copilot-guide copilot-instructions.md

Contribution instructions for a Markdown-only guide to GitHub Copilot's customization and agent features. GitHub Copilot is an AI coding assistant, and the guide documents how developers can configure and use it.

In plain words
What is it for?
Use them when adding or updating Copilot documentation, examples, feature explanations, locations, and quick-reference summaries.
Why use it?
They keep the guide accurate, consistent, and easy to scan by requiring one source file, a fixed section structure, examples, and motivation for each feature.

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/nishanil/copilot-guide/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/nishanil/copilot-guide

Made for: GitHub Copilot.

Per session 679 This file is loaded in full into every session.
When invoked 679 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 $0.00679 $0.00679
Opus 5 $0.00340 $0.00340
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 2d ago against content hash 790b88dc56d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-guide 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

copilot-guide — Copilot Instructions

This repository is a comprehensive reference guide documenting every GitHub Copilot customization and agentic feature. Its single artifact is README.md.

What this repo is

  • Content type: Markdown documentation only — no source code, no build step, no tests
  • Audience: Developers who want to understand and use Copilot's customization and agentic features
  • Goal: Accurate, concise, and up-to-date descriptions of each feature with concrete examples

Contribution conventions

  • Keep all content inside README.md — do not split into separate pages
  • Use the existing section structure: Customization → Agentic → Platform → Community → Best Practices → Quick Reference → Further Reading
  • Every feature section must include:
    • A one-line summary
    • A > **When you need it:** callout explaining the motivation
    • A 📁 Location: line (where applicable)
    • A concrete code or config example (preferably inside a <details> block if it is long)
    • A two-column summary table at the end of the section
  • Use <details markdown> / <summary> blocks to keep examples collapsible and the page scannable (the markdown attribute is required for MkDocs rendering on GitHub Pages)
  • Feature names in prose should match their heading exactly (e.g. "Custom Instructions", "Copilot Coding Agent")
  • Link every external reference (docs, blog posts, repos) — no bare mentions without a URL

Style rules

  • Use **bold** for UI labels and key terms on first use in a section
  • Use backticks for file paths, CLI commands, and code values
  • Prefer concrete names over abstract ones: "RecipeShare" app examples are used throughout; keep new examples consistent with that project
  • Do not add emojis to prose; the ASCII-art diagram at the top and the section header emojis are intentional — don't add more
  • Keep the Quick Reference table in sync when adding or removing features

What not to change

  • Do not reorder the top-level sections
  • Do not remove or rename existing feature entries
  • Do not convert <details markdown> examples to inline code blocks — keeping them collapsible is intentional
  • Do not modify these structural HTML wrappers — they control GitHub Pages rendering:
    • <div align="center"> ... </div> (top header)
    • <div class="ascii-glance" markdown> ... </div> (At a Glance code block)
    • <div class="svg-glance"> ... </div> (SVG placeholder for Pages)
    • <div class="readme-toc" markdown> ... </div> (Table of Contents)
    • <p class="gh-pages-link"> ... </p> (Pages link, hidden on site)

Read the full file on GitHub · 48 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 · 48 lines · 679 tokens per session scan A 790b88dc56d6

Subscribe to this mod's changes

copilot-guide copilot-instructions.md is an instructions file published in the GitHub repository nishanil/copilot-guide (4 stars, last pushed 4mo ago), licensed MIT. It adds 679 tokens to every session, about $0.0034 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.

Related

Other instructions, from other repositories

Project Guidelines

VS Code extension project guidelines for GitHub Copilot Insights. Covers project shape, code style, VS Code extension rules, build and test, and repository discipline.

kasuken/vscode-copilot-insights · 835 tokens

Repo Validation Workflow

Use when: changing, validating, testing, or reviewing this VS Code extension repository. Covers npm compile, lint, test harness, Electron test caveats, and build output.

kasuken/vscode-copilot-insights · 265 tokens

github-copilot-superpowers copilot-agent.instructions.md

Instructions for kasuken/github-copilot-superpowers, covering copilot agent instructions, 🎯 instruction hierarchy, 📋 execution order vs priority, execution order (workflow sequence) and ⛔ mandatory response template (every request).

kasuken/github-copilot-superpowers · 2,285 tokens

github-copilot-superpowers subagents.instructions.md

Instructions for kasuken/github-copilot-superpowers, covering subagent instructions (ssot), terminology, agent role: orchestrator only, ⚠️ absolute rules (non-negotiable) and mcp delegation rules.

kasuken/github-copilot-superpowers · 1,913 tokens

github-copilot-superpowers taming-copilot.instructions.md

Prevent Copilot from wreaking havoc across your codebase, keeping it under control.

kasuken/github-copilot-superpowers · 499 tokens

github-copilot-superpowers task-direction-approval.instructions.md

Prevents unauthorized direction changes by requiring user approval before deviating from original requirements.

kasuken/github-copilot-superpowers · 247 tokens