llm-sandbox CLAUDE.md

llm-sandbox CLAUDE.md is an instructions file for Claude Code from vndee/llm-sandbox. It costs 2,639 tokens per session, scanned A, original, MIT.

A project guide for LLM Sandbox, a Python tool that runs AI-generated code in isolated containers. It describes the project structure, execution sessions, container backends, and supported environments.

In plain words
What is it for?
Use it when asking an agent to modify, debug, or understand sandbox sessions, container support, artifact capture, or interactive Python execution.
Why use it?
It gives an AI coding agent the background needed to work safely and consistently in an unfamiliar codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

About the project

LLM Sandbox is a Python library and MCP server for running code generated by large language models inside isolated containers. It is used when AI-generated programs need controlled access to languages, dependencies, computing resources, or networks without directly reaching the host system. The catalogue add-ons help agents use the sandbox.

vndee/llm-sandbox · 1,119 stars · on GitHub · vndee.github.io

Install

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.

agentmods
npx agentmods add instructions/vndee/llm-sandbox/claude-md
Clone the repo
git clone --depth 1 https://github.com/vndee/llm-sandbox

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.

agentmods badge for llm-sandbox CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vndee/llm-sandbox/claude-md.svg)](https://agentmods.dev/instructions/vndee/llm-sandbox/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vndee/llm-sandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/vndee/llm-sandbox/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,639 This file is loaded in full into every session.
When invoked 2,639 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02639 $0.02639
Opus 5 $0.01319 $0.01319
Sonnet 5 $0.00528 $0.00528
Haiku 4.5 $0.00264 $0.00264

Measured 6d ago against content hash a33cbf89080f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

llm-sandbox 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 6d 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 · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Sandbox - AI Assistant Guide

This document provides context and guidance for AI assistants working with the LLM Sandbox codebase.

Project Overview

LLM Sandbox is a lightweight and portable sandbox environment designed to run Large Language Model (LLM) generated code in a safe and isolated mode. It provides secure execution environments for AI-generated code while offering flexibility in container backends and comprehensive language support.

Version: 0.3.13 License: MIT Python Support: 3.10+ Documentation: https://vndee.github.io/llm-sandbox/ Repository: https://github.com/vndee/llm-sandbox

Core Architecture

Key Components

  1. Session Management (llm_sandbox/session.py)

    • SandboxSession: Basic code execution in isolated containers
    • ArtifactSandboxSession: Execution with automatic artifact capture (plots, visualizations)
    • InteractiveSandboxSession: Stateful sessions maintaining Python interpreter state
    • create_session(): Factory function for session creation
  2. Container Backends (llm_sandbox/docker.py, llm_sandbox/kubernetes.py, llm_sandbox/podman.py)

    • Docker (default, most common)
    • Kubernetes (enterprise-grade orchestration)
    • Podman (rootless containers)
  3. Language Handlers (llm_sandbox/language_handlers/)

    • Python (python_handler.py)
    • JavaScript/Node.js (javascript_handler.py)
    • Java (java_handler.py)
    • C++ (cpp_handler.py)
    • Go (go_handler.py)
    • R (r_handler.py)
    • Ruby (ruby_handler.py)
  4. Container Pooling (llm_sandbox/pool/)

    • Pre-warmed container management for performance
    • Thread-safe concurrent execution
    • Configurable pool sizes and lifecycle management
  5. Security (llm_sandbox/security.py)

    • Security policies and pattern matching
    • Code scanning for vulnerabilities
    • Resource limits and network isolation
  6. MCP Server (llm_sandbox/mcp_server/)

    • Model Context Protocol integration
    • Enables Claude Desktop and other MCP clients to execute code

Read the full file on GitHub · 351 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.

  1. 6d ago First seen · 351 lines · 2,639 tokens per session scan A a33cbf89080f

Subscribe to this mod's changes

llm-sandbox CLAUDE.md is an instructions file published in the GitHub repository vndee/llm-sandbox (1,119 stars, last pushed 3d ago), licensed MIT. It adds 2,639 tokens to every session, about $0.0132 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.