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 agents/ocean-industries-concept-lab/openbridge-webcomponents/ui-componentsgit clone --depth 1 https://github.com/Ocean-Industries-Concept-Lab/openbridge-webcomponentsWrote 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/agents/ocean-industries-concept-lab/openbridge-webcomponents/ui-components)<a href="https://agentmods.dev/agents/ocean-industries-concept-lab/openbridge-webcomponents/ui-components"><img src="https://agentmods.dev/badge/agents/ocean-industries-concept-lab/openbridge-webcomponents/ui-components.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 | $0.00015 | $0.00948 |
| Opus 5 | $0.00008 | $0.00474 |
| Sonnet 5 | $0.00003 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
ui-components 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 yesterday.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Components Instructions
These instructions apply to all general UI components: buttons, cards, forms/inputs, feedback indicators, navigation, menus/overlays, tables, and utility components.
Architecture
All UI components extend LitElement directly — there are no shared base classes or helper mixins. Each component is fully self-contained with its own variants, enums, events, and styles.
Elevation Variants via @mixin style
Full reference: IMPLEMENTATION_GUIDELINES.md § PostCSS
Most interactive components support elevation variants (flat, normal, raised, amplified, indent, selected). Apply them with the PostCSS mixin:
.wrapper {
@mixin style style=flat visibleWrapperClass=.visible-wrapper;
color: var(--on-flat-active-color);
}
.wrapper.variant-raised {
@mixin style style=raised visibleWrapperClass=.visible-wrapper;
color: var(--on-raised-active-color);
}
- Always specify
visibleWrapperClass— it targets the inner visual element that receives border/background styles - The outer wrapper is the touch target (transparent); the inner
.visible-wrapperis the visual target (styled) - Use variant-specific color variables:
--on-flat-active-color,--on-normal-active-color,--on-raised-active-color, etc. - Interactive state colors follow
--{variant}-{state}-background-color/--{variant}-{state}-border-color(see full convention in IMPLEMENTATION_GUIDELINES.md) - Use
noClickfor display-only sub-parts that need colors but no interactivity
Slot Conventions
| Pattern | Usage |
|---|---|
leading-icon, trailing-icon |
Icon positions in buttons and inputs |
icon, icon-left, icon-right |
Generic icon containers |
title, content |
Main content areas in cards and modals |
dialog-title, dialog-content |
Dialog-specific content |
cancel-label, done-label, option-label |
Action button labels in modals |
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.
- yesterday First seen · 117 lines · 15 tokens per session scan A 2ef61b9b3bdb
ui-components is an agent published in the GitHub repository Ocean-Industries-Concept-Lab/openbridge-webcomponents (92 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 948 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
breeze-developer
Seed Breeze 컴포넌트 개발 전문가. 유용한 UI 유틸리티 컴포넌트를 개발하고 CSS Modules로 스타일링합니다.
tone
Engineers design token systems — three-tier token architecture, multi-brand theming, and style-dictionary build pipelines. Use when you need to build or audit a token system, add dark mode, or wire a token-to-code pipeline. Trigger with "design my token architecture", "audit my design tokens".
angular-patterns
// Optional with default value readonly name = input ('').
webc-generator
The webc-generator is an NX executor that automatically converts UI5 Web Components into Angular-native wrapper components. It eliminates manual maintenance of 100+ component wrappers by reading a Custom Elements Manifest (CEM) and generating the full library from it.
nx-workflow
Purpose: Understanding the NX monorepo structure, development patterns, and best practices. For commands, see docs/internal/commands.md.
testing-guidelines
Agent "testing-guidelines" from SAP/fundamental-ngx, covering testing guidelines, test commands, run all tests in a library, run specific test file and examples.