modernization-kit copilot-instructions.md

A set of Copilot instructions for modernizing legacy applications through a six-phase process. It treats modernization as improving architecture and workflows, not merely translating old code into a new language.

In plain words
What is it for?
Use it during legacy-application discovery, planning, redesign, and implementation, following the appropriate phase prompt and producing its required engineering deliverable.
Why use it?
It gives teams a staged method with human review between phases, reducing the risk of changing a legacy system without understanding its behavior or constraints.

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/burly-mingo/modernization-kit/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Burly-Mingo/modernization-kit

Made for: GitHub Copilot.

Per session 1,572 This file is loaded in full into every session.
When invoked 1,572 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 $0.01572 $0.01572
Opus 5 $0.00786 $0.00786
Sonnet 5 $0.00314 $0.00314
Haiku 4.5 $0.00157 $0.00157

Measured 3d ago against content hash 3b18cd048423, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

modernization-kit 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 3d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Application Modernization — Copilot Custom Instructions

Part of the Legacy Application Modernization Kit by Burly Mingo LLC

You are assisting with a legacy application modernization project. This workspace contains a structured, multi-phase methodology that produces real engineering deliverables through iterative collaboration between you and a human domain expert.

How to Use This

This methodology has 6 phases (0-5), each with a dedicated prompt file in .github/prompts/. Work through them in order:

  1. Open the prompt file for the current phase (e.g., @workspace /prompts/phase-0-discovery.prompt.md)
  2. Follow the instructions in that prompt to produce the phase deliverable
  3. The human reviews and corrects your output
  4. Move to the next phase only after human approval

The prompt files contain the detailed requirements for each phase. These instructions provide the principles and constraints that apply across all phases.

Non-Negotiable Principles

  1. Modernize, don't translate. Changing the language without rethinking the architecture is not modernization. Every legacy system has workflows that exist because of technical limitations that no longer apply. Find them. Fix them. Don't preserve them in a new language.

  2. Containers by default, not by dogma. Recommend containerized, cloud-agnostic deployment as the default. But if the organization is committed to a specific cloud and cloud-native services genuinely simplify their life, that's valid. Ask, respect the answer, document the trade-off.

  3. Buy vs. build at every decision point. For every component, ask: does a product (open source or commercial) do this better than we could build it? But know the audience — many enterprises require vendor support contracts, SLAs, and security attestations. Ask about open-source policy and procurement requirements early.

  4. AI-assisted, spec-driven development is the baseline. Estimates assume an experienced developer/architect using an AI IDE with structured workflow. Not vibe coding. Without experience or structured specs, AI multiplies chaos. If traditional development is planned, multiply timelines by 2.5-4x.

Read the full file on GitHub · 87 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. 3d ago First seen · 87 lines · 1,572 tokens per session scan A 3b18cd048423

Subscribe to this mod's changes

modernization-kit copilot-instructions.md is an instructions file published in the GitHub repository Burly-Mingo/modernization-kit (11 stars, last pushed 6mo ago), licensed MIT. It adds 1,572 tokens to every session, about $0.0079 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.