ruff-mcp-server copilot-instructions.md

ruff-mcp-server copilot-instructions.md is an instructions file for GitHub Copilot from drewsonne/ruff-mcp-server. It costs 417 tokens per session, scanned A, original, MIT.

Project instructions for GitHub Copilot in a Python repository. They define where source code and tests belong and how tests and code should be written.

In plain words
What is it for?
Use them when adding Python code or pytest tests to the project, especially when following GIVEN/WHEN/THEN test sections, imports inside test functions, PEP 8, and Ruff linting.
Why use it?
They give code suggestions a shared structure and make testing and style expectations explicit. This reduces inconsistent examples and misplaced files.

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/drewsonne/ruff-mcp-server/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/drewsonne/ruff-mcp-server

Made for: GitHub Copilot.

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 ruff-mcp-server copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/drewsonne/ruff-mcp-server/copilot-instructions.svg)](https://agentmods.dev/instructions/drewsonne/ruff-mcp-server/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/drewsonne/ruff-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/drewsonne/ruff-mcp-server/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 417 This file is loaded in full into every session.
When invoked 417 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 $0.00417 $0.00417
Opus 5 $0.00209 $0.00209
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 3d ago against content hash cbd5e8e7fb9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruff-mcp-server 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 3d 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 · 55 lines

What it actually says

GitHub Copilot Instructions

These instructions guide GitHub Copilot to generate consistent, idiomatic code for this Python project.

🧪 Tests

  • Use pytest.
  • Follow the GIVEN / WHEN / THEN structure in all tests.
  • Use assert statements for validation.
  • Group related setup under # GIVEN.
  • The action being tested goes under # WHEN.
  • Assertions and expectations go under # THEN.
  • Always place imports inside test functions — this ensures proper load order and test isolation.

Example:

def test_user_creation():
    # GIVEN
    #     a user data payload
    from myapp.users import create_user
    user_data = {"name": "Alice", "email": "[email protected]"}

    # WHEN
    #     we create the user
    user = create_user(user_data)

    # THEN
    #     the user is stored with correct attributes
    assert user.name == "Alice"
    assert user.email == "[email protected]"

📦 Project Structure

  • Source code lives in the src/ directory.
  • Tests live in the tests/ directory, mirroring the source layout.

✅ Style & Linting

  • Follow PEP8.
  • Linting is enforced by Ruff.
  • Do not use assert in production code — raise exceptions instead.

🧩 Type Hints

  • The project must be fully typed.
  • Use Python type hints (str, int, Optional[...], etc.) in all functions, classes, and variables where applicable.
  • All public APIs must have complete type annotations.
  • Use mypy to enforce type checking.

💡 Docstrings

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. 3d ago First seen · 55 lines · 417 tokens per session scan A cbd5e8e7fb9b

Subscribe to this mod's changes

ruff-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository drewsonne/ruff-mcp-server (1 stars, last pushed 1y ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 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.