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.
Borrowing it
Nothing to install: this file belongs to vndee/llm-sandbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vndee/llm-sandbox/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/vndee/llm-sandboxWrote 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/vndee/llm-sandbox/copilot-instructions)<a href="https://agentmods.dev/instructions/vndee/llm-sandbox/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/vndee/llm-sandbox/copilot-instructions/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.
<a href="https://agentmods.dev/instructions/vndee/llm-sandbox/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/vndee/llm-sandbox/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02205 | $0.02205 |
| Opus 5.5 | $0.00882 | $0.00882 |
| Sonnet 5.5 | $0.00441 | $0.00441 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
llm-sandbox copilot-instructions.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 1mo 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for LLM Sandbox
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. The project provides secure execution environments for AI-generated code with:
- Multi-language support: Python, JavaScript/Node.js, Java, C++, Go, R, and Ruby
- Flexible backends: Docker, Kubernetes, Podman, and Micromamba
- Security-first design: Isolated execution, security policies, resource limits, and network isolation
- LLM framework integration: Works with LangChain, LangGraph, LlamaIndex, OpenAI, and more
- Model Context Protocol (MCP): Server implementation for MCP clients like Claude Desktop
Code Style and Formatting
Python Code Standards
- Python version: Support Python 3.10, 3.11, 3.12, and 3.13
- Style guide: Follow PEP 8 with Ruff enforced rules (see
pyproject.toml) - Line length: Maximum 120 characters
- Type hints: Always use type hints for function signatures and class attributes
- Docstrings: Use Google-style docstrings for all public functions, classes, and modules
Example:
def execute_code(code: str, timeout: int = 30) -> ExecutionResult:
"""Execute code in the sandbox environment.
Args:
code: The code to execute
timeout: Maximum execution time in seconds
Returns:
ExecutionResult containing stdout, stderr, and exit code
Raises:
TimeoutError: If execution exceeds timeout
SecurityError: If code violates security policy
"""
pass
Code Organization
- Use Pydantic models for data structures and configuration
- Follow existing module structure:
llm_sandbox/core/: Core functionality and base classesllm_sandbox/language_handlers/: Language-specific handlersllm_sandbox/mcp_server/: MCP server implementation- Backend implementations:
docker.py,kubernetes.py,podman.py,micromamba.py
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.
- 1mo ago First seen · 349 lines · 2,205 tokens per session scan A 78b622304e4b
llm-sandbox copilot-instructions.md is an instructions file published in the GitHub repository vndee/llm-sandbox (1,137 stars, last pushed yesterday), licensed MIT. It adds 2,205 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.