git-notes-memory copilot-instructions.md

A set of instructions that helps GitHub Copilot work consistently on the git-notes-memory-manager Python project. It describes the project, its folder structure, coding rules, testing practices, and required tools.

In plain words
What is it for?
It is for guiding changes in a Python 3.12+ project, including type hints, uv package management, Ruff formatting and linting, mypy checks, pytest tests, and Bandit security scans.
Why use it?
It gives Copilot project-specific context so its code suggestions follow the repository's conventions and quality checks.

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/zircote/git-notes-memory/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/zircote/git-notes-memory

Made for: GitHub Copilot.

Per session 634 This file is loaded in full into every session.
When invoked 634 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 $0.00634 $0.00634
Opus 5 $0.00317 $0.00317
Sonnet 5 $0.00127 $0.00127
Haiku 4.5 $0.00063 $0.00063

Measured yesterday against content hash 7cfa3114874e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-notes-memory 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 · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

git-notes-memory-manager - Copilot Instructions

This file provides context to GitHub Copilot for better code suggestions.

Project Overview

git-notes-memory-manager is a Python project for managing memory and context using git notes.

Python Guidelines

  • Use Python 3.12+ features and syntax
  • Type hints are required for all functions and methods
  • Use uv for package management (NOT pip)
  • Follow ruff formatting and linting rules
  • Use mypy for static type checking (strict mode preferred)
  • Use pytest for testing with high coverage (80% minimum)
  • Use bandit for security scanning

Code Style

  • Write clean, readable, maintainable code
  • Prefer explicit over implicit
  • Keep functions small and focused
  • Add comments only when necessary (code should be self-documenting)
  • Use descriptive names for variables and functions
  • Follow PEP 8 naming conventions:
    • snake_case for functions and variables
    • PascalCase for classes
    • UPPER_CASE for constants

Project Structure

src/
  git_notes_memory_manager/
    __init__.py
    ...
tests/
  __init__.py
  test_*.py
  conftest.py

Testing Patterns

  • Write tests for new functionality
  • Aim for high test coverage (80% minimum)
  • Test edge cases and error conditions
  • Use meaningful test names that describe the expected behavior
  • Use pytest fixtures for common setup
  • Prefer parametrized tests for testing multiple inputs
  • Mock external dependencies appropriately

Example test structure:

import pytest
from git_notes_memory_manager import SomeClass

class TestSomeClass:
    def test_method_returns_expected_value(self):
        """Test that method returns expected value for valid input."""
        obj = SomeClass()
        result = obj.method("input")
        assert result == "expected"

    def test_method_raises_on_invalid_input(self):
        """Test that method raises ValueError for invalid input."""
        obj = SomeClass()
        with pytest.raises(ValueError):
            obj.method(None)

Read the full file on GitHub · 109 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. yesterday First seen · 109 lines · 634 tokens per session scan A 7cfa3114874e

Subscribe to this mod's changes

git-notes-memory copilot-instructions.md is an instructions file published in the GitHub repository zircote/git-notes-memory (4 stars, last pushed 8mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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.