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 OpenMinis/MinisSkills --skill openstreetmap-markergit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/openstreetmap-marker)<a href="https://agentmods.dev/skills/openminis/minisskills/openstreetmap-marker"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/openstreetmap-marker/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/openminis/minisskills/openstreetmap-marker"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/openstreetmap-marker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00158 | $0.01933 |
| Opus 5 | $0.00079 | $0.00966 |
| Sonnet 5 | $0.00032 | $0.00387 |
| Haiku 4.5 | $0.00016 | $0.00193 |
Grade A, and why
openstreetmap-marker 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 9d 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.
OpenStreetMap Marker
Generates a self-contained, browser-previewable custom marker map HTML page styled after Amap's mobile app (light minimal basemap + circular colored icon + text label + immersive full-screen layout with safe-area support).
Core Workflow
- Get marker coordinates: prefer
apple-maps search --query "place name city" --lat <city lat> --lon <city lng> --limit 1 -q --compact, which returns JSON withlat/lon/coordinate_system. - Coordinate conversion (critical, do not skip): Apple Maps / Amap / Tencent / Baidu almost always return GCJ-02 coordinates in mainland China, while this skill's Leaflet+OSM/CartoDB basemap uses WGS-84. Using GCJ-02 directly causes markers to drift tens to hundreds of meters (often landing in a river or the sea). Coordinates within mainland China MUST be converted with
scripts/gcj_convert.pybefore writing tolandmarks.json; the script automatically skips conversion for points outside China (out_of_chinacheck).python3 /var/minis/skills/openstreetmap-marker/scripts/gcj_convert.py <lng> <lat> # outputs "wgs_lat,wgs_lng" - Assemble
landmarks.json: an array where each item is:{"name": "West Lake", "desc": "UNESCO World Heritage Site, Hangzhou's iconic landmark", "address": "Xihu District, Hangzhou", "lat": 30.2614, "lng": 120.1443, "type": "green", "icon": "fa-tree"}name/lat/lngare required;desc/address/type/iconare optional.typedetermines the marker dot color:red(government/medical/core attraction),green(park/nature),blue(transport/building),purple(commercial/venue),brown(heritage/university), ororange(other). Defaults toblue. Each type also has a sensible default Font Awesome icon (red→fa-star, green→fa-tree, blue→fa-building, purple→fa-bag-shopping, brown→fa-landmark, orange→fa-circle-dot). Leaveiconempty to use it.icon(optional): a Font Awesome 6 solid-style icon class name, e.g."fa-train","fa-utensils","fa-mosque","fa-museum","fa-mountain". Overrides the type default. Look up icon names at fontawesome.com/icons (free "solid" set). Do NOT use emoji; all icons are unified Font Awesome glyphs rendered via<i class="fa-solid ...">for a consistent cross-device look.- Write this JSON array to a temp file with
file_write, e.g./tmp/landmarks.json.
- Generate the page:
python3 /var/minis/skills/openstreetmap-marker/scripts/build_map.py \ /tmp/landmarks.json /var/minis/workspace/<descriptive-filename>.html \ --title "West Lake Area Landmarks" --header "⚡ Hangzhou Trip" \ --style light--style light(default, light minimal, Amap-like palette) or--style dark(dark immersive).- Without
--center/--zoom, the script automatically centers and zooms to fit all points with padding; a single point defaults to zoom 14.
- Deliver: present the result to the user as a Markdown link
[Preview](minis://workspace/<filename>.html), tappable to open in the built-in browser.
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.
- 9d ago First seen · 70 lines · 158 tokens per session scan A 0ed7c28be1c0
openstreetmap-marker is a skill published in the GitHub repository OpenMinis/MinisSkills (404 stars, last pushed 5d ago), licensed MIT. It adds 158 tokens to every session and 1,933 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
animate-expo
Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and…
leanback-to-compose-tv-migration
Provides instructions and architectural patterns for migrating Android TV applications from legacy Leanback UI Toolkit, Android Views, or Support Fragments to Jetpack Compose for TV (androidx.tv). Use this skill for Leanback to Compose migrations, including browse screen, settings screen, authentication screen, login…
maui-data-binding
Guidance for .NET MAUI XAML and C# data bindings — compiled bindings, INotifyPropertyChanged / ObservableObject, value converters, binding modes, multi-binding, relative bindings, fallbacks, and MVVM best practices. USE FOR: setting up compiled bindings with x:DataType, implementing INotifyPropertyChanged or…
web-haptics
Add haptic feedback to web apps using the web-haptics library. Use when building mobile-facing UIs that need tactile feedback on buttons, toggles, forms, pickers, and other interactive elements.
migrate-xml-views-to-jetpack-compose
Provides a structured workflow for migrating an Android XML View to Jetpack Compose. This skill details the step-by-step process, from planning and dependency setup, to theming and layout migration, validation and XML cleanup. Use this skill when you need to migrate an XML View to Jetpack Compose in an Android…
axiom-swiftui
Use when building, fixing, or improving ANY SwiftUI UI — views, navigation, layout, animations, performance, architecture, gestures, debugging, iOS 26 features.