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/manage-securitynpx skills add mendixlabs/mxcli --skill manage-securitygit 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 | $0.00052 | $0.03824 |
| Opus 5 | $0.00026 | $0.01912 |
| Sonnet 5 | $0.00010 | $0.00765 |
| Haiku 4.5 | $0.00005 | $0.00382 |
Grade A, and why
manage-security 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Management Skill
This skill covers Mendix security configuration via MDL: module roles, user roles, access control (microflows, pages, entities), project security settings, and demo users.
When to Use This Skill
Use when the user asks to:
- Set up security for a module or project
- Create or manage module roles / user roles
- Grant or revoke access to microflows, pages, or entities
- Configure project security level or demo users
- Review existing security configuration
Security Concepts
- Module Roles define permissions within a single module (e.g.,
Shop.Admin,Shop.Viewer) - User Roles aggregate module roles from multiple modules (e.g.,
AdministratorincludesShop.Admin+System.Administrator) - Access Rules control CRUD rights on entities per module role
- Microflow/Page Access controls which module roles can execute/view specific elements
- Project Security Level determines enforcement:
off,prototype, orproduction
The System-module ceiling — decide the role model around this FIRST
No project module can widen access to System.User, System.Workflow or
System.WorkflowUserTask. Access to System entities comes from the System
module's own roles, and a grant in your module cannot raise it. This is a design
constraint, not a detail: it decides what your screens can be, and finding it late
means rebuilding them (ako/mxcli-maintenance-2 designed a technician picker, built
it, tested it, and tore it out).
Both consequences are silent — the page renders, the data is simply missing, and
mx check and mxcli lint both pass:
| What you build | What a non-Administrator sees |
|---|---|
A combo box over System.User (e.g. "pick a technician") |
The current user only |
A grid over System.Workflow / System.WorkflowUserTask |
Empty |
Three ways around it, in order of preference:
- Record, don't pick. Target the task at a role, let whoever opens it do the work, and stamp who acted on completion — a plain association plus a denormalised name your own module owns, which every role can then read.
- A microflow data source. Microflows bypass entity access by default, so a page can show data the role cannot read directly.
- Split the page by role. Keep raw System grids on an Administrator-only page. Mendix hides a button to a page the user may not view, so the link simply does not appear.
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 · 438 lines · 52 tokens per session scan A eb10c2526613
manage-security is a skill published in the GitHub repository mendixlabs/mxcli (115 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,824 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
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…