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 skills add mendixlabs/mxcli --skill write-layoutsgit 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/write-layouts)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/write-layouts"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/write-layouts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mendixlabs/mxcli/write-layouts"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/write-layouts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00072 | $0.04751 |
| Opus 5.5 | $0.00029 | $0.01900 |
| Sonnet 5.5 | $0.00014 | $0.00950 |
| Haiku 4.5 | $0.00007 | $0.00475 |
Grade A, and why
write-layouts 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.
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find it fast
sed -n '<from>,<to>p' SKILL.md one section rather than reading the file;
./mxcli syntax <topic> answers how do I write this for a fraction of either.
| lines | section |
|---|---|
| 30-135 | Do not edit Atlas_Core |
| 136-195 | Syntax |
| 196-235 | The four things only a layout has |
| 236-247 | Layout type, and why there is no native: flag |
| 248-269 | The layout class is load-bearing |
| 270-316 | Gotchas |
| 317-329 | Validate |
| 330-342 | What mxcli new scaffolds |
| 343-345 | Layouts (SHOW/DESCRIBE/CREATE [OR REPLACE] LAYOUT) |
CREATE LAYOUT — the frame a page is built on
A layout is the frame every page renders inside: the topbar, the navigation sidebar, and the hole the page's own content drops into. Until now it was the one document mxcli could not author, which put the topbar out of reach of MDL.
Do not edit Atlas_Core
Mendix's own documentation says it plainly: "Do not change the supplied layouts. Either create a separate module with the custom layouts, page templates, and building blocks or create your own." An Atlas layout lives in a Marketplace module, and a Marketplace update replaces the module wholesale — every local edit is gone, silently.
CREATE LAYOUT refuses a Marketplace module for that reason. Put your layout
in a module you own.
The usual starting point is a copy of an Atlas layout, and describe already
gives you one:
mxcli -p app.mpr -c "describe layout Atlas_Core.Atlas_Default" > mine.mdl
# edit the qualified name to your own module, then:
mxcli exec mine.mdl -p app.mpr
DESCRIBE LAYOUT emits re-executable MDL, so describe → rename → exec is the
copy operation. There is no COPY DOCUMENT verb and none is needed.
A copy is only as good as what MDL can spell. A widget describe cannot render
comes out as a comment ending -- NOT re-executable, and re-running the script
drops it. Measured on Atlas_Core.Atlas_SideBar: its two
Forms$SidebarToggleButton widgets do not survive the round trip, and an
image widget copied this way loses its image reference (CE0463 until
mxcli fix widgets, then "No image selected"). Read the describe output
before running it — the comments name exactly what will be lost. To change a
layout without that risk, use ALTER LAYOUT, which edits the stored document in
place and leaves everything it was not asked to touch alone.
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.
- 2d ago Changed · +31 lines · +14 tokens per session fc9c543473d3
- 5d ago Changed · +18 lines fa47b12cc154
- 15d ago Changed · +7 lines 5f4125b1d5f6
- 16d ago Changed 8e457c9b40b2
- 22d ago Changed · +26 lines d203d9f08438
- 24d ago Changed · +4 lines a4d9f9f34447
- 1mo ago Changed · +39 lines 31d683562a7a
- 1mo ago First seen · 221 lines · 58 tokens per session scan A b6166f64add6
write-layouts is a skill published in the GitHub repository mendixlabs/mxcli (131 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 4,751 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
workflow-creator
Create or update reusable Dynamic Workflow JavaScript files under .qwen/workflows. Use when the user asks to create, save, edit, or reuse a Dynamic Workflow, including requests started from the Web Shell Workflows page.