rm-mcp copilot-instructions.md

rm-mcp copilot-instructions.md is an instructions file for GitHub Copilot from wavyrai/rm-mcp. It costs 2,072 tokens per session, scanned A, original, MIT.

Contribution instructions for rm-mcp, a Python server that gives AI assistants access to reMarkable tablet data. They define the Git workflow, dependency commands, and test commands.

In plain words
What is it for?
Use them when developing, testing, or submitting changes to the rm-mcp repository.
Why use it?
They prevent direct changes to the protected main branch and keep dependency installation and testing consistent across contributors.

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/wavyrai/rm-mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/wavyrai/rm-mcp

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 rm-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wavyrai/rm-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/wavyrai/rm-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/wavyrai/rm-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/wavyrai/rm-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,072 This file is loaded in full into every session.
When invoked 2,072 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 $0.02072 $0.02072
Opus 5 $0.01036 $0.01036
Sonnet 5 $0.00414 $0.00414
Haiku 4.5 $0.00207 $0.00207

Measured 4d ago against content hash 93d0380d80db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rm-mcp 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 4d 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 · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions for rm-mcp

Project Overview

This is an MCP (Model Context Protocol) server that provides access to reMarkable tablet data. It's a Python project using FastMCP.

Git Workflow

Always work on feature branches and submit PRs. Never push directly to main.

# Create a feature branch
git checkout -b feature/my-feature

# After making changes, push and create PR
git push origin feature/my-feature
# Then create PR via GitHub

Branch protection is enabled on main - all changes must go through pull requests with passing CI checks.

Package Management

Always use uv for all package management operations.

# Install dependencies
uv sync

# Install with dev dependencies
uv sync --extra dev

# Add a new dependency
uv add <package>

# Add a dev dependency
uv add --dev <package>

Never use:

  • pip install directly
  • pip freeze
  • poetry

Running Tests

Always run tests with:

uv run pytest test_server.py -v

For specific test patterns:

# Run specific test class
uv run pytest test_server.py -v -k "TestClassName"

# Run with coverage
uv run pytest test_server.py -v --cov=server

# Skip slow tests if any
uv run pytest test_server.py -v -m "not slow"

Important: Tests use pytest-asyncio for async testing. All async tests should use the @pytest.mark.asyncio decorator.

Building & Running

# Run the MCP server directly
uv run python server.py

# Interactive setup (one-time)
uv run python server.py --setup

# Run as installed package
uv run rm-mcp

Code Quality

Before committing, always run:

# 1. Lint code (REQUIRED - CI will fail without this)
uv run ruff check .

# 2. Check formatting (REQUIRED - CI will fail without this)
uv run ruff format --check .

# 3. Run tests (REQUIRED - CI will fail without this)
uv run pytest test_server.py -v

Fix issues automatically:

# Fix lint issues
uv run ruff check . --fix

# Fix formatting
uv run ruff format .

Read the full file on GitHub · 269 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. 4d ago First seen · 269 lines · 2,072 tokens per session scan A 93d0380d80db

Subscribe to this mod's changes

rm-mcp copilot-instructions.md is an instructions file published in the GitHub repository wavyrai/rm-mcp (20 stars, last pushed 10d ago), licensed MIT. It adds 2,072 tokens to every session, about $0.0104 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 2026-08-30.