local-code-interpreter-tool copilot-instructions.md

A repository guide for a local code interpreter that lets AI agents run code in isolated environments. It is built with Microsoft Agent Framework and supports Python plus a virtual-machine option for Python or JavaScript.

In plain words
What is it for?
Use it when changing code execution, sandboxing, the interpreter agent, its command-line entry point, or the tools exposed to the agent.
Why use it?
It explains where execution logic belongs, which environments are available, and how tools are registered, reducing mistakes when extending the agent.

Instructions file for GitHub Copilot

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/jsturtevant/local-code-interpreter-tool/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/jsturtevant/local-code-interpreter-tool

Made for: GitHub Copilot.

Per session 1,016 This file is loaded in full into every session.
When invoked 1,016 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 $0.01016 $0.01016
Opus 5 $0.00508 $0.00508
Sonnet 5 $0.00203 $0.00203
Haiku 4.5 $0.00102 $0.00102

Measured 2d ago against content hash 2e016b8b2318, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

local-code-interpreter-tool 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 2d 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.

.github/copilot-instructions.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Code Interpreter Tool - Copilot Instructions

Project Overview

A local code interpreter tool built with the Microsoft Agent Framework. It provides sandboxed code execution capabilities for AI agents.

Architecture

src/local_code_interpreter/
├── __init__.py       # Package initialization
├── __main__.py       # CLI entry point
├── tools.py          # CodeExecutionTool - the core execution logic
└── agent.py          # ChatAgent setup, CLI, and DevUI

Key Components

  • CodeExecutionTool (tools.py): The main tool class that executes code. Supports two environments:

    • python: Fast subprocess execution (default)
    • hyperlight: VM-isolated sandbox using hyperlight-nanvix (JavaScript or Python)
  • create_interpreter_agent (agent.py:185): Factory function that creates a configured ChatAgent with the code execution tool.

Key pattern: Tools are defined once in tools.py and imported by the agent. When adding new capabilities, add the tool function to tools.py first, then register it in the agent's tools=[] list.

Execution Environments

Python Subprocess (default)

  • Fast execution in isolated subprocess
  • Output captured via stdout/stderr
  • Configurable timeout (default 30s)
  • Environment stripped for security

Hyperlight VM Sandbox

  • Uses hyperlight-nanvix for VM-level isolation
  • Supports JavaScript (default) and Python
  • Requires Linux with KVM support (/dev/kvm)
  • Higher security for untrusted code execution

Development Commands

This project uses just as a task runner. All commands automatically use the virtual environment.

# Initial setup (creates venv and installs deps)
just setup
cp .env.example .env  # Configure API keys

# Run agent (auto-detects OpenAI vs Azure based on env vars)
just run          # Run with example queries
just interactive  # Interactive chat mode

# Code quality
just format       # Format with black
just lint         # Lint with ruff
just lint-fix     # Auto-fix lint issues
just typecheck    # Type check with mypy
just check        # Run all quality checks

# Testing
just test         # Run tests
just test-ci      # Tests with coverage reports

# Build & CI
just build        # Build package
just clean        # Clean artifacts
just ci           # Run full CI pipeline locally
just pre-commit   # Validate before committing

# Utilities
just              # Show all available commands
just info         # Show environment info
just tree         # Show project structure

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 1,016 tokens per session scan A 2e016b8b2318

Subscribe to this mod's changes

local-code-interpreter-tool copilot-instructions.md is an instructions file published in the GitHub repository jsturtevant/local-code-interpreter-tool (2 stars, last pushed 7mo ago), licensed MIT. It adds 1,016 tokens to every session, about $0.0051 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 2026-08-31.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens