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 instructions/qbtrix/ripple-iui/claude-mdgit clone --depth 1 https://github.com/qbtrix/ripple-iuiWrote 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/instructions/qbtrix/ripple-iui/claude-md)<a href="https://agentmods.dev/instructions/qbtrix/ripple-iui/claude-md"><img src="https://agentmods.dev/badge/instructions/qbtrix/ripple-iui/claude-md.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 5.1 | $0.00967 | $0.00967 |
| Opus 5 | $0.00483 | $0.00483 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
ripple-iui CLAUDE.md 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
@ripple-ui/svelte — a Svelte 5 component library that renders UI from JSON specs. Designed for AI-generated interfaces: an LLM produces a declarative JSON spec, and Ripple renders it as a fully interactive UI with state management, event handling, and expression resolution.
Commands
bun run dev # Start dev server (SvelteKit)
bun run build # Build library to dist/ via svelte-package
bun run check # Type-check (svelte-kit sync && svelte-check --tsconfig ./tsconfig.json)
bun run test # Run tests (vitest) — no tests exist yet
Package manager is Bun (bun.lock). Use bun install for dependencies.
Architecture
Two Spec Systems
- UISpec (
src/lib/schema/ui-spec.ts) — Low-level: explicit widget tree withUINodecontainingtype,props,children,show, event handlers. Direct control over layout. - UniversalSpec (
src/lib/schema/universal-spec.ts) — High-level intent-based: declares what the UI should accomplish (browse, select, form, detail, dashboard, etc.) and the layout engine picks the best rendering.
The normalizer (src/lib/core/normalizer.ts) converts UISpec → UniversalSpec by wrapping it as intent: 'custom'.
Core Engine (src/lib/core/)
- StateManager (
state-manager.svelte.ts) — Svelte 5$staterune-based. Path-based get/set with dot notation ("user.profile.name"). Auto-creates intermediate objects. - ExpressionResolver (
expression-resolver.ts) — Resolves{state.foo},{item.price}, ternaries, comparisons, and template strings within props. - EventDispatcher (
event-dispatcher.ts) — Handles actions:set,api,navigate,toast,emit,open,pin,unpin. Resolves expressions in URLs/body/headers.
Rendering Pipeline
Ripple.svelte → initializes state/events/context → NodeRenderer.svelte recursively renders the widget tree. NodeRenderer evaluates show conditions, resolves props via expressions, binds events, manages loop context (item_as, index_as), and renders children.
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.
- 5d ago First seen · 65 lines · 967 tokens per session scan A 34c4360ef789
ripple-iui CLAUDE.md is an instructions file published in the GitHub repository qbtrix/ripple-iui (6 stars, last pushed 11d ago), licensed MIT. It adds 967 tokens to every session, about $0.0048 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 2026-08-31.
Other instructions, from other repositories
agents-universe CLAUDE.md
Claude Code instructions for agents-universe/agents-universe, covering agents universe — enterprise ai agent framework, project overview, monorepo layout, development commands and api (from packages/api/).
generative-ui-playground CLAUDE.md
Claude Code instructions for CopilotKit/generative-ui-playground, covering ui protocols demo, architecture overview, three protocols, 1. static genui and 2. mcp apps.
angular-a2ui-macroquest AGENTS.md
AGENTS.md instructions for Soverius-AI/angular-a2ui-macroquest: MacroQuest is an Angular 22 demonstration application for CopilotKit Angular, A2UI, Open Generative UI, and NgRx Signal Store. Keep implementation changes small, visible, and reliable enough for a live talk.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
elysia-admin AGENTS.md
AGENTS.md instructions for meishanlaoyao/elysia-admin, covering elysia admin — codex global rules, dependency direction (strict), generation principles, module dev triggers and file reading discipline (token budget).