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 skills add Jamie-BitFlight/claude_skills --skill code-review-webgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/code-review-web)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/code-review-web"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-web/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/jamie-bitflight/claude_skills/code-review-web"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 60 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00066 | $0.01099 |
| Opus 5.5 | $0.00026 | $0.00440 |
| Sonnet 5.5 | $0.00013 | $0.00220 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
code-review-web 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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Frontend Code Review Patterns
Load these checks for browser-targeted HTML, CSS, JavaScript, TypeScript, JSX, and TSX. Confirm the rendering/runtime path from source and relevant framework configuration; apply TypeScript checks alongside these checks when applicable.
Load /dh:review-principles before applying these checks.
Accessibility
- Every interactive element (button, link, input, select) must have an accessible name — either visible text,
aria-label, oraria-labelledby - Verify focus behavior for the component's semantics: modal interaction needs appropriate containment and restoration; do not impose a modal focus trap on an ordinary nonmodal panel.
- Check text contrast and large-text eligibility against the target's applicable accessibility standard; record the actual foreground/background and sizing evidence rather than guessing from visual appearance.
- Icon-only buttons without visible text must have
aria-labelor a visually-hidden text span - Verify form controls have programmatically associated names/labels appropriate to their semantics; visual proximity alone does not establish that relationship.
- Images conveying information must have descriptive
alttext; decorative images usealt="" - Keyboard navigation must work — focus order must follow visual order, no focus traps outside intentional modal patterns
XSS Prevention
element.innerHTML = userValueis a blocking finding — usetextContentfor plain textdangerouslySetInnerHTML(React) or equivalent without sanitization is a blocking finding- User-controlled values used in
eval(),Function(), orsetTimeout(string)are a blocking finding - Validate user-controlled URL schemes for the actual attribute and content context; prevent executable or unauthorized navigation/content while preserving deliberately supported media sources.
Performance
- Investigate interleaved layout reads (
offsetWidth,getBoundingClientRect) and style writes for repeated layout work; establish the affected rendering path and cost before assigning severity. - Check that image layout reserves the required space through dimensions or an equivalent supported layout rule; report observed or source-established layout-shift risk.
- Review off-screen image loading against the critical rendering path and intended preload behavior; recommend lazy loading where it addresses a demonstrated cost.
- Check the actual script-loading semantics and critical rendering effect of large bundles; absence of a particular attribute alone does not establish a performance defect.
- Trace expensive render work to its input size, frequency, and user-visible cost before recommending memoization or another optimization.
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.
- 7d ago Changed · -1 lines ce580c64b056
- 15d ago Changed · +5 lines · -25 tokens per session 53432dca7c33
- 1mo ago First seen · 93 lines · 91 tokens per session scan A 79bbf734d752
code-review-web is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,099 once invoked, about $0.0003 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 2026-09-03.
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.
ring:validating-ux-completeness
Validating that UX specifications are complete before technical design: a read-only checklist over wireframes, states, responsive behavior, accessibility, and component-library alignment, emitting a DESIGN VALIDATED / NEEDS REVISION verdict to design-validation.md. Standalone utility — run after a product-designer…
a11y-audit
Run a Maestro-style accessibility audit for WCAG compliance, ARIA usage, keyboard navigation, and screen reader compatibility.
seo-audit
Run a Maestro-style SEO assessment for meta tags, structured data, crawlability, and Core Web Vitals.
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.
web-standards-reviewer
Review an existing web project for web-standards use and essential dependencies only, against the rules of /web-conventions, /javascript-conventions, and the stack skill the project composes (web-static, web-sprinkles, web-components), and answer with the shortest possible feedback — one line per finding, one line…