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 run-localgit 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/run-local)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/run-local"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/run-local/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/run-local"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/run-local.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00101 | $0.11033 |
| Opus 5.5 | $0.00040 | $0.04413 |
| Sonnet 5.5 | $0.00020 | $0.02207 |
| Haiku 4.5 | $0.00010 | $0.01103 |
Grade D, and why
run-local scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
In a **non-root devcontainer** the service start is elevated with `sudo -n` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
changes, so **never** `rm -rf theme-cache/ .mendix-cache/ deployment/` — clearing Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `until grep -q 'App is running' log; do sleep 2; done`, `curl` loops on 8080 | nothing — `--detach` returns when the app serves (or `run wait --ready`) | How it starts
The opening of the file, as written. The whole thing — 673 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 |
|---|---|
| 40-47 | Overview |
| 48-60 | When to Use This Skill |
| 61-116 | Usage |
| 117-129 | How apply is chosen |
| 130-195 | Prerequisites |
| 196-213 | The intended loop |
| 214-238 | Editing themes (SCSS) — rebuild, never clear caches |
| 239-265 | --watch waits for a write to finish before it builds |
| 266-294 | "My edit didn't show up" — stale process, not stale cache |
| 295-323 | Flags |
| 324-377 | Metrics and OpenTelemetry |
| 378-435 | Pages render in the browser |
| 436-453 | Pixel-perfect page loop |
| 454-474 | Debugging a server-side error |
| 475-495 | "Sign in failed" that is not about the password |
| 496-528 | The same licence also stops the app after a few hours |
| 529-608 | External browser preview (--hub) |
| 609-617 | Validation checklist |
| 618-657 | Constant values come from a configuration |
| 658-661 | Warm local dev loop (mxcli run --local [--watch] [--screenshot]) |
| 662-665 | External browser preview (mxcli run --hub <url> + mxcli tunnel-hub) |
| 666-669 | Tunnel-hub GitHub authentication (opt-in, gated on --github-oauth-client-id; absent = today's open hub) |
| 670-672 | Runtime metrics + settings passthrough (mxcli run --local --metrics / --runtime-setting Key=Value) |
Warm Local Dev Loop — mxcli run --local
Overview
mxcli run --local runs a Mendix app without Docker, keeping a
mxbuild --serve process and a standalone runtime hot so model changes apply in
~1 s instead of a ~30–60 s rebuild-and-restart. Use it as the fast inner loop when
iterating on an app; use mxcli docker run when you need the fully-rendered browser
client (see the limitation below).
When to Use This Skill
Use this when:
- You want the fastest edit → running-app loop for a Mendix 11.x project.
- You're driving the model programmatically (
mxcli exec/MDL) and want each change live immediately. - You're iterating on page design (the app renders in a real browser) or doing runtime/model/API/headless verification.
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 Changed · +1 lines 8b083e7bd0c4
- 5d ago Changed · +32 lines 0f03dc3b0255
- 10d ago Changed · +50 lines · +42 tokens per session c8ef8f68478f
- 12d ago Changed · +10 lines cc6591b0ed10
- 23d ago Changed · +2 lines 22e4715972aa
- 24d ago Changed · +16 lines 1ffc4309f24f
- 29d ago Changed · +2 lines 88d450d39913
- 1mo ago Changed · +6 lines scan C → D ec0332a8e9d5
- 1mo ago First seen · 554 lines · 59 tokens per session scan C 713ee30a432b
run-local is a skill published in the GitHub repository mendixlabs/mxcli (131 stars, last pushed yesterday), licensed Apache-2.0. It adds 101 tokens to every session and 11,033 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hatch3r-reliability-verify
Reliability verification gate before declaring an agent-produced service done — SLO defined, kill switch, timeouts, retries, probes, runbook, staged rollout.
hatch3r-scalability-verify
Scalability verification gate before commit/release — stateless-handler ratio, back-pressure patterns, idempotency-key adoption, queue-based offloading, pool sizing, bulkheads, load-test pass at target scale.
terraform-infrastructure
Structures, writes, and reviews Terraform infrastructure code. Covers module layout, remote state, workspace strategy, variable and secrets handling, CI plan/apply pipeline, naming conventions, and multi-region deployment patterns (provider aliases, per-region state, failover strategies), while delegating shared risk…
health-check-endpoints
Implements liveness and readiness health check endpoints following Kubernetes probe conventions. Covers response schema, dependency checks, Kubernetes probe config, and circuit breaker integration. Invoked when the user asks to add health checks, implement a /health endpoint, or set up Kubernetes probes.
serverless-architecture
Designs and implements serverless functions: function boundary design, runtime selection, event sources, IAM least privilege, configuration, observability, and cost estimation. Invoked when the user asks to build a serverless function, design a Lambda-based system, or move workloads to serverless.
create-terraform-module
Creates or updates AWS-oriented Terraform module structure and implementation scaffolding. Focuses on file layout, variable/output contracts, provider and version constraints, tagging standards, safe composition patterns, and address-stability guardrails.