assess-migration

A structured investigation of an existing application written in Java, .NET, Python, Node.js, PHP, or another technology, to judge how it could be moved to Mendix. Mendix is a platform for building business software with visual models.

In plain words
What is it for?
Use it to create a migration inventory, assess a legacy codebase, plan migration phases, and estimate the work involved.
Why use it?
It reveals the application's technology, data, integrations, and likely migration work before anyone starts rebuilding it.

Skill for Claude CodeCodex

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 skills/mendixlabs/mxcli/assess-migration
Any agent
npx skills add mendixlabs/mxcli --skill assess-migration
Clone the repo
git clone --depth 1 https://github.com/mendixlabs/mxcli

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,288 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 $0.00066 $0.03288
Opus 5 $0.00033 $0.01644
Sonnet 5 $0.00013 $0.00658
Haiku 4.5 $0.00007 $0.00329

Measured 2d ago against content hash 49073b65cb0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assess-migration 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.

.claude/skills/mendix/assess-migration/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migration Assessment: Investigating Non-Mendix Projects

This skill guides the investigation of existing non-Mendix applications to produce a structured migration assessment for Mendix.

When to Use This Skill

Use this skill when:

  • A user asks to analyze an existing project for migration to Mendix
  • Investigating a codebase in any technology (Java, .NET, Python, Node.js, PHP, etc.)
  • Producing a migration inventory or assessment report
  • Planning the scope and phases of a migration project

Investigation Process

Step 1: Identify the Technology Stack

Determine the application's technology stack by examining:

  • Build files (pom.xml, *.csproj, package.json, requirements.txt, Gemfile, composer.json)
  • Configuration files (application.properties, appsettings.json, web.config, .env)
  • Framework indicators (Spring Boot, ASP.NET, Django, Express, Laravel, Rails)
  • Database configuration (connection strings, ORM config, migration files)
  • Frontend framework (angular.json, next.config.js, Vue/React/Svelte indicators)

Step 2: Map the Data Model

Investigate and document all entities, their attributes, and relationships.

Where to look:

Technology Data Model Location
Java/Spring @entity classes, JPA annotations, Hibernate mappings
.NET/EF DbContext, entity classes, EF migrations
Django models.py files
Rails app/models/, db/schema.rb
Node.js Sequelize/TypeORM/Prisma models, Mongoose schemas
PHP/Laravel Eloquent models, migrations
Database-first SQL schema, stored procedures, views

Output format:

### data model

#### entities

| entity | attributes | type | Constraints | Mendix mapping |
|--------|-----------|------|-------------|----------------|
| Customer | id | long (auto) | PK | (auto-generated) |
| | name | string(200) | not null | string(200) |
| | email | string(200) | unique | string(200) |
| | creditLimit | decimal(10,2) | | decimal |
| | isActive | boolean | default true | boolean |
| | createdAt | datetime | | datetime |
| Order | id | long (auto) | PK | (auto-generated) |
| | orderNumber | string(50) | unique, not null | string(50) |
| | status | enum | | enumeration |
| | totalAmount | decimal | | decimal |

#### associations

| from | to | type | Mendix mapping |
|------|----|------|----------------|
| Order | Customer | Many-to-One | reference (Order → Customer) |
| Order | OrderLine | One-to-Many | reference (OrderLine → Order) |
| user | role | Many-to-Many | ReferenceSet |

#### enumerations

| Name | values | Used by |
|------|--------|---------|
| OrderStatus | PENDING, PROCESSING, COMPLETED, CANCELLED | Order.status |
| UserRole | ADMIN, MANAGER, user | User.role |

Read the full file on GitHub · 349 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. 2d ago First seen · 349 lines · 66 tokens per session scan A 49073b65cb0d

Subscribe to this mod's changes

assess-migration is a skill published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,288 once invoked, about $0.0003 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.