agentmods.dev

arcjet-ai-apps

Security rules for AI and large-language-model endpoints, which are web services that send user input to an AI model. They describe checks for bots, request rates, sensitive information, and prompt-injection attacks—messages designed to manipulate the model.

In plain words
What is it for?
Use them when protecting AI endpoints with Arcjet. The guidance covers JavaScript and Python checks for bot detection, token-based rate limits, sensitive information, and prompt injection.
Why use it?
They help stop abusive traffic, control AI usage costs, keep personal information out of model context, and block malicious instructions before they reach the model.

Cursor rule

1 7d ago A scan 0 tokens original Apache-2.0
View the source file arcjet/arcjet-plugin
Install

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.

agentmods
npx agentmods add rules/arcjet/arcjet-plugin/arcjet-ai-apps
Clone the repo
git clone --depth 1 https://github.com/arcjet/arcjet-plugin
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00299
Opus 5 $0.00000 $0.00150
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 2d ago against content hash 09447af8fc90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arcjet-ai-apps 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 2d 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.

plugins/arcjet/rules/arcjet-ai-apps.mdc · 22 lines

What it actually says

Arcjet for AI Endpoints

  • AI endpoints need layered protection: shield() + detectBot() + tokenBucket() + sensitiveInfo() + detectPromptInjection().
  • Use tokenBucket() for AI (not fixed/sliding window) — allows bursts while enforcing average token spend. Set requested parameter to deduct proportional to model cost.
  • sensitiveInfo() with deny list (CREDIT_CARD_NUMBER, EMAIL, PHONE_NUMBER) prevents PII entering model context. Runs locally in WASM — no data sent externally.
  • detectPromptInjection() blocks jailbreaks before they reach the model, saving AI budget & protecting the context.
  • Pass user message to both sensitiveInfoValue and detectPromptInjectionMessage in the protect() call.
  • Python equivalents: detect_sensitive_info(), detect_prompt_injection(), with sensitive_info_value and detect_prompt_injection_message parameters.
  • Ref: https://docs.arcjet.com/llms.txt
Changes

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.

  1. 2d ago First seen · 22 lines · 0 tokens per session scan A 09447af8fc90

Subscribe to this mod's changes

arcjet-ai-apps is a cursor rule published in the GitHub repository arcjet/arcjet-plugin (1 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 299 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 2026-08-31.

Securityai-skillsclaude-codeclaude-code-pluginclaude-pluginclaude-skillscursor-plugin
Related

Other cursor rules, from other repositories

facebook-ads

Meta Ads (Facebook & Instagram) platform expertise. Audit campaigns, audiences, creative strategy, pixel tracking, and CAPI. Use when the user asks about Facebook Ads, Instagram Ads, Meta Ads, social media advertising, Advantage+ campaigns, or Meta pixel/CAPI setup.

thatrebeccarae/claude-marketing · 55 tokens

moodle-hooks-api

Use when implementing or migrating to the Moodle 4.4+ Hooks API. Covers hook class authoring (db/hooks.php), callback registration, dispatching, replacing legacy magic callbacks (extendnavigation, beforehttpheaders, etc.), and testing hook listeners.

SaadRahman01/claude-moodle-dev · 0 tokens

svg-check

Apply when editing, generating, or reviewing any SVG diagram. Pixel-perfect Playwright bbox-check is the acceptance test — eyeballing is not sufficient. Run on every SVG before declaring done.

sordi-ai/skill-everything · 37 tokens

readme-best-practices

README Best Practices - enforces high-quality README patterns when creating or editing README files.

ofershap/readme-best-practices · 276 tokens

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens