ui-knowledge

ui-knowledge is a skill for Claude Code, Cursor from redhat-community-ai-tools/UnifAI. It costs 33 tokens per session (2,577 once invoked), scanned A, original, Apache-2.0.

A reference guide for the UnifAI frontend, a React and TypeScript web application. It explains how the interface is organized into features, pages, shared components, API clients, and state-management helpers.

In plain words
What is it for?
Use it when working under ui/client/src/, especially on pages, feature modules, API calls, shared widgets, hooks, contexts, or agentic-AI screens.
Why use it?
It helps the coding agent place changes in the correct frontend area and follow the existing structure instead of applying backend conventions to the user interface.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: paths in frontmatter, but also installed under .cursor/.

Good fit Use it when working under ui/client/src/, especially on pages, feature modules, API calls, shared widgets, hooks, contexts, or agentic-AI screens.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhat-community-ai-tools/unifai/ui
Install

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.

Any agent
npx skills add redhat-community-ai-tools/UnifAI --skill ui
Clone the repo
git clone --depth 1 https://github.com/redhat-community-ai-tools/UnifAI

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for ui-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/ui/github.svg)](https://agentmods.dev/skills/redhat-community-ai-tools/unifai/ui)
Your own site
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/ui"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/ui/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.

agentmods 80×15 button for ui-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/ui"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.02577
Opus 5 $0.00016 $0.01288
Sonnet 5 $0.00007 $0.00515
Haiku 4.5 $0.00003 $0.00258

Measured 10d ago against content hash 03739c565ed9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ui-knowledge 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 10d 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.

.cursor/skills/codebase/domains/ui/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Knowledge System

React 18 SPA (~280 TS/TSX files) with Nginx reverse proxy. Feature-oriented layout (NOT hexagonal).

Component Routing

Path prefix Module Files Description
api/ API Layer ~19 Typed API modules, one per backend target service
components/agentic-ai/ Agentic AI ~51 Graph builder, chat, templates, inventory
components/ui/ shadcn/ui ~51 Radix-based UI primitives (Button, Dialog, Select, etc.)
components/shared/ Shared ~22 FieldRenderer, ShareWorkflow, common widgets
hooks/ Custom Hooks ~23 Domain hooks (sessions, graphs, workspace, etc.)
contexts/ React Contexts 7 files / 8 contexts Auth, Theme, View, Shared, Notification, AgenticAI, Streaming, Project
http/ HTTP Clients 4 Axios instances for each backend service
features/ Feature Modules ~22 Slack, docs, configuration slices
pages/ Pages ~12 Route-level page components
types/ Types ~8 Shared TypeScript types (graph, session, workspace, templates)

HTTP Clients (4 backends)

Client File Base URL Target
queryClient http/queryClient.ts /api1 RAG
axiosAgentConfig http/axiosAgentConfig.ts /api2 MAS
authClient http/authClient.ts /api3 Identity
backendClient http/backendClient.ts /api4 Platform

Context Provider Tree

QueryClientProvider → ThemeProvider → AuthProvider → SharedProvider
  → ViewProvider → ProjectProvider → NotificationProvider → routes
      Route-scoped: AgenticAIProvider (agentic routes)
                    StreamingDataProvider (chat/execution views)
Context Hook Key Responsibility
AuthContext useAuth Session, login/logout, token refresh, X-Authenticated-User
ViewContext useView Private vs team workspace, selected team, user groups
ThemeContext useTheme Dark/light toggle, primary color CSS vars
AgenticAIContext useAgenticAI Resource UUID↔name maps, validation caches (~760 LOC)
StreamingDataContext useStreamingData In-memory node stream map for live graph/chat
NotificationContext useNotifications Share invites (received/sent), accept/decline

Read the full file on GitHub · 222 lines

Changes

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.

  1. 10d ago First seen · 222 lines · 33 tokens per session scan A 03739c565ed9

Subscribe to this mod's changes

ui-knowledge is a skill published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 2,577 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 2026-08-30.