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 rules/hajjy22/animai/cursorrulesgit clone --depth 1 https://github.com/Hajjy22/animaiWhat 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 | $0.00627 | $0.00627 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
cursorrules 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 today.
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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animon Project - Agentic Engineering Specification
Project Identity
You are building AnimAI, an MCP (Model Context Protocol) server and CLI tool that injects pre-vetted 3D/motion components into existing codebases using AST (Abstract Syntax Tree) manipulation. Do NOT generate mathematical 3D loops or GLSL shaders from scratch; always retrieve from the static template cache.
Tech Stack
- Runtime: Node.js (TypeScript)
- AST Engine:
@ast-grep/napi - MCP SDK:
@modelcontextprotocol/sdk(usingstdiotransport) - Output Targets: Next.js 14/15, React Three Fiber (R3F), GSAP, Tailwind CSS v4
1. MCP Server Constraints
- Use the
stdiotransport to act as a local subprocess for IDEs. - Keep tool definition schemas completely flat. Do not use deeply nested parameter objects, as this increases agent timeout latency [cite: 4].
- Tool outputs must be deterministic JSON containing the dependency list, the integration instructions, and the target code.
2. AST Manipulation Rules (CRITICAL)
- NEVER use Regular Expressions (Regex) or string
.replace()to modify user code. It is brittle and corrupts files. - ALWAYS use
@ast-grep/napiwith the "Find & Patch" methodology to safely traverse and inject imports, variables, and JSX nodes [cite: 5, 6].
3. WebGL & React Three Fiber Constraints
- VRAM Memory Leaks: R3F does not auto-dispose GPU resources [cite: 7]. Every generated 3D component MUST include a manual
useEffectcleanup function that traverses the scene and calls.dispose()on all geometries, materials, and textures [cite: 8, 9]. - Canvas Sizing: The
<Canvas>wrapper must always be injected into a parent container with explicit CSS dimensions (e.g.,h-screen w-full relative). - Inline Assets: For small 3D primitives (
.glb), encode them as Base64 data URIs inline to avoid CORS blocking on local dev servers.
4. Next.js 14/15 Constraints
- SSR Safety: WebGL crashes Node.js servers [cite: 10]. Any file utilizing Three.js, R3F, or
windowAPIs MUST have the"use client"directive at the top [cite: 11]. - Hydration: When injecting heavy canvas elements into a layout, wrap the import with
next/dynamicand set{ ssr: false }to prevent hydration mismatches [cite: 12].
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.
- today First seen · 32 lines · 627 tokens per session scan A 987641ef151c
cursorrules is a cursor rule published in the GitHub repository Hajjy22/animai (0 stars, last pushed 1mo ago), licensed MIT. It adds 627 tokens to every session, about $0.0031 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 cursor rules, from other repositories
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
cursorrules
This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
nix-security
Nix Security and Sandboxing.