Borrowing it
Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. 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/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-web-CodeReview/SKILL.mdgit clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-DelphiWrote 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/gabrielondelphi/claude-tools-for-delphi/light-web-codereview)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-web-codereview"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-web-codereview/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/gabrielondelphi/claude-tools-for-delphi/light-web-codereview"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-web-codereview.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 | $0.00051 | $0.00644 |
| Opus 5 | $0.00026 | $0.00322 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
light-web-CodeReview 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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-web-CodeReview — HTML / CSS / JS Review
This is a thin launcher. Your only job is to resolve the input scope and launch the
light-web-CodeReview agent. You do NOT review the code yourself.
Step 1 — Resolve the input
The argument is in $args. The user may pass one or more web files, a folder, or nothing.
Build the review set:
- One or more explicit file paths (
.html,.htm,.css,.js,.mjs) → use them as-is. - A folder → Glob
<folder>/**/*.{html,htm,css,js,mjs}for the file list. If the result is large (more than ~25 files), tell the user the count and ask whether to review all or narrow the scope. - No argument → review the web files with uncommitted changes. Run
git status --porcelainand keep the.html/.css/.jsfiles it lists. The agent reviews recently changed code by default, so this matches its intent. If that list is empty, ask the user which file or folder to review.
Print the resolved review set as a short list before launching.
Step 2 — Launch the agent
Call the Agent tool with subagent_type: "light-web-CodeReview". Pass it the full
review set in one prompt — HTML, CSS, and JS together when present, so it can cross-reference
(e.g. unused CSS selectors against the HTML, missing handlers against the markup).
Relay its final report to the user.
Step 3 — Summary
Print a short summary (the agent's full report is already in the transcript — do not re-paste it): how many files reviewed and how many issues by severity / category.
Rules
- You do not review code. Resolving the scope, launching the agent, and summarizing is your entire job. The agent does the review.
- Recently changed code by default. Do not expand to the whole codebase unless the user explicitly asks.
Claude Tools for Delphi — © 2026 Gabriel Moraru, gabrielmoraru.com — MPL-2.0
Autopilot for Delphi — Claude clicks, types and reads inside your running VCL / FMX app.
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.
- 5d ago Changed · +2 lines b154cb9a6b00
- 9d ago First seen · 53 lines · 51 tokens per session scan A 2b848b3c9f28
light-web-CodeReview is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 51 tokens to every session and 644 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
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
code-review-web
Use when reviewing web frontend code — HTML, CSS, JSX, or browser-targeted JavaScript. Enforces accessibility (WCAG AA, aria labels, focus management), XSS prevention (innerHTML, dangerouslySetInnerHTML), performance (layout thrash, CLS, lazy loading), CSS design tokens, form labeling, and event listener cleanup.…
ia-tailwind-css
Tailwind CSS v4 patterns: CSS-first config, utility classes, component variants, v3 migration. Use when styling with Tailwind, configuring @theme tokens, using tailwind-variants/CVA, migrating v3 to v4, or fixing Tailwind styles and dark mode.
tailwind-css
Tailwind CSS v4 patterns: CSS-first config, utility classes, component variants, v3 migration. Use when styling with Tailwind, configuring @theme tokens, using tailwind-variants/CVA, migrating v3 to v4, or fixing Tailwind styles and dark mode.
motion-review-gate
Review frontend motion and animation code before shipping, with strict checks for purpose, frequency, easing, duration, transform origin, interruptibility, GPU-safe properties, reduced-motion support, and hover behavior. Use when a diff touches transitions, keyframes, Framer Motion, Lottie, drawers, popovers, toasts…