github-copilot-assets-library copilot-instructions.md

Repository instructions for a library of GitHub Copilot customisation files, including prompts, chat modes, instructions, and MCP server configurations. They describe the repository layout, asset types, style rules, and file checks.

In plain words
What is it for?
Maintaining Copilot assets, checking Markdown-based files, locating repository components, and following its documentation and validation conventions.
Why use it?
They give contributors shared guidance for editing a documentation and configuration repository that has no compiled application to build.

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/plagueho/github-copilot-assets-library/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/PlagueHO/github-copilot-assets-library

Made for: GitHub Copilot.

Per session 840 This file is loaded in full into every session.
When invoked 840 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 $0.00840 $0.00840
Opus 5 $0.00420 $0.00420
Sonnet 5 $0.00168 $0.00168
Haiku 4.5 $0.00084 $0.00084

Measured 2d ago against content hash 77e3bb2db46e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-copilot-assets-library 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 2d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This is a GitHub Copilot Assets Library that provides customization assets including Copilot Instructions, Prompt Files, Custom Chat Modes, and MCP Server configurations.

Core Commands

  • Documentation: Use README.md as the primary source - contains comprehensive asset descriptions
  • No build/test commands: This is a documentation/asset library with no compiled code
  • File validation: Ensure Markdown syntax is valid for .chatmode.md, .prompt.md and .instruction.md files

Repository Architecture

Major Components

  • .github/copilot-instructions.md - Repository-level Copilot instructions (n)
  • /prompts/ - Reusable prompt files for common tasks
  • /chatmodes/ - Custom chat modes with specialized instructions and tools
  • /instructions/ - Custom instruction files for Copilot
  • /mcp/ - Sample Model Context Protocol (MCP) server configurations for external integrations
  • .devcontainer/ - Development container for standardized environment

Key Asset Types

  • Prompt Files: Task-specific prompts (create specs, GitHub issues, code reviews)
  • Chat Modes: Specialized modes (expert engineers, planners, mentors, Azure modules)
  • MCP Servers: External integrations (Microsoft Docs, GitHub, Playwright, Giphy, Azure DevOps)

Style Rules

File Naming

  • Chat modes: [descriptive-name].chatmode.md
  • Prompts: [descriptive-name].prompt.md
  • Instructions: [descriptive-name].instructions.md
  • Use lowercase with hyphens for file names

Markdown Standards

  • Follow front matter YAML structure exactly as shown in examples
  • Use proper heading hierarchy (# ## ###)
  • Include description and tools array in chat mode front matter
  • Include mode and description in prompt file front matter

Content Guidelines

  • Precise Language: Use explicit, unambiguous instructions
  • Structured Format: Use headings, bullets, tables for clarity
  • No Boilerplate: Avoid generic advice, focus on specific guidance
  • Self-Contained: Each asset should be complete and context-independent

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 840 tokens per session scan A 77e3bb2db46e

Subscribe to this mod's changes

github-copilot-assets-library copilot-instructions.md is an instructions file published in the GitHub repository PlagueHO/github-copilot-assets-library (84 stars, last pushed 1mo ago), licensed MIT. It adds 840 tokens to every session, about $0.0042 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.