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/download-marketplace-contentnpx skills add mendixlabs/mxcli --skill download-marketplace-contentgit clone --depth 1 https://github.com/mendixlabs/mxcliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mendixlabs/mxcli/download-marketplace-content)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/download-marketplace-content"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/download-marketplace-content.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.05390 |
| Opus 5 | $0.00026 | $0.02695 |
| Sonnet 5 | $0.00010 | $0.01078 |
| Haiku 4.5 | $0.00005 | $0.00539 |
Grade A, and why
download-marketplace-content 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Download, Install and Update Marketplace Content
This skill covers the full lifecycle of Mendix Marketplace content (modules and widgets) from the command line: discover → download → install → check for local edits → update. These are CLI commands, not MDL statements.
When to Use This Skill
- User wants to add a marketplace module or widget to a project
- User wants to upgrade a module that is already installed
- User asks whether a marketplace module has been edited locally, or what an upgrade would overwrite
- User asks to download a specific
.mpk(e.g. for CI, or to import in Studio Pro) - User asks which versions of a marketplace item are compatible with their Mendix version
- User reports
CE0463orCE6087right after installing or updating a module
Prerequisites: Authenticate
Marketplace access needs a Mendix Personal Access Token (PAT), created at https://user-settings.mendix.com/ (Developer Settings → Personal Access Tokens).
mxcli auth login # interactive prompt for the PAT
mxcli auth login --token <PAT> # non-interactive (CI)
export MENDIX_PAT=<PAT> # or via environment
mxcli auth status # verify it validates
Credentials are stored at ~/.mxcli/auth.json (mode 0600).
Module installs also need the mxbuild toolchain for the project's Mendix version:
mxcli setup mxbuild -p app.mpr.
Step 1 — Discover
mxcli marketplace search "database connector" # find content by name/publisher
mxcli marketplace info 2888 # details for a content id
mxcli marketplace versions 2888 # available versions
mxcli marketplace versions 2888 --min-mendix 10.24.0 # compatible versions only
The numeric content id (from search/info) is what every other command takes.
Search caching. The Content API has no server-side search, so the first search
fetches the whole catalog (tens of seconds) and caches it under ~/.mxcli/ for 24h;
later searches are instant. If the first search seems slow, it is scanning the catalog —
let it finish. Pass --refresh to bypass the cache (e.g. for a brand-new module). If
search returns nothing, the content may be private or listed under a different name —
look it up by id with info <id> (ids come from the marketplace URL
.../link/component/<id>).
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.
- 5d ago First seen · 417 lines · 52 tokens per session scan A e3f1e723aba9
download-marketplace-content is a skill published in the GitHub repository mendixlabs/mxcli (116 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 5,390 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
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.