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 vaisala-xweather/xweather-agent-skills --skill raster-mapsgit clone --depth 1 https://github.com/vaisala-xweather/xweather-agent-skillsWrote 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/vaisala-xweather/xweather-agent-skills/raster-maps)<a href="https://agentmods.dev/skills/vaisala-xweather/xweather-agent-skills/raster-maps"><img src="https://agentmods.dev/badge/skills/vaisala-xweather/xweather-agent-skills/raster-maps/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/vaisala-xweather/xweather-agent-skills/raster-maps"><img src="https://agentmods.dev/badge/skills/vaisala-xweather/xweather-agent-skills/raster-maps.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 | $0.00198 | $0.04703 |
| Opus 5 | $0.00099 | $0.02351 |
| Sonnet 5 | $0.00040 | $0.00941 |
| Haiku 4.5 | $0.00020 | $0.00470 |
Grade A, and why
raster-maps scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://www.xweather.com/docs/api/maps/layers How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xweather Raster Maps URL builder
Turn a description of wanted weather imagery into a maps.api.xweather.com URL — as a standalone
static image or as a tile template for an interactive mapping library.
This is a different product from the Weather API: different host, different URL grammar, and credentials sit in the path, not in the query string.
https://maps.api.xweather.com/{client_id}_{client_secret}/{layers}/…/{offset}.{format}
Two output methods — ask which one
Every Raster Maps request is one of two shapes, and they are not interchangeable:
| Static map | Map tiles | |
|---|---|---|
| Produces | A single finished image | A 256×256 tile template a library fetches many of |
| Use when | Email, report, dashboard panel, <img> tag, Slack, PDF |
Leaflet / Mapbox / Google Maps / OpenLayers / Apple Maps |
| Path | {layers}/{w}x{h}/{place},{zoom}/{offset}.{fmt} |
{layers}/{z}/{x}/{y}/{offset}.{fmt} |
| Interactive | No — no pan or zoom | Yes |
If the user hasn't said which one they want, ask before generating anything. Use
Ask a direct either/or question — a structured-choice prompt if the agent has one, plain text otherwise.
Don't guess from weak signals and don't produce both by default — a tile template pasted into an
<img> tag renders one 256-pixel square, and a static URL handed to Leaflet fails outright.
Signals strong enough to skip the question: the user names a mapping library, says "tile layer" or
"XYZ", or gives {z}/{x}/{y} (→ tiles); or names pixel dimensions, says "image", "PNG for a
report", or shows an <img> tag (→ static).
Workflow
- Determine the output method — ask if not already clear (above).
- Pick the layers. Use the intent map below and confirm codes against
references/layers.md. Order matters: they composite left to right, so base map first, weather next, labels last. - Add the geography. Static:
place,zoomor asouth,west,north,eastbounding box. Tiles: the library substitutes{z}/{x}/{y}— leave the placeholders in. - Add the time offset.
currentunless the user wants past or forecast imagery. - Pick the format.
pngfor tile overlays (transparency is mandatory);pngorjpgfor static maps that include their own base layer. - Apply modifiers if the request implies them — opacity, blur, blend, recolour. See
references/modifiers.md. - Report the URL with its map-unit cost (see Map units), then handle credentials (see below).
- Include the attribution. Any markup you hand over — an
<img>tag, a tile layer, a template — needs the Xweather credit alongside it. See "Attribution is required" below.
What ships with it
5 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.
- 8d ago Changed 110db03d6239
- 12d ago First seen · 320 lines · 198 tokens per session scan A cf86d9eb50cb
raster-maps is a skill published in the GitHub repository vaisala-xweather/xweather-agent-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 198 tokens to every session and 4,703 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…