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.
git clone --depth 1 https://github.com/epam/ai-dial-ui-kitWrote 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/rules/epam/ai-dial-ui-kit/ui-kit-react)<a href="https://agentmods.dev/rules/epam/ai-dial-ui-kit/ui-kit-react"><img src="https://agentmods.dev/badge/rules/epam/ai-dial-ui-kit/ui-kit-react/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/rules/epam/ai-dial-ui-kit/ui-kit-react"><img src="https://agentmods.dev/badge/rules/epam/ai-dial-ui-kit/ui-kit-react.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 | $0.00000 | $0.00391 |
| Opus 5.5 | $0.00000 | $0.00156 |
| Sonnet 5.5 | $0.00000 | $0.00078 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
ui-kit-react 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 24d 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.
What it actually says
AI DIAL UI Kit — TS/React
- TypeScript: After edits in this repo, run
npm run typecheck. Fix all reported errors before finishing (including in*.stories.tsx/*.spec.tsxyou touched). Prefer strict typings overany; match existingDial*prop patterns. - Exports: Public API lives in
src/index.ts. ExportDial*components andexport type { …Props }when needed. - Components:
src/components/<PascalName>/with.tsximplementation; useDialprefix for exported names. - Stories:
*.stories.tsxalongside the component; use Storybook 10 patterns already in the repo. - Tests:
*.spec.tsxor__tests__/with Vitest + Testing Library; mirror user-visible behavior and a11y where relevant. - Styles: Tailwind +
tailwind-merge/mergeClasseswhere the codebase already does; followeslint-plugin-tailwindcssrules. - Public classes: A generation 2.0 component stamps its
DIAL_KIT_CLASSentry (src/constants/public-class-names.ts) on the element that draws it, read from the record rather than written as a literal, last in themergeClassescall. The class carries no declarations, and a new entry needs a case insrc/constants/public-class-names.spec.tsxand a README row. See AGENTS.md § Public class names. - Types: Shared types under
src/types/; co-locate small types in the component file if local only.
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.
- 24d ago Changed 033eecfd6664
- 27d ago First seen · 17 lines · 0 tokens per session scan A 06803c5bb79b
ui-kit-react is a cursor rule published in the GitHub repository epam/ai-dial-ui-kit (10 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 391 tokens. 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 2026-09-19.
Other cursor rules, from other repositories
react-query-tests
// ✅ CORRECT: Legacy React Query pattern const ctx = konn() .beforeEach(() => createAppRouter()) .afterEach((ctx) => ctx?.close?.()) .done().
tanstack-react-query-tests
// ✅ CORRECT: Use await using for automatic cleanup await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).
upgrade-tests
// ✅ CORRECT: Upgrade package pattern await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }).
testing
A high-quality & reliable React Hooks library. https://alibaba.github.io/hooks/.
creative-phase-uiux
UI/UX Design Guidelines and Process for the Creative Phase.
benchmark
Measure, review or repair Plate performance with honest cohorts, baseline identity, correctness guards and causal proof. Load before choosing, running or waiving a scale or latency gate.