legacy-modernization-assistant.USAGE

A review agent for older .NET software that creates a step-by-step modernization roadmap. Modernization means improving or replacing aging technology gradually instead of rewriting everything at once.

In plain words
What is it for?
Use it to assess a legacy .NET codebase, plan a move to modern .NET, untangle a monolith, or identify work involving packages, data access, dependency injection, asynchronous code, and testing.
Why use it?
It helps identify outdated .NET Framework dependencies and decide what to change first based on risk and value, avoiding an unplanned large rewrite.

Agent

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 agents/stefanthecode/dotnet-ai-toolkit/legacy-modernization-assistant.usage
Clone the repo
git clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 413 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00413
Opus 5 $0.00000 $0.00206
Sonnet 5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00041

Measured 2d ago against content hash 01e5eaeb648b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

legacy-modernization-assistant.USAGE 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.

agents/legacy-modernization-assistant.USAGE.md · 17 lines

What it actually says

How to use — Legacy Modernization Assistant (agent)

What it is. An agent that assesses a legacy .NET codebase and produces a pragmatic, incremental modernization roadmap (strangler-fig, not big-bang) — platform, architecture, DI, async, testability — sequenced by risk and value.

When to reach for it. Modernizing legacy code, migrating off .NET Framework, or "where do I even start with this old codebase".

How to use it. Point it at the codebase (path or GitHub URL). Example prompts:

  • "Assess this legacy app and give me a modernization roadmap."
  • "We're on .NET Framework — how do we move to modern .NET incrementally?"
  • "Where do I start untangling this monolith?"

Get the best out of it. Decide the destination with it first — consolidate on .NET Framework 4.8 (modern tooling, same runtime) or port to modern .NET — because that changes which blockers matter. It runs a concrete .NET Framework blocker scan (System.Web, WCF, Remoting, BinaryFormatter, packages.config, classic csproj) and then hands the actual edits to the right skill: legacy-package-migrator (packages.config → Central Package Management), adonet-data-access-auditor (classic ADO.NET), winforms-maintainer (WinForms fixes), plus dotnet-upgrade-agent, modular-monolith-generator, test-coverage-gap-finder, and async-await-auditor.

Try it on the sample. examples/legacy-pack/ ships a deliberately-broken .NET Framework solution — point the agent at it and compare against examples/legacy-pack/VALIDATION-REPORT.md.

Won't do. It won't recommend a big-bang rewrite unless there's strong justification — incremental is the default. It plans and sequences; the skills make the edits, one project per PR.

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 · 17 lines · 0 tokens per session scan A 01e5eaeb648b

Subscribe to this mod's changes

legacy-modernization-assistant.USAGE is an agent published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 413 tokens. 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.