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 rolledoatmeals/website-audit-mcp --skill website-auditgit clone --depth 1 https://github.com/rolledoatmeals/website-audit-mcpWrote 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/rolledoatmeals/website-audit-mcp/website-audit)<a href="https://agentmods.dev/skills/rolledoatmeals/website-audit-mcp/website-audit"><img src="https://agentmods.dev/badge/skills/rolledoatmeals/website-audit-mcp/website-audit/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/rolledoatmeals/website-audit-mcp/website-audit"><img src="https://agentmods.dev/badge/skills/rolledoatmeals/website-audit-mcp/website-audit.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 | $0.00081 | $0.01010 |
| Opus 5.5 | $0.00032 | $0.00404 |
| Sonnet 5.5 | $0.00016 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
website-audit 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website audit
Runs a real audit of a public web page and turns the result into something the owner of that site can act on. It is not an opinion about the design: every finding comes from something measured on the page.
What it needs
This skill drives the website-audit MCP server, which exposes one tool:
audit_website(url, type?)
url— the address to audit, such asexample.comorhttps://example.comtype— optional, one oflocal,ecommerce,portfolio,saas. It changes what counts as a problem: a missing phone number is serious for a local business and irrelevant for a portfolio. Leave it out and the type is worked out from the page itself.
If the tool is not available, the server is not installed. Tell the user to run:
claude mcp add website-audit -- npx -y github:rolledoatmeals/website-audit-mcp
Any MCP-speaking client works; the equivalent config is command: npx,
args: ["-y", "github:rolledoatmeals/website-audit-mcp"]. Node 18+ required.
What it does on the network: it resolves the address, fetches that public
page the way a phone browser would (following redirects), and makes one plain
http:// HEAD request to the same host to check whether it redirects to the
secure version. Those requests go to the audited host and nowhere else. It signs
in to nothing, sends no data to any third party, and stores nothing. Addresses
that resolve to private or internal ranges are refused.
How to run it
- Take the address from the user. If they gave a bare domain, pass it as-is.
- Call
audit_website. Passtypeonly when the user has told you what kind of site it is, or when the auto-detected type in the result is clearly wrong and they want it re-scored. - Read the result before summarising it. It returns a 0–100 score, a headline, a page-weight and response-time reading, and findings grouped into six categories: Speed, Phone experience, Getting found, Getting in touch, How the writing reads, How current it looks.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 84 lines · 81 tokens per session scan A f6c2a97a7fed
website-audit is a skill published in the GitHub repository rolledoatmeals/website-audit-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 1,010 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 2026-11-04.
website-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| website-auditrolledoatmeals/website-audit-mcp | Skill | 0 | 5d ago | MIT | A | 81 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |