context-engineering copilot-instructions.md

A project instruction file for the context-engineering repository, covering its goals, structure, technology choices, testing expectations and documentation practices.

In plain words
What is it for?
Use it to guide changes in that project, including adding unit tests, handling expected and failure cases, and updating architecture documentation.
Why use it?
It gives a coding agent project-specific guidance when the repository’s own setup and standards are not obvious.

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/wmeints/context-engineering/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/wmeints/context-engineering

Made for: GitHub Copilot.

Per session 271 This file is loaded in full into every session.
When invoked 271 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 $0.00271 $0.00271
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured yesterday against content hash 8d0c3b7ed34c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-engineering 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/.github/copilot-instructions.md · 45 lines

What it actually says

Github Copilot Instructions

Follow these instructions when writing code or documentation for the project.

Project goals

TODO: Describe the goals of the project

Project Structure

TODO: Describe your project structure

  • Tip Are you using feature slicing or clean architecture?
  • Tip Where are projects located in the directory structure?
  • Tip What does each of the projects do in the solution?

Technology stack

TODO: Describe your technology stack

  • Tip How do the technologies map on the project structure?
  • Tip How are technologies used?

Testing the project

  • Always create unit-tests for components you introduce into the application.
  • After changing or introducing new logic make sure that the tests are updated to match the new situation.
  • Include at least the following types of test cases:
    • 1 test case for the expected use
    • 1 edge case
    • 1 failure case

Documenting the code

Make sure to document the code properly in the architecture documentation located at docs/architecture. We follow the arc42 template for structuring the architecture documentation.

When changing code, make sure to:

  • Document important structures in the building blocks view
  • Document important flows in the runtime view
  • Update the glossary with new terms introduced in the feature
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 · 45 lines · 271 tokens per session scan A 8d0c3b7ed34c

Subscribe to this mod's changes

context-engineering copilot-instructions.md is an instructions file published in the GitHub repository wmeints/context-engineering (37 stars, last pushed 8mo ago), licensed MIT. It adds 271 tokens to every session, about $0.0014 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.