Borrowing it
Nothing to install: this file belongs to mendix/web-widgets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mendix/web-widgets/main/.agents/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/mendix/web-widgetsWrote 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/mendix/web-widgets/code-review)<a href="https://agentmods.dev/skills/mendix/web-widgets/code-review"><img src="https://agentmods.dev/badge/skills/mendix/web-widgets/code-review/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/mendix/web-widgets/code-review"><img src="https://agentmods.dev/badge/skills/mendix/web-widgets/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 52 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 53 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00045 | $0.03527 |
| Opus 5.5 | $0.00018 | $0.01411 |
| Sonnet 5.5 | $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 1mo 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 — 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.
- 1mo ago 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 5.5. 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
assess-quality
Audit a Mendix project against best practices for naming, security, performance, maintainability and architecture, and report a scored result. Use when asked to evaluate project quality, run a pre-go-live health check, or get oriented in an unfamiliar app.
sublime-detection-engineering
Load when the prompt's first line is Sublime detection proposal . Turns one confirmed malicious email into a tested Sublime MQL detection rule proposal: read what made the message malicious, check what already catches it, author MQL, validate the syntax, prove it matches the source message, backtest it over history…
code-review-expert
Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…