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 microlinkhq/mcp --skill audit-website-insightsgit clone --depth 1 https://github.com/microlinkhq/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/microlinkhq/mcp/audit-website-insights)<a href="https://agentmods.dev/skills/microlinkhq/mcp/audit-website-insights"><img src="https://agentmods.dev/badge/skills/microlinkhq/mcp/audit-website-insights/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/microlinkhq/mcp/audit-website-insights"><img src="https://agentmods.dev/badge/skills/microlinkhq/mcp/audit-website-insights.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 | $0.00092 | $0.00784 |
| Opus 5 | $0.00046 | $0.00392 |
| Sonnet 5 | $0.00018 | $0.00157 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
audit-website-insights 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit website insights
Get a Lighthouse audit and detected technology stack for a URL via microlink_insights.
Run an audit
Pass insights: true for defaults, or an insights object to configure it:
- Lighthouse only:
{ "url": "...", "insights": { "lighthouse": true } } - Technologies only:
{ "url": "...", "insights": { "technologies": true } } - Both (default):
{ "url": "...", "insights": true }
Configure Lighthouse under insights.lighthouse:
preset:"desktop","perf","experimental","lr-desktop","lr-mobile","full", or"default"(mobile). Use"desktop"for desktop-emulated audits.onlyCategories: limit the audit to specific categories to run faster, e.g.["performance", "accessibility"]. Valid IDs:performance,accessibility,best-practices,seo,pwa.output:"json"(default),"html", or"csv".
Focused performance-only example:
{
"url": "https://example.com",
"insights": {
"lighthouse": { "preset": "desktop", "onlyCategories": ["performance"] },
"technologies": true
}
}
Read the results
- Category scores:
microlink.data.insights.lighthouse.categories.<id>.score(0–1; multiply by 100 for the familiar 0–100 score). - Core Web Vitals & metrics: under
microlink.data.insights.lighthouse.audits(e.g.largest-contentful-paint,cumulative-layout-shift,total-blocking-time,first-contentful-paint). - Tech stack:
microlink.data.insights.technologies— an array of detected tools/frameworks (name + categories), e.g. React, Next.js, Cloudflare, GA.
When reporting to the user, translate scores to 0–100, call out the weakest category, and cite the specific failing audits rather than only the headline number.
Tips & gotchas
- Slow tool: a full Lighthouse run takes many seconds. Narrow with
onlyCategoriesand apresetto speed things up when you only need one dimension. - Timeouts: raise
timeout(e.g."60s") for heavy pages. - Fresh numbers: audits are cached — pass
force: trueto re-measure. - Combine:
microlink_extractacceptsinsightsalongsidescreenshot/meta, so you can grab an audit and a screenshot of the page in one request. - Free endpoint caps at 50 requests/day; set
MICROLINK_API_KEYfor more.
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.
- 8d ago First seen · 70 lines · 92 tokens per session scan A 4dd5722df03e
audit-website-insights is a skill published in the GitHub repository microlinkhq/mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 784 once invoked, about $0.0005 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.