UKHO.GitHubCopilot.ToolKit copilot-instructions.md

Repository-wide guidance for writing reusable Copilot instructions, prompts, templates, documentation, and related project assets.

In plain words
What is it for?
It guides updates to repository instructions and reusable agent materials, including how to treat AGENTS.md and lessons.md.
Why use it?
It helps keep guidance clear, broadly applicable across Microsoft projects, and free from assumptions tied to one technology or repository.

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/ukho/ukho.githubcopilot.toolkit/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKit

Made for: GitHub Copilot.

Per session 1,049 This file is loaded in full into every session.
When invoked 1,049 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 $0.01049 $0.01049
Opus 5 $0.00524 $0.00524
Sonnet 5 $0.00210 $0.00210
Haiku 4.5 $0.00105 $0.00105

Measured yesterday against content hash db394eb25075, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

UKHO.GitHubCopilot.ToolKit 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-instructions.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

Overview

These instructions standardize how Copilot-related assets are authored and maintained in this repository. They are intended for any change that touches instructions, prompts, templates, supporting documentation, or related repository guidance.

Scope

Applies to: **/*

General Guidelines

  • Encourage established design and documentation principles such as clarity, separation of concerns, explicit dependencies, and reusable guidance.
  • Prefer technology guidance that is applicable across Microsoft projects unless a file is explicitly scoped to a narrower stack or workflow.
  • Keep repository assets adaptable so teams can reuse them in different Microsoft project contexts without inheriting assumptions from one specific solution.
  • Treat ./AGENTS.md as the repository-level operating policy for agent execution style and ./lessons.md as the durable record of stable repository learnings.

Instructions

MUST

  • Keep instructions, prompts, templates, and examples neutral enough to apply across Microsoft projects unless a file explicitly targets a narrower technology, framework, or workflow.
  • Ground Microsoft-technology guidance in authoritative Microsoft documentation when practical, and periodically re-validate repository instruction files against those sources.
  • Reuse and extend existing instructions, prompts, templates, and agents when they already cover the needed pattern closely enough, instead of creating near-duplicate repository assets.
  • Use placeholders, examples, and workflow descriptions that describe patterns rather than repository-specific implementations.
  • Keep documentation about repository workflows at the top level under docs/ when the guidance is intended for reuse across multiple work packages or teams.
  • Review ./AGENTS.md when creating or updating reusable agents, prompts, instructions, templates, or workflow documentation so the repository operating style stays consistent.
  • Update ./AGENTS.md when a stable repository-wide execution pattern or operating constraint emerges that should guide future agent behavior.
  • Update ./lessons.md when implementation, validation, or maintenance work reveals a stable lesson that future contributors should not need to rediscover.
  • For new or existing projects that begin using this repository workflow, create the wiki baseline first, then review .github/copilot-instructions.md and .github/instructions/*.instructions.md, identify uncovered areas, and add any missing scoped instruction files before creating work-package documentation.
  • Treat docs/wiki/ as the current project source of truth for Copilot-assisted workflow decisions once the wiki baseline exists.
  • In prompts, agents, templates, and workflow documentation that guide planning or project updates, require contributors to review the relevant wiki pages before drafting plans, requirements, specifications, implementation changes, or workflow updates.
  • In prompts, agents, templates, and workflow documentation that guide planning or project updates, require contributors to update the affected wiki pages after changes are made so the wiki remains aligned with the current project state before the task is considered complete.
  • Do not draft docs/00x-work/ work packages unless explicitly requested.
  • When generating review reports in this repository, create a new report file instead of updating the existing report so prior report history remains visible.
  • Use lowercase model identifiers such as gpt-5.4 in agent and prompt files to match repository conventions.

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 1,049 tokens per session scan A db394eb25075

Subscribe to this mod's changes

UKHO.GitHubCopilot.ToolKit copilot-instructions.md is an instructions file published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,049 tokens to every session, about $0.0052 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