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.
npx agentmods add instructions/utensils/mcp-nixos/copilot-instructionsgit clone --depth 1 https://github.com/utensils/mcp-nixosWrote 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.
[](https://agentmods.dev/instructions/utensils/mcp-nixos/copilot-instructions)<a href="https://agentmods.dev/instructions/utensils/mcp-nixos/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/utensils/mcp-nixos/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.01510 | $0.01510 |
| Opus 5 | $0.00755 | $0.00755 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
mcp-nixos 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for MCP-NixOS
Project Context
MCP-NixOS is a Model Context Protocol (MCP) server providing real-time information about NixOS packages, options, Home Manager, nix-darwin, and flakes. The server prevents AI hallucination by querying official APIs and documentation sources.
Architecture: Modular FastMCP 4.x async server exposing only 2 MCP tools (consolidated from 17 in v1.0 to reduce context window usage).
Key Modules:
mcp_nixos/server.py- MCP tools, routing, and entry pointmcp_nixos/sources/- Per-source modules (nixos, home_manager, darwin, flakehub, wiki, etc.)mcp_nixos/config.py- Configuration constantsmcp_nixos/caches.py- Cache implementationsmcp_nixos/utils.py- Shared utilities
Core Development Workflows
Build & Test Commands (Nix Flake Required)
nix develop # Enter dev shell with Python venv
run # Start MCP server
run-tests # Run all tests with coverage
lint # Check code with ruff
format # Format code with ruff
typecheck # Run mypy type checker
build # Build package distributions
Python-only alternative: uv pip install -e ".[dev]" then uv run mcp-nixos
Testing Strategy
- Markers:
@pytest.mark.unitor@pytest.mark.integration(defined in tests/conftest.py) - Integration tests hit real APIs - no mocks, use
@pytest.mark.flaky(reruns=3)for flaky network calls - Async everywhere: pytest-asyncio auto mode enabled, function-scoped event loops
- Coverage: Always enabled (
--cov=mcp_nixos) - Output validation: All tests verify plain text output (no XML/JSON leakage)
Run specific tests: pytest tests/test_server.py::test_nixos_search -v
Project-Specific Patterns
1. Plain Text Output Only
Critical: All MCP tool responses must return plain text formatted for LLM consumption. Never return raw JSON or XML to users.
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 Changed 14155362f8b0
- 6d ago First seen · 128 lines · 1,510 tokens per session scan A 83e063cf698c
mcp-nixos copilot-instructions.md is an instructions file published in the GitHub repository utensils/mcp-nixos (823 stars, last pushed yesterday), licensed MIT. It adds 1,510 tokens to every session, about $0.0076 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.
Other instructions, from other repositories
postgres-mcp-server copilot-instructions.md
Copilot instructions for satish-kori-27/postgres-mcp-server: Ensure that the previous step has been marked as completed. Call project setup tool with projectType parameter. Run scaffolding command to create project files and folders. Use '.' as the working directory. If no appropriate projectType is available, search…
awesome-openclaw-usecases-zh AGENTS.md
Instructions for AlexAnys/awesome-openclaw-usecases-zh, covering agents.md, 仓库定位, 你正在用哪个 agent？（quick start）, openclaw（原生） and hermes（nous research）.
agentor copilot-instructions.md
Instructions for CelestoAI/agentor: Read AGENTS.md in the repository root. It is the single source of contributor guidance for this project — architecture, development setup, code style, testing, and CI — and applies to Copilot exactly as written.
latchkey AGENTS.md
AGENTS.md instructions for imbue-ai/latchkey: For information about the high-level goal and motivations, see README.md.
claudekit AGENTS.md
Instructions for duthaho/claudekit, covering agents.md, what this is, build, test, run, architecture and conventions & gotchas.
med-paper-assistant AGENTS.md
AGENTS.md instructions for u9401066/med-paper-assistant, covering agents.md - vs code copilot agent 指引, 核心價值：逐步多輪演進, 運行模式, 檔案保護（normal/research） and 專案規則.