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.
npx agentmods add skills/mendixlabs/mxcli/custom-widgetsnpx skills add mendixlabs/mxcli --skill custom-widgetsgit clone --depth 1 https://github.com/mendixlabs/mxcliWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00101 | $0.05409 |
| Opus 5 | $0.00051 | $0.02704 |
| Sonnet 5 | $0.00020 | $0.01082 |
| Haiku 4.5 | $0.00010 | $0.00541 |
Grade A, and why
custom-widgets 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.
How it starts
The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom & Pluggable Widgets in MDL
Built-in Pluggable Widgets
GALLERY
Card-layout list with optional template content and filters.
gallery galleryName (
datasource: database from Module.Entity sort by Name asc,
selection: single | multiple | none,
DesktopColumns: 3,
TabletColumns: 2,
PhoneColumns: 1
) {
template template1 {
dynamictext title (content: '{1}', contentparams: [{1} = Name], rendermode: H4)
dynamictext info (content: '{1}', contentparams: [{1} = Email])
}
filter filter1 {
textfilter searchName (attribute: Name)
numberfilter searchScore (attribute: Score)
dropdownfilter searchStatus (attribute: status)
datefilter searchDate (attribute: CreatedAt)
}
}
templateblock -> mapped tocontentproperty (child widgets rendered per row)filterblock -> mapped tofiltersPlaceholderproperty (shown above list)selection: noneomits the selection property (default if omitted)DesktopColumns,TabletColumns,PhoneColumnscontrol responsive grid columns (default: 1 each, omit if default)- Children written directly under GALLERY (no container) go to the first slot with
mdlContainer: "template"
COMBOBOX
Two modes depending on the attribute type:
-- Enumeration mode (Attribute is an enum)
combobox cbStatus (label: 'Status', attribute: status)
-- Association mode (Attribute is an association)
combobox cmbCustomer (
label: 'Customer',
attribute: Order_Customer,
datasource: database Module.Customer,
CaptionAttribute: Name
)
- Engine detects association mode when
datasourceis present (hasDataSourcecondition) CaptionAttributeis the display attribute on the target entity- In association mode, mapping order matters: DataSource must resolve before Association (sets entityContext)
Charts (Mendix Charts.mpk)
Charts are pluggable widgets authored by their package id. Install Charts.mpk
into the project's widgets/ folder first (any Charts-based app has it); exec
auto-generates the .def.json.
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.
- yesterday First seen · 495 lines · 101 tokens per session scan A a33ca2605036
custom-widgets is a skill published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 101 tokens to every session and 5,409 once invoked, about $0.0005 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.
Other skills, from other repositories
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
systematic-debugging
Root-cause a bug already in front of you, instead of guessing at fixes. Use on triggers like "root cause this", "why is this failing", "debug systematically", "this test is flaky", "it works locally but not in CI", or when a fix attempt has already failed once. Enforces a phased evidence-first process before any code…