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 ivklgn/ai-kit --skill audit-websitegit clone --depth 1 https://github.com/ivklgn/ai-kitWrote 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/ivklgn/ai-kit/audit-website)<a href="https://agentmods.dev/skills/ivklgn/ai-kit/audit-website"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/audit-website/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/ivklgn/ai-kit/audit-website"><img src="https://agentmods.dev/badge/skills/ivklgn/ai-kit/audit-website.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Rogue Agent · line 103 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00110 | $0.04211 |
| Opus 5.5 | $0.00044 | $0.01684 |
| Sonnet 5.5 | $0.00022 | $0.00842 |
| Haiku 4.5 | $0.00011 | $0.00421 |
Grade A, and why
audit-website 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.
This is a copy
88% identical to audit-website — 33 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Audit Skill
Audit websites for SEO, technical, content, performance and security issues using the squirrelscan cli.
squirrelscan provides a cli tool squirrel - available for macos, windows and linux. It carries out extensive website auditing by emulating a browser, search crawler, and analyzing the website's structure and content against over 230+ rules.
It will provide you a list of issues as well as suggestions on how to fix them.
Links
- squirrelscan website is at https://squirrelscan.com
- documentation (including rule references) are at docs.squirrelscan.com
You can look up the docs for any rule with this template:
https://docs.squirrelscan.com/rules/{rule_category}/{rule_id}
example:
https://docs.squirrelscan.com/rules/links/external-links
What This Skill Does
This skill enables AI agents to audit websites for over 230 rules in 21 categories, including:
- SEO issues: Meta tags, titles, descriptions, canonical URLs, Open Graph tags
- Technical problems: Broken links, redirect chains, page speed, mobile-friendliness
- Performance: Page load time, resource usage, caching
- Content quality: Heading structure, image alt text, content analysis
- Security: Leaked secrets, HTTPS usage, security headers, mixed content
- Accessibility: Alt text, color contrast, keyboard navigation
- Usability: Form validation, error handling, user flow
- Links: Checks for broken internal and external links
- E-E-A-T: Expertise, Experience, Authority, Trustworthiness
- User Experience: User flow, error handling, form validation
- Mobile: Checks for mobile-friendliness, responsive design, touch-friendly elements
- Crawlability: Checks for crawlability, robots.txt, sitemap.xml and more
- Schema: Schema.org markup, structured data, rich snippets
- Legal: Compliance with legal requirements, privacy policies, terms of service
- Social: Open graph, twitter cards and validating schemas, snippets etc.
- Url Structure: Length, hyphens, keywords
- Keywords: Keyword stuffing
- Content: Content structure, headings
- Images: Alt text, color contrast, image size, image format
- Local SEO: NAP consistency, geo metadata
- Video: VideoObject schema, accessibility
What ships with it
3 files 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.
- 2mo ago First seen · 470 lines · 110 tokens per session scan A 656edf8e57af
audit-website is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 4,211 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to audit-website, differing in 33 lines, and is treated as a copy.
audit-website compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-websiteivklgn/ai-kit | Skill | 12 | 1mo ago | MIT | A | 110 | Claude Code |
| building-agentsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 85 | Claude Code, Codex |
| ai-ml-developmenttravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| authentication-patternstravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 28 | Claude Code, Codex |
| email-systemstravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 55 | Claude Code, Codex |
| agent-svelte-experttravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 101 | Claude Code |
| performance-engineeringtravisjneuman/.claude | Skill | 107 | 2d ago | MIT | A | 38 | Claude Code, Codex |