img src="https://agentmods.dev/badge/instructions/sangkwun/sandy/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,435 This file is loaded in full into every session.

When invoked 1,435 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01435	$0.01435
Opus 5.5	$0.00574	$0.00574
Sonnet 5.5	$0.00287	$0.00287
Haiku 4.5	$0.00144	$0.00144

Measured 2mo ago against content hash 835308190dc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sandy CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandy - MCP Scenario Player

Project Overview

Sandy is a deterministic workflow accelerator for AI agents. Agents create MCP tool call sequences as scenarios, then replay them without LLM inference—saving tokens and time.

Core Value:

Deterministic replay of MCP tool calls without LLM
Reduced token costs for repetitive tasks
Ideal for CI/CD pipelines and regression testing

How Agents Use Sandy:

Execute a workflow using MCP tools
Identify it as repeatable
Write the tool sequence as a scenario JSON
Replay via Sandy on future requests

Tech Stack

Language: Python 3.14
Core Dependencies:
- mcp>=1.0.0 - MCP Python SDK
- websockets>=12.0 - WebSocket support
- jsonpath-ng>=1.6.0 - JSONPath output extraction
- python-dotenv>=1.0.0 - Environment variable loading

Project Structure

sandy/
├── sandy-skill/                    # Main plugin/CLI implementation
│   ├── .claude-plugin/
│   │   └── plugin.json            # Claude Code plugin manifest
│   ├── .sandy/
│   │   └── config.json            # MCP server configuration
│   ├── skills/sandy/
│   │   └── SKILL.md               # Skill specification (for Claude Code)
│   ├── scripts/                   # Core Python implementation
│   │   ├── play.py               # CLI entry point
│   │   ├── player.py             # Scenario executor
│   │   ├── scenario.py           # Scenario parser & validator
│   │   ├── config.py             # Config auto-detection
│   │   ├── reporter.py           # Result formatting
│   │   └── clients/              # MCP transport implementations
│   │       ├── base.py           # Abstract base class
│   │       ├── stdio_client.py   # stdio transport
│   │       ├── sse_client.py     # SSE transport
│   │       ├── websocket_client.py
│   │       └── socket_client.py  # Unix socket
│   ├── assets/examples/          # Example scenarios
│   ├── references/schema.md      # JSON schema documentation
│   └── tests/                    # Unit tests
└── README.md

Read the full file on GitHub · 172 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 172 lines · 1,435 tokens per session scan A 835308190dc0

Subscribe to this mod's changes

sandy CLAUDE.md is an instructions file published in the GitHub repository Sangkwun/sandy (14 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 1,435 tokens to every session, about $0.0057 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Deterministic automation claude-code-plugin mcp scenario-replay

sandy CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sandy CLAUDE.mdSangkwun/sandy	Instructions file	14	9mo ago	Apache-2.0	A	1,435	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

sandy: Instructions file for Claude Code