light-web-CodeReview

light-web-CodeReview is an agent for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 59 tokens per session (764 once invoked), scanned A, original, MPL-2.0.

A code-review agent for recently changed HTML, CSS, and JavaScript. It checks correctness, formatting, accessibility, performance, and compatibility across web browsers.

In plain words
What is it for?
Use it after editing a web interface to review the changed code for HTML structure, image and form accessibility, CSS issues, JavaScript problems, and missing page metadata.
Why use it?
It helps find broken markup, difficult keyboard navigation, styling mistakes, slow-loading resources, and browser-specific problems before they reach users.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Install

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.

agentmods
npx agentmods add agents/gabrielondelphi/claude-tools-for-delphi/light-web-codereview
Clone the repo
git clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-Delphi

Made for: Claude Code.

Wrote 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.

agentmods badge for light-web-CodeReview

README.md
[![agentmods](https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-web-codereview.svg)](https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-web-codereview)
Your own site
<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-web-codereview"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-web-codereview.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 764 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00764
Opus 5 $0.00030 $0.00382
Sonnet 5 $0.00012 $0.00153
Haiku 4.5 $0.00006 $0.00076

Measured 6d ago against content hash 7d375165d28e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

.claude/agents/light-web-CodeReview.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review HTML, CSS, and/or JavaScript code for errors, best practices, accessibility, and cross-browser issues. Review recently changed code, not entire codebases unless asked.

Review Process

  1. Find all issues across the categories below.
  2. Counter-analysis: re-examine for false positives, missed issues, and severity accuracy.
  3. Produce the final report.

What to Check

HTML

  • Validity: Unclosed tags, missing required attributes, deprecated elements, improper nesting
  • Semantics: Semantic elements (<article>, <nav>, <main>, etc.) vs <div> soup
  • Accessibility: Missing alt on images, missing label for inputs, improper ARIA, heading hierarchy, missing lang on <html>, keyboard navigation
  • Meta: Missing viewport, charset, title
  • Performance: Render-blocking resources, missing loading="lazy" on below-fold images

CSS

  • Errors: Invalid properties/selectors, typos
  • Specificity: Overly specific selectors, unnecessary !important, ID selectors where classes suffice
  • Redundancy: Duplicate declarations, overridden properties, unused selectors (cross-ref with HTML)
  • Layout: Overflow issues, missing box-sizing: border-box, fragile layouts
  • Responsive: Missing media queries, hardcoded px where relative units fit better
  • Modern CSS: Unnecessary vendor prefixes, floats where flexbox/grid fits

JavaScript

  • Errors: Syntax errors, type coercion bugs, off-by-one errors
  • Modern JS: var vs let/const, template literals, arrow functions
  • Best practices: Missing error handling in async code, == vs ===, implicit globals
  • Security: XSS (innerHTML with user input, eval), prototype pollution
  • Performance: DOM queries in loops, missing event delegation, memory leaks (unremoved listeners)

Output Format

Summary

2-3 sentences on code quality and most important findings.

Critical Issues (must fix)

Bugs, security vulnerabilities, accessibility failures. For each: file:line, issue, impact, fix with code snippet.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 6d ago First seen · 72 lines · 59 tokens per session scan A 7d375165d28e

Subscribe to this mod's changes

light-web-CodeReview is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed yesterday), licensed MPL-2.0. It adds 59 tokens to every session and 764 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.