Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/RealTimeLogic/LSP-Examplesnpx agentmods add skills/realtimelogic/lsp-examples/customWrote 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/realtimelogic/lsp-examples/custom)<a href="https://agentmods.dev/skills/realtimelogic/lsp-examples/custom"><img src="https://agentmods.dev/badge/skills/realtimelogic/lsp-examples/custom/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/realtimelogic/lsp-examples/custom"><img src="https://agentmods.dev/badge/skills/realtimelogic/lsp-examples/custom.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 | $0.00046 | $0.04699 |
| Opus 5 | $0.00023 | $0.02350 |
| Sonnet 5 | $0.00009 | $0.00940 |
| Haiku 4.5 | $0.00005 | $0.00470 |
Grade A, and why
light-dashboard-custom 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 — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Light Dashboard Custom Variant Skill
Use this skill when developing the custom/ dashboard variant in this repo.
The custom/ variant is the primary target for new work. It uses:
- a small database-free CMS in
custom/.lua/cms.lua; - a shared shell in
custom/.lua/www/template.lsp; - HTMX fragment navigation;
- custom CSS in
custom/static/styles.css; - a two-level menu from
custom/.lua/menu.json; - CMS-level SMQ support from
custom/static/cms-smq.js; - native JavaScript only for custom application code.
Light Dashboard is appropriate for real-time device interfaces on platforms ranging from RTOS targets to Embedded Linux. When a project instead requires SQLite-backed content, browser-based administration, themes, or plugins, consider FuguHub as the more advanced Mako Server CMS alternative.
Do not use this skill for the www/ or htmx/ variants unless the user
explicitly asks for parity across variants.
First Files to Read
Before making changes, inspect the relevant files:
custom/.lua/cms.luafor routing, full-page vs HTMX response behavior, and security headers.custom/.lua/www/template.lspfor the shell, menu rendering, global assets, and#main.custom/.lua/menu.jsonfor navigation and routing.custom/static/styles.cssfor layout, colors, typography, forms, and navigation styles.custom/static/ui.jsfor menu toggling and active navigation state.custom/static/cms-smq.jswhen adding or modifying SMQ behavior.custom/.preloadandcustom/SMQ/index.lspfor server-side SMQ broker behavior.doc/custom-design.mdfor detailed architecture notes.
Core Architecture
The CMS is designed to behave like a normal server-rendered site on direct page loads and like a lightweight SPA when HTMX is available.
Request flow:
- Static files are served first by the resource reader.
- Unmatched requests fall through to
cmsfunc(...)incustom/.lua/cms.lua. - Directory requests are normalized to
index.html. - HTML pages must be registered in
custom/.lua/menu.json. - Normal requests return the full
template.lspshell. - HTMX requests return only the page fragment.
- HTMX history-restore requests return the full shell.
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 · 623 lines · 46 tokens per session scan A f154114a7f2d
light-dashboard-custom is a skill published in the GitHub repository RealTimeLogic/LSP-Examples (41 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 4,699 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 2026-09-13.
Other skills, from other repositories
ha-lovelace
This skill should be used when the user asks about "dashboard", "lovelace", "card", "view", "theme", "UI", mentions dashboard design, card configuration, dashboard layout, or needs help with Home Assistant Lovelace dashboard creation and customization.
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.
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.
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.
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…