Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sangkwun/sandy/claude-mdgit clone --depth 1 https://github.com/Sangkwun/sandyWrote 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.
[](https://agentmods.dev/instructions/sangkwun/sandy/claude-md)<a href="https://agentmods.dev/instructions/sangkwun/sandy/claude-md"><img src="https://agentmods.dev/badge/instructions/sangkwun/sandy/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01435 | $0.01435 |
| Opus 5 | $0.00718 | $0.00718 |
| Sonnet 5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00144 | $0.00144 |
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 5d 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.
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 SDKwebsockets>=12.0- WebSocket supportjsonpath-ng>=1.6.0- JSONPath output extractionpython-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
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.
- 5d ago First seen · 172 lines · 1,435 tokens per session scan A 835308190dc0
sandy CLAUDE.md is an instructions file published in the GitHub repository Sangkwun/sandy (14 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,435 tokens to every session, about $0.0072 per session on Opus 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.
Other instructions, from other repositories
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.