explore

A project exploration command for inspecting the structure of a Mendix application, including modules, entities, microflows, and pages.

In plain words
What is it for?
It is for listing modules and entities, viewing element signatures and types, counting elements, or including system and marketplace modules.
Why use it?
It provides a quick map of an unfamiliar project and lets you focus on one module or choose how much detail to display.

Command for Claude Code

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 commands/mendixlabs/mxcli/explore
Clone the repo
git clone --depth 1 https://github.com/mendixlabs/mxcli

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 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 $0.00009 $0.00821
Opus 5 $0.00005 $0.00411
Sonnet 5 $0.00002 $0.00164
Haiku 4.5 $0.00001 $0.00082

Measured yesterday against content hash caa43ec36587, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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.

.claude/commands/mendix/explore.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore Project

Explore and understand the Mendix project structure.

Start Here: Project Structure Overview

All element names in the output are fully qualified (Module.Element). In VS Code terminals, these are clickable links — click any element name to open its MDL description.

-- Get a compact overview of the entire project (best first command)
SHOW STRUCTURE;

-- Module-level summary with element counts
SHOW STRUCTURE DEPTH 1;

-- Elements with signatures (default) — entities, microflows, pages, etc.
SHOW STRUCTURE DEPTH 2;

-- Full types and parameter names
SHOW STRUCTURE DEPTH 3;

-- Focus on a single module
SHOW STRUCTURE IN ModuleName;

-- Include system/marketplace modules
SHOW STRUCTURE DEPTH 1 ALL;

CLI equivalent:

mxcli structure -p app.mpr                  # depth 2 (default)
mxcli structure -p app.mpr -d 1             # counts only
mxcli structure -p app.mpr -d 3             # full types
mxcli structure -p app.mpr -m ModuleName    # single module
mxcli structure -p app.mpr -d 1 --all       # include system modules

Quick Commands

-- List all modules
SHOW MODULES;

-- List entities in a module
SHOW ENTITIES IN ModuleName;

-- Show entity definition
DESCRIBE ENTITY Module.EntityName;

-- List microflows
SHOW MICROFLOWS IN ModuleName;

-- Show microflow logic
DESCRIBE MICROFLOW Module.MicroflowName;

-- List pages
SHOW PAGES IN ModuleName;

-- List workflows
SHOW WORKFLOWS IN ModuleName;

-- Show workflow definition
DESCRIBE WORKFLOW Module.WorkflowName;

Catalog Queries

For more flexible searching, use catalog queries:

REFRESH CATALOG;

-- Find entities by name pattern
SELECT QualifiedName, AttributeCount
FROM CATALOG.ENTITIES
WHERE Name LIKE '%Customer%';

-- Find large microflows
SELECT QualifiedName, ActivityCount
FROM CATALOG.MICROFLOWS
WHERE ActivityCount > 10
ORDER BY ActivityCount DESC;

Code Search Commands

For deeper code navigation (requires REFRESH CATALOG FULL). Like structure output, qualified names in the results are clickable in VS Code terminals.

Read the full file on GitHub · 136 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 · 136 lines · 9 tokens per session scan A caa43ec36587

Subscribe to this mod's changes

explore is a command published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 9 tokens to every session and 821 once invoked, about $0.0000 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.