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/agents/light-web-CodeReview.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/agents/gabrielondelphi/claude-tools-for-delphi/light-web-codereview)<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/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/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="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 | $0.00059 | $0.00764 |
| Opus 5.5 | $0.00024 | $0.00306 |
| Sonnet 5.5 | $0.00012 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
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 2mo 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 — 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
- Find all issues across the categories below.
- Counter-analysis: re-examine for false positives, missed issues, and severity accuracy.
- 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
alton images, missinglabelfor inputs, improper ARIA, heading hierarchy, missinglangon<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:
varvslet/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.
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.
- 2mo ago First seen · 72 lines · 59 tokens per session scan A 7d375165d28e
light-web-CodeReview is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (23 stars, last pushed 28d ago), licensed MPL-2.0. It adds 59 tokens to every session and 764 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…