web-launch-check

web-launch-check is a skill for Claude Code, Codex from viknesh20-20/claude-code-tool-kit. It costs 71 tokens per session (1,423 once invoked), scanned A, original, MIT.

A pre-launch checklist for websites that checks legal pages, search-engine settings, accessibility, performance, sessions, and privacy compliance. It reports findings by severity and gives a launch recommendation.

In plain words
What is it for?
Use it before launching or redesigning a website, or when reviewing an existing one. It checks items such as privacy policies, cookie consent, sitemaps, structured data, WCAG AA accessibility, and Core Web Vitals.
Why use it?
It helps find missing pages, broken settings, accessibility problems, and compliance gaps before users reach the site. This reduces launch-day defects and avoidable legal or search-visibility issues.

Skill for Claude CodeCodex

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 skills/viknesh20-20/claude-code-tool-kit/web-launch-check
Any agent
npx skills add viknesh20-20/claude-code-tool-kit --skill web-launch-check
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

Made for: Claude Code, Codex.

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 web-launch-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/web-launch-check.svg)](https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/web-launch-check)
Your own site
<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/web-launch-check"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/web-launch-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,423 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 $0.00071 $0.01423
Opus 5 $0.00036 $0.00711
Sonnet 5 $0.00014 $0.00285
Haiku 4.5 $0.00007 $0.00142

Measured 4d ago against content hash ee1e526ce57e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-launch-check 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 4d 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/skills/web-launch-check/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/web-launch-check

Run this before any production website launch to catch missing legal pages, broken SEO, accessibility violations, or compliance gaps that would expose the user to legal risk or hurt search ranking.

When to use

  • Before pushing a marketing site, landing page, or web app to production.
  • After a major redesign that changed page structure, routes, or third-party integrations.
  • Before adding analytics or tracking scripts.
  • When taking over an existing site to assess current state.

What it checks

Layer 1 — Legal pages (CRITICAL — block launch)

Page Path checked Required when
Privacy Policy /privacy, /privacy-policy, footer link Always (any data collection, including cookies/IP)
Terms of Service /terms, /tos, /terms-of-service Any signup, transaction, or user-generated content
Cookie Policy /cookies, section in /privacy EU/UK visitors, or any non-essential cookies
Contact / Address /contact, footer EU jurisdictions (Impressum, EU consumer law); always recommended
Refund / Cancellation /refunds, /cancellation Any e-commerce or paid product

Layer 2 — Consent & tracking (HIGH)

  • Cookie consent banner present before any non-essential cookie is set.
  • Reject button as prominent as Accept.
  • Tracking scripts (Google Analytics, Meta Pixel, etc.) blocked until consent.
  • "Do Not Sell or Share" link if California users (CCPA/CPRA).
  • Global Privacy Control signal honored.

Layer 3 — Sessions & auth (HIGH)

  • Cookies have Secure, HttpOnly, SameSite=Lax (or Strict).
  • Auth tokens not in localStorage if long-lived.
  • Logout invalidates session server-side.
  • CSRF protection on state-changing requests.
  • Session expiry explicit; idle timeout for sensitive flows.

Layer 4 — SEO essentials (HIGH)

  • Every page has unique <title> (≤ 60 chars).
  • Every page has unique <meta name="description"> (~150 chars).
  • Every page has <link rel="canonical">.
  • Every page has Open Graph tags (og:title, og:description, og:image, og:url, og:type).
  • Every page has Twitter Card tags.
  • Structured data (JSON-LD) where relevant (Organization, Article, Product, BreadcrumbList, FAQ).
  • <html lang> set.
  • Exactly one <h1> per page; heading hierarchy correct.
  • Alt text on every meaningful image.

Read the full file on GitHub · 152 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. 4d ago First seen · 152 lines · 71 tokens per session scan A ee1e526ce57e

Subscribe to this mod's changes

web-launch-check is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 1,423 once invoked, about $0.0004 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 2026-08-31.