What is codebox-ai copilot-instructions.md?

A project guide for developing, running, testing, and checking the CodeBox-AI application with uv, a Python tool for managing project environments and commands.

Setting up CodeBox-AI, running its standard or MCP server, executing tests, measuring coverage, and running formatting and import checks.

It puts the project's setup and command details in one place, so contributors do not have to guess how to install dependencies, start services, or run checks.

codebox-ai copilot-instructions.md — Instructions file by tomconte

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/tomconte/codebox-ai/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/tomconte/codebox-ai

Made for: GitHub Copilot.

Per session 911 This file is loaded in full into every session.

When invoked 911 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.

Model	Per session	Once invoked
Fable 5	$0.00911	$0.00911
Opus 5	$0.00456	$0.00456
Sonnet 5	$0.00182	$0.00182
Haiku 4.5	$0.00091	$0.00091

Measured yesterday against content hash 0a21a6457805, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebox-ai 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 yesterday.

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 · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeBox-AI Development Guide

This guide contains instructions for developing, building, and testing the CodeBox-AI project using uv's native commands.

Build Commands

Environment Setup

Install all dependencies: uv sync
Install without dependencies: uv sync --no-dev
Install with specific extras: uv sync --extra "examples"

Running the Application

Standard Server

uv run -m codeboxai.main

MCP Server Options

Standalone MCP server (for Claude Desktop):
```
uv run mcp dev mcp_server.py
```

uv run mcp install mcp_server.py --name "CodeBox-AI"

Combined FastAPI + MCP server:
```
uv run run.py
```
MCP server only:
```
uv run run.py --mode mcp
```

Testing

Run all tests: uv run -m pytest
Run single test: uv run -m pytest tests/path/to/test.py::test_function_name -v
Run tests with coverage: uv run -m pytest --cov=codeboxai
Generate coverage report: uv run -m pytest --cov=codeboxai --cov-report=html

Linting and Code Quality

Run all code quality checks: uv run pre-commit run --all-files
Individual checks:
- Format code: uv run -m black .
- Check imports: uv run -m isort .
- Lint code: uv run -m flake8 codeboxai
- Type checking: uv run -m mypy codeboxai

Project Management

Add a dependency: uv add <package-name>
Remove a dependency: uv remove <package-name>
Lock dependencies: uv lock
View dependency tree: uv tree

Building and Publishing

Build package: uv run -m build
Publish package: uv publish

Code Style Guidelines

Imports

Group in order: stdlib, third-party, local
Sort alphabetically within groups
Use isort for automatic sorting

Formatting

Use black for code formatting with default settings (line length 120 as configured in pyproject.toml)
Ensure consistent indentation (4 spaces)

Type Annotations

Use type hints for all function parameters and return values
Use mypy for type checking

Read the full file on GitHub · 153 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.

yesterday First seen · 153 lines · 911 tokens per session scan A 0a21a6457805

Subscribe to this mod's changes

codebox-ai copilot-instructions.md is an instructions file published in the GitHub repository tomconte/codebox-ai (9 stars, last pushed 1y ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 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.

Languages Testing

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

buildNext

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

codebox-ai copilot-instructions.md