Outdated logo

Outdated

Organization
codewithmukesh
outdated

Dependency health report for .NET solutions: outdated NuGet packages, vulnerable versions, and commercial-license traps (MediatR, MassTransit, FluentAssertions, AutoMapper) — powered by the get_nuget_packages MCP tool. Invoke when: "outdated packages", "check dependencies", "stale packages", "package audit", "dependency health", "are my packages up to date", "license check", "vulnerable packages", "nuget audit".

Overview

Publishercodewithmukesh
Repositorydotnet-claude-kit
Skill nameoutdated
Stars
721
Forks
170
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by codewithmukesh on GitHub. Read the source before you install it.

Installation

Install the Outdated AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/codewithmukesh/dotnet-claude-kit.git /tmp/dotnet-claude-kit
mkdir -p .claude/skills
cp -r /tmp/dotnet-claude-kit/skills/outdated .claude/skills/outdated
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Outdated in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Outdated on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Outdated is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/outdated

What

A three-layer dependency health report:

  1. Inventory — every PackageReference per project, with TFMs and central package management awareness, via the get_nuget_packages MCP tool (no network, token-cheap).
  2. Staleness + vulnerabilities — current vs latest stable, and known CVEs, via the dotnet CLI.
  3. License screen — flags packages that moved to commercial licenses so an innocent dotnet outdated --upgrade doesn't silently change your legal position.

The output is a single prioritized table — vulnerabilities first, license traps second, staleness last — with a recommended action per row.

When

  • "check for outdated packages", "package audit", "dependency health"
  • Before a .NET version upgrade (pairs with /migrate Flow B)
  • After inheriting an unfamiliar codebase
  • Dependabot/NuGet audit warnings appeared and you want the full picture
  • Periodically on long-lived projects — quarterly is a good cadence

How

Step 1: Inventory (MCP, no network)

get_nuget_packages()                          -- whole solution
get_nuget_packages(projectFilter: "Api")      -- or one project

Returns per-project {Name, TargetFramework, Cpm, Packages: [{Id, Version}]}. Note Cpm: true — updates then belong in Directory.Packages.props, not the csproj. Flag mixed TFMs across projects while you're here.

Step 2: Staleness and vulnerabilities (CLI)

bash
dotnet list package --outdated
dotnet list package --vulnerable --include-transitive

Both need a successful restore first. If restore fails, fix that before auditing — a broken lock state makes version output unreliable.

Step 3: License screen

Check the inventory against the known commercial moves (full rationale in knowledge/package-recommendations.md):

PackageCommercial fromFree alternative
MediatR13+ (Lucky Penny, RPL)Mediator (martinothamar) — source-generated, MIT
MassTransit9+ (v8 Apache, patches end 2026 then EOL)Wolverine 6.x, or stay on v8 short-term
FluentAssertions8+ (v7 stays Apache, frozen)xUnit built-in Assert (kit default), Shouldly, AwesomeAssertions
AutoMapper15+ (Lucky Penny)Manual mapping (kit default) or Mapperly (MIT)

A license flag fires when the project is on the free major and a naive "update all" would cross the boundary — that is the trap this step exists for.

Step 4: Report

One table, priority-ordered:

PriorityMeaningAction
VULNERABLEKnown CVE in current versionUpdate now, test, deploy
LICENSENext major crosses a commercial boundaryPin below boundary or plan migration
MAJORBehind a major (breaking changes likely)One at a time, release notes first
MINOR/PATCHRoutine driftBatch patches; minors one at a time

Step 5: Act (optional)

Offer to execute updates via /migrate Flow C — one package at a time, dotnet build && dotnet test between each. Never batch major updates: batched failures are unattributable.

MCP Tools Used

  • get_nuget_packages — inventory, CPM detection, TFM audit
  • get_diagnostics — verify the solution still compiles clean after updates

Example

User: /outdated

Claude: Inventorying packages (get_nuget_packages)...
  3 projects, CPM enabled (Directory.Packages.props), all net10.0.

  Checking versions and CVEs...

  | Package                  | Current | Latest  | Priority   | Action                          |
  |--------------------------|---------|---------|------------|---------------------------------|
  | System.Text.Json (trans.)| 10.0.2  | 10.0.10 | VULNERABLE | Update now (CVE-2026-XXXX)      |
  | MassTransit              | 8.3.0   | 9.1.2   | LICENSE    | v9 is commercial. Stay on v8    |
  |                          |         |         |            | (EOL end 2026) or plan Wolverine|
  | Serilog.AspNetCore       | 9.0.0   | 10.0.0  | MAJOR      | Update alone, check sink compat |
  | FluentValidation         | 12.0.1  | 12.1.1  | PATCH      | Batch with other patches        |

  1 vulnerability, 1 license trap, 1 major, 1 patch.
  Want me to apply these via /migrate Flow C?

Related

  • /migrate — Flow C executes the updates this report recommends
  • knowledge/package-recommendations.md — vetted packages + licensing detail
  • knowledge/mediatr-to-mediator-migration.md — step-by-step MediatR exit
  • /verify — full pipeline after applying updates

Frequently asked questions

What does the Outdated AI skill do?

Dependency health report for .NET solutions: outdated NuGet packages, vulnerable versions, and commercial-license traps (MediatR, MassTransit, FluentAssertions, AutoMapper) — powered by the get_nuget_packages MCP tool. Invoke when: "outdated packages", "check dependencies", "stale packages", "package audit", "dependency health", "are my packages up to date", "license check", "vulnerable packages", "nuget audit".

Why use Outdated on TypingMind?

Because you install it once and use it with any model. Outdated is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Outdated in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/codewithmukesh/dotnet-claude-kit/tree/main/skills/outdated. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Outdated?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Outdated?

As many as you like. As long as a model supports skills, you can use Outdated with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Outdated AI skill free?

Yes. It is published on GitHub by codewithmukesh under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇