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/code-reviewnpx skills add mendix/web-widgets --skill code-reviewgit 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 | $0.00045 | $0.03527 |
| Opus 5 | $0.00023 | $0.01764 |
| Sonnet 5 | $0.00009 | $0.00705 |
| Haiku 4.5 | $0.00005 | $0.00353 |
Grade A, and why
code-review 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review the PR diff against the standards in this repository. Read AGENTS.md for full repo context.
Before reviewing anything, run:
gh pr diff --name-only # build the exact list of changed files — only read these
gh pr checks # surface any failing CI checks before reading code
Only read files that appear in the diff output.
What to check on every PR
PR metadata
- Title: JIRA format
[XX-000]: descriptionor conventional commits (feat:,fix:, etc.) - Template adherence: lint/test run locally, new tests added, related PRs linked
- Multi-package PRs: validate each changed package separately
CI checks
Review the gh pr checks output before reading any files:
- Lint failing → Medium finding — paste the relevant error lines in the finding
- Unit tests failing → Medium finding — note the package and failing test file
- E2E tests failing → Medium finding — note the test name and failure reason
- All checks passing → add "All CI checks passed ✅" to the summary comment
Changelog (per changed package)
Version bumps happen in a separate dedicated PR — do not require or flag missing semver bumps.
If runtime code, public API, XML schema, or behavior changed:
- Require
CHANGELOG.mdentry (Keep a Changelog format) - Suggest:
pnpm -w changelog
If refactor/docs/tests-only: changelog entry not required — confirm with author.
Mendix-specific
AGENTS.md covers the core rules (canExecute, loading states, lowerCamelCase XML keys). Flag these additional review issues:
- XML changed but TS props not updated, or widget ID is not unique
EditableValueread without checking.status— can render stale/undefined dataActionValue.execute()called without checking.canExecutefirst
React
Flag these patterns — general React conventions are assumed known:
- Missing or wrong
useEffect/useMemo/useCallbackdeps; stale closures - Async effect sets state without a cleanup guard:
useEffect(() => { let active = true; (async () => { const data = await fetchData(); if (active) setState(data); })(); return () => { active = false; }; }, [fetchData]); - Array index used as list
key— requires a stable unique key - Props spread onto DOM nodes (
<div {...props}>) — strips unknown HTML attributes
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 · 334 lines · 45 tokens per session scan A 9667d18de920
code-review is a skill published in the GitHub repository mendix/web-widgets (40 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 3,527 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.