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/mendix/web-widgets/debug-widgetnpx skills add mendix/web-widgets --skill debug-widgetgit clone --depth 1 https://github.com/mendix/web-widgetsWhat 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 | $0.00037 | $0.01917 |
| Opus 5 | $0.00018 | $0.00958 |
| Sonnet 5 | $0.00007 | $0.00383 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
debug-widget 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 today.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Widget
Overview
Evidence-first debugging for Mendix pluggable widgets. You MUST reproduce the bug with Playwright before reading source code, and MUST verify the fix with Playwright before declaring success.
REQUIRED BACKGROUND: superpowers:systematic-debugging for general root-cause methodology.
Prerequisites
Before starting, confirm with the user:
- Test project running? The Mendix app must be live at
http://localhost:8080. Ask: "Is the Studio Pro project running?" - MX_PROJECT_PATH set? Needed for deploying the built widget. Ask if not provided.
- JIRA/bug description? Extract: widget package, symptom, reproduction steps.
Workflow
Phase 1: Reproduce
-
Identify the target from the bug report:
- Widget package (
combobox-web,datagrid-web, …) - Symptom type — see Bug Categories table below
- Reproduction steps from JIRA
- Widget package (
-
Find the page — see page-discovery.md
-
Write a diagnostic Playwright script that follows the JIRA reproduction steps and captures the symptom as a measurable assertion or console output diff.
See diagnostic-patterns.md for templates by bug category.
Save it as:
packages/pluggableWidgets/<widget>-web/e2e/<bug-id>-diagnostic.spec.js -
Run it:
cd packages/pluggableWidgets/<widget>-web npx playwright test e2e/<bug-id>-diagnostic.spec.js --headed -
Confirm reproduction:
- Script shows wrong values / assertion fails → proceed to Phase 2
- Script does NOT demonstrate the bug → fix the script (selectors, timing, page URL). Do NOT proceed to Phase 2 until the script confirms the symptom.
Phase 2: Analyze + Fix
Now you may read source code.
- Trace the reactive chain from DOM symptom to root cause.
See reactive-chain.md.
- Simple widgets (combobox, badge): React props → hooks → component render
- Complex widgets (datagrid, gallery): React props → Gate → MobX stores → Observer components
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 167 lines · 37 tokens per session scan A 6fa5c0ce020d
debug-widget is a skill published in the GitHub repository mendix/web-widgets (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,917 once invoked, about $0.0002 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 2026-09-01.
Other skills, from other repositories
sql-database-support
Guides classifying, gap-analyzing, and scaffolding support for a new SQL database in pREST (wire-compatible variants like TimescaleDB or new dialects). Use when adding database support, creating integration/ /, DIFFERENCES.md, adapters/ , per-DB docker-compose or GitHub workflows, or planning where config/app wiring…
cli-commands
MUST use when using the CLI, including debugging job failures and inspecting run history via wmill job.
native-trigger
Guidance for adding native trigger services to Windmill. Use when implementing or modifying native trigger integrations across the backend and frontend.
write-script-python3
MUST use when writing Python scripts.
migrate-design-prototype
Reproduce a Claude Design prototype or design handoff (HTML/CSS, .dc.html export, tokens, screenshots) inside a Mendix app: build the palette with mxcli theme create --from, then apply classes in pages with MDL. Use when given a design artefact and asked to make the app look like it.
raw-app
MUST use when creating raw apps.