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/KaelSensei/MagicAIBuilderWrote 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/kaelsensei/magicaibuilder/security)<a href="https://agentmods.dev/rules/kaelsensei/magicaibuilder/security"><img src="https://agentmods.dev/badge/rules/kaelsensei/magicaibuilder/security/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/kaelsensei/magicaibuilder/security"><img src="https://agentmods.dev/badge/rules/kaelsensei/magicaibuilder/security.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 | $0.00540 | $0.00540 |
| Opus 5.5 | $0.00216 | $0.00216 |
| Sonnet 5.5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
security 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Rules for Cursor
This repository contains a React Native mobile app with JavaScript/TypeScript code and uses HTML scraping, SQLite, and local file storage.
Cursor (or any AI assistant) must treat security and user privacy as first‑class requirements, even though this is a personal project.
Before any branch is considered ready for merge, the following rules must be enforced.
General Security Principles
- Never introduce hidden logic, obfuscated code, or unnecessary indirection.
- Avoid dynamic code execution (
eval,Function, dynamic imports, unsafe reflection). - Avoid uncontrolled access to the filesystem or device APIs.
- Prefer explicit, readable, auditable logic over clever or compact code.
- Assume all dependencies may be compromised unless verified.
JavaScript / TypeScript / React Native Security
- No post-install scripts, shell execution, or arbitrary filesystem access unless strictly required for the app.
- No new network calls to unknown or undocumented endpoints.
- Allowed domains should stay limited to Moxfield (for scraping HTML/JSON) and Scryfall (for images), plus standard Android/React Native tooling.
- Avoid dynamic requires/imports based on user input.
- Avoid prototype pollution vectors and unsafe object merging.
- Keep dependencies minimal and well-known; prefer built‑ins and lightweight libs.
- Do not introduce any background tracking, analytics, or hidden telemetry.
Local Data & Offline Behavior
- SQLite is the single source of truth; never leak or sync data to a remote backend.
- Local image caching should:
- Store only card images and app‑needed assets.
- Avoid writing arbitrary user-provided paths.
- Clean up safely when needed (no recursive deletes outside the app’s sandbox).
- Scraping logic must treat remote HTML as untrusted input:
- Validate and sanitize scraped fields before inserting into SQLite.
- Handle missing/changed fields defensively (no crashes on bad data).
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 · 56 lines · 540 tokens per session scan A 79660aac89e7
security is a cursor rule published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed today), licensed MIT. It adds 540 tokens to every session, about $0.0022 per session on Opus 5.5. 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 2026-09-04.
Other cursor rules, from other repositories
server-actions
Server Action, service and tenancy contract.
project
Product, stack and layer contract. Always applies.
ui-design-system
UI, design tokens and mobile-first rules.
performance
Navigation, caching and PWA contract.
prisma-schema
Prisma schema and migration conventions.
tdd-domain
TDD contract for business logic.