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/javascript-actionsnpx skills add mendixlabs/mxcli --skill javascript-actionsgit 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 | $0.00053 | $0.01509 |
| Opus 5 | $0.00026 | $0.00754 |
| Sonnet 5 | $0.00011 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
javascript-actions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mendix JavaScript Actions Skill
Guidance for creating, calling, and dropping JavaScript actions in Mendix projects with MDL. JavaScript actions hold custom client-side logic and are called from nanoflows (not microflows — those use Java actions).
When to Use This Skill
- Adding client-side behaviour (browser/native APIs, DOM,
fetch, geolocation, …) - Logic that must run on the device rather than the server
- Calling an existing JavaScript action from a nanoflow
- Wrapping a marketplace/native capability exposed as a JS action
For server-side custom code, use Java actions instead (see java-actions).
Overview
A JavaScript action is two things on disk:
- The model unit (
JavaScriptActions$JavaScriptAction). - A source file
javascriptsource/<Module>/actions/<Name>.jscontaining an exportedasync function.
CREATE JAVASCRIPT ACTION writes both. The MDL body you provide becomes the
function body (between the BEGIN USER CODE / END USER CODE markers), so it
normally returns a Promise.
Syntax
CREATE [OR MODIFY] JAVASCRIPT ACTION Module.Name ( parameters )
RETURNS type
[EXPOSED AS 'caption' IN 'category']
[PLATFORM Web | Native | Hybrid | All] -- default Web
AS $$
<javascript>
$$;
DROP JAVASCRIPT ACTION Module.Name;
Clause order is fixed: returns, then exposed as, then platform, then as.
AS $$ ... $$is mandatory. Omitting the body causesno viable alternative at input '...'. Use a stub:AS $$ return Promise.resolve(false); $$.PLATFORMdefaults toWeb. UseNative,Hybrid, orAllto widen.OR MODIFYupdates an existing action in place (UUID preserved); without it, a duplicate name is an error (use create or modify to overwrite).
Parameter types
Same type system as Java actions:
- Primitives:
String,Integer,Long,Decimal,Boolean,DateTime - Entity:
Module.EntityName· List:List of Module.EntityName - Enumeration:
ENUM Module.EnumName - Type parameter (generics): declare
EntityType: ENTITY <pEntity>, then use the barepEntityfor instance parameters - Append
NOT NULLto mark a parameter required.
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 · 193 lines · 53 tokens per session scan A c3a059a56cf3
javascript-actions is a skill published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,509 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.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…
kb-builder
Build an Obsidian-compatible knowledge base from public web sources using the TinyFish CLI. Use this skill when a user wants a builder-grade markdown knowledge base on a technical topic, asks for a structured research vault, or wants a topic compiled from live public sources into interlinked markdown files. Supports…
tinyfish-social-listening
Monitor brand mentions, sentiment, and industry chatter across the web using TinyFish Search and Fetch. Use when a user asks to track what people are saying about a brand, product, or topic, run social listening, or get a pulse on public perception. If the user already named the target, proceed directly. Default time…