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 chris-page-gov/mcp-geo --skill mcp-geo-detailed-os-mapsgit clone --depth 1 https://github.com/chris-page-gov/mcp-geoWrote 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/chris-page-gov/mcp-geo/mcp-geo-detailed-os-maps)<a href="https://agentmods.dev/skills/chris-page-gov/mcp-geo/mcp-geo-detailed-os-maps"><img src="https://agentmods.dev/badge/skills/chris-page-gov/mcp-geo/mcp-geo-detailed-os-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/chris-page-gov/mcp-geo/mcp-geo-detailed-os-maps"><img src="https://agentmods.dev/badge/skills/chris-page-gov/mcp-geo/mcp-geo-detailed-os-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 | $0.00041 | $0.00629 |
| Opus 5 | $0.00020 | $0.00315 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
mcp-geo-detailed-os-maps 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 12d 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.
MCP Geo Detailed OS Maps
Use this skill when a user-facing map in this repo needs precise Ordnance Survey street or building context, especially for report HTML, accessibility mapping, town-centre navigation, or slide-like static map outputs that still benefit from interactive zoom.
Default approach
- Prefer a MapLibre underlay with the OS vector Light style:
OS_VTS_3857_Light.json. - Keep your thematic overlay separate from the basemap. Do not bake route highlighting into the basemap.
- Treat the OS detail layer as progressive enhancement:
- if a browser-held OS Maps API key is available, enable detailed context by default
- if not, keep a simplified fallback view that still works offline or without secrets
Overlay design rules
- Preserve OS labels. Use casing, outlines, or translucent edge emphasis instead of thick opaque fills when highlighting roads or paths.
- Match the geometry to the mapped object as closely as possible:
- road access overlays should sit on the road segment or pavement edge
- avoid bubbles or large markers that hide the exact segment being discussed
- Put long explanations in hover text, sidebars, or perimeter callouts, not on the centre of the map.
- If the map is for navigation, remove decorative labels before removing orientation cues such as north arrow, rail line, seafront, river edge, or major anchors.
Browser key pattern
- Never hardcode OS keys into generated HTML.
- Store the browser-side key locally in browser storage only.
- Make the no-key path explicit and usable.
- When only the presentation layer changes, prefer regenerating from a saved
export rather than refetching live OS data. For the wheelchair report
generator, use
--reuse-exportwith the existing dated JSON export. - When switching styles in MapLibre, remember that style changes clear custom
sources and layers; rehydrate overlays after
style.loadif you render them inside the MapLibre stack.
Validation checklist
- Open the generated HTML in a real browser.
- Check default fit at desktop width with no clipping or hidden sidebars.
- Check zoom in/out, mouse wheel zoom, drag pan, and reset behavior.
- Check label readability with the detailed OS basemap enabled.
- Check that fallback behavior is still clear and usable when no browser key is present.
- If the map is intended for a static export, generate a screenshot after the final browser pass.
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.
- 12d ago First seen · 64 lines · 41 tokens per session scan A 27d76f18aca4
mcp-geo-detailed-os-maps is a skill published in the GitHub repository chris-page-gov/mcp-geo (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 629 once invoked, about $0.0002 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
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.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
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.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.