Rill is a business intelligence tool for turning data sources into SQL models, metrics, dashboards, and natural-language analysis. It is used by business users and coding agents, with OLAP engines such as ClickHouse and DuckDB supporting its queries. Its catalogue add-ons support agent-driven work on Rill projects.
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/rilldata/rillWrote 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/rilldata/rill/frontend-development)<a href="https://agentmods.dev/rules/rilldata/rill/frontend-development"><img src="https://agentmods.dev/badge/rules/rilldata/rill/frontend-development/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/rilldata/rill/frontend-development"><img src="https://agentmods.dev/badge/rules/rilldata/rill/frontend-development.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 | $0.00336 |
| Opus 5.5 | $0.00000 | $0.00134 |
| Sonnet 5.5 | $0.00000 | $0.00067 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
frontend-development 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 1mo 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
Frontend Development Guidelines
Technology Stack
Web Applications
- web-local: Local Rill application (data modeler)
- web-admin: Admin control plane frontend
- web-common: Shared components and utilities
Component Architecture
Shared Components (web-common)
- Generic, reusable components
- No business logic dependencies
- Proper TypeScript interfaces
- Comprehensive prop validation
Component Guidelines
- Keep components small and focused
State Management
Svelte Stores
- Use Svelte stores for global state
- Keep stores modular and focused
- Use derived stores for computed values
- Implement proper store subscriptions
Data Fetching
- Use
@tanstack/svelte-queryfor server state - Implement proper loading states
- Handle errors gracefully
- Use optimistic updates where appropriate
API Integration
Client Generation
- Use
orvalfor OpenAPI client generation - Standardize the naming convention of the admin service usage. Example:
const removeProjectMemberUsergroup = createAdminServiceRemoveProjectMemberUsergroup(); - Generate clients in
web-common - Use generated types for type safety
- Implement proper error handling
API Patterns (TODO)
- Implement proper request/response types
- Handle authentication and authorization
- Use proper error boundaries
Accessibility
ARIA Guidelines
- Use proper ARIA labels and roles
- Implement keyboard navigation
- Ensure proper color contrast
- Test with screen readers
Semantic HTML
- Implement proper heading hierarchy
- Use proper form labels and descriptions
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.
- 1mo ago First seen · 75 lines · 0 tokens per session scan A 472d9879495d
frontend-development is a cursor rule published in the GitHub repository rilldata/rill (2,970 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 336 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 2026-08-30.
Other cursor rules, from other repositories
cursor-shadcn-svelte
Shadcn Svelte UI specialist — use when building or redesigning SvelteKit pages/components with shadcn-svelte, Bits UI, theming, icons, or install commands.
svelte
When writing code for svelte (.svelte or .svelte.ts files) make sure to do the following.
best-practices
SvelteKit Best Practices - enforces current best practices when working with SvelteKit / Svelte 5 code.
vue-typescript-patterns
A set of coding rules for Vue 3 projects using TypeScript, a language that adds type checking to JavaScript. It covers component structure, file locations, TypeScript usage, and Pinia, a library for shared application state.
svelte-5-vs-svelte-4-cursorrules-prompt-file
Cursor rules for comparing Svelte 5 and Svelte 4 development.
svelte-mcp-tools
Instructions for using the Svelte MCP server tools for documentation lookup, code analysis, and validation.