A website management skill that coordinates the full site lifecycle, from planning and building through testing, launch, monitoring, and maintenance. It acts as a project manager across checks such as usability, security, search visibility, and performance.

Use it for pre-launch reviews, full site quality checks, monthly maintenance, emergency fixes, deployment checks, and tracking ongoing website health.

It brings separate website reviews into one coordinated process so important launch checks and follow-up work are less likely to be missed.

How mrhinkle/VibeCoding-a-Website configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrhinkle/VibeCoding-a-Website. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mrhinkle/VibeCoding-a-Website/main/.claude/skills/webmaster/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/mrhinkle/VibeCoding-a-Website

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/webmaster/github.svg)](https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/webmaster)

Your own site

<a href="https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/webmaster"><img src="https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/webmaster/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/webmaster"><img src="https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/webmaster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,599 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00114	$0.02599
Opus 5.5	$0.00046	$0.01040
Sonnet 5.5	$0.00023	$0.00520
Haiku 4.5	$0.00011	$0.00260

Measured 2mo ago against content hash 33c58d657947, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

webmaster 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.

.claude/skills/webmaster/SKILL.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Webmaster Skill

Think of the webmaster as your site's project manager. While other skills are specialists (the SEO expert, the designer, the security guard), the webmaster sees the whole picture, knows who needs to do what and when, and produces a unified health report that tells you if your site is truly ready.

What The Webmaster Does

The webmaster orchestrates the full lifecycle of your website:

Planning Phase → Interview and define site goals, brand identity, audience
Building Phase → Generate initial site structure, wire forms, create content
Testing Phase → Run QA tests, security audits, SEO checks, copy review, UX evaluation
Deployment Phase → Check links, optimize performance, deploy to production
Monitoring Phase → Track ongoing health, detect regressions, flag issues
Iteration Phase → Update content, fix bugs, improve based on audit feedback

You don't need to remember what to check or the order to check it—the webmaster knows the playbook.

Workflow Presets

Pick the workflow that matches your situation:

Pre-Launch Review

When: 48 hours before going live. You've built your site and want to make sure it's truly production-ready.
What runs:

QA Tester (broken links, forms, functionality)
Security Auditor (vulnerabilities, data exposure)
SEO/AEO Auditor (search visibility, answer engine optimization)
Copy Editor (grammar, tone, brand consistency)
UX Reviewer (usability, accessibility, navigation)
Link Checker (all internal/external links valid)
Performance Optimizer (page speed, Core Web Vitals)

Output: A single Pre-Launch Report with:

Overall readiness score (0–100)
Critical blockers (fix before launch)
High-priority issues (fix within 1 week)
Nice-to-haves (optimize after launch)
Time estimate to fix everything

Typical time: 30–45 minutes to complete all audits

Quick Update

When: You've made changes (updated copy, fixed a bug, added a page) and want confidence they work.
What runs:

Site Updater (applies your changes)
Link Checker (ensures nothing broke)
Performance Optimizer (no speed regressions)
Auto-deploys to staging, then production if all clear

Read the full file on GitHub · 334 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.

2mo ago First seen · 334 lines · 114 tokens per session scan A 33c58d657947

Subscribe to this mod's changes

webmaster is a skill published in the GitHub repository mrhinkle/VibeCoding-a-Website (17 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 2,599 once invoked, about $0.0005 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.

Project management

webmaster next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
webmastermrhinkle/VibeCoding-a-Website	Skill	17	6mo ago	MIT	A	114	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

VibeCoding-a-Website: Skill for Claude Code