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 agentmods add skills/microlinkhq/mcp/build-link-previewnpx skills add microlinkhq/mcp --skill build-link-previewgit 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/build-link-preview)<a href="https://agentmods.dev/skills/microlinkhq/mcp/build-link-preview"><img src="https://agentmods.dev/badge/skills/microlinkhq/mcp/build-link-preview.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.00776 |
| Opus 5 | $0.00052 | $0.00388 |
| Sonnet 5 | $0.00021 | $0.00155 |
| Haiku 4.5 | $0.00010 | $0.00078 |
Grade A, and why
build-link-preview 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build link-preview cards
Assemble a rich preview for a URL: title, description, favicon, thumbnail image, and a WCAG-safe color scheme derived from the page's imagery.
Steps
- Metadata — call
microlink_metafor the card text and imagery:microlink.data.title,.description,.author,.date,.publishermicrolink.data.image.url(hero image),microlink.data.logo.url(favicon)
- Colors — call
microlink_paletteon the same URL to theme the card:microlink.data.image.palette— dominant colors (most → least dominant)microlink.data.image.background_color— best card backgroundmicrolink.data.image.color— readable text/overlay color (WCAG-contrast)microlink.data.image.alternative_color— accent
- Thumbnail (optional) — if the page has no good
image, callmicrolink_screenshotwith{ "screenshot": { "type": "jpeg" } }and usemicrolink.data.screenshot.urlas the fallback preview image.
To do it in a single request, use microlink_extract with palette: true (and
screenshot: true if you also want a fallback thumbnail) — metadata, palette, and
screenshot come back together under microlink.data.
{ "url": "https://example.com", "palette": true, "screenshot": true }
Render
Fill references/card-template.html with the values above. The template uses the
palette so text stays readable on the chosen background. Minimal mapping:
- Background ←
background_color - Title / description text ←
color - Accent border/badge ←
alternative_color(orpalette[0]) - Thumbnail ←
image.url(fallback:screenshot.url) - Favicon + publisher ←
logo.url+publisher
Tips & gotchas
- Always check
status === "success"and thatimage.urlexists before rendering; fall back to a screenshot thumbnail when it doesn't. - Missing colors: palette data is nested under each image field
(e.g.
data.image.palette), not at the top level. - Consistency: cache with a
ttl(e.g."1d") so repeated previews of the same link stay identical; useforce: trueonly when you need to refresh. - Accessibility:
background_color+colorare already chosen for contrast — use them together rather than mixing in arbitrary palette entries for body text. - Free endpoint caps at 50 requests/day; set
MICROLINK_API_KEYfor more.
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 · 64 lines · 104 tokens per session scan A 6ad7cfee7709
build-link-preview is a skill published in the GitHub repository microlinkhq/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 776 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 — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.