cursorrules

A set of Cursor coding rules for an AI-agent project using Next.js, Tailwind CSS, TypeScript, Supabase, Redis, and related services.

In plain words
What is it for?
Building and changing the project's web application, database functions, agent tools, billing integrations, and usage-tracking code.
Why use it?
It keeps new code aligned with the project's chosen technologies, naming styles, database practices, SDK rules, and telemetry requirements.

Cursor rule for Cursor

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/jayasukuv11-beep/agenthelm/cursorrules
Clone the repo
git clone --depth 1 https://github.com/jayasukuv11-beep/agenthelm

Made for: Cursor.

Per session 320 This file is loaded in full into every session.
When invoked 320 The same file — it is already loaded in full.
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 $0.00320 $0.00320
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash 2463824a3ab5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.cursorrules · 29 lines

What it actually says

AgentHelm Cursor Rules

Optimized for building sovereign AI Agent infrastructure.

Project Architecture

  • Framework: Next.js (App Router), TailwindCSS, TypeScript.
  • Database: Supabase (Postgres) with heavily documented RLS policies.
  • Redis (Upstash): Used for Rate-limiting and Idempotency locks.
  • SDKs: Python (primary) and Node.js (secondary).
  • Billing: Cashfree (Indian) / Stripe (International).

Naming Conventions

  • Database Tables: snake_case (e.g. agent_logs).
  • TypeScript: PascalCase for components/types, camelCase for variables/functions.
  • React Components: Function-based components with use client or use server markers.

Primary Stack Preferences

  • Always use Lucide React for icons.
  • Prefer Radix UI primitives and Shadcn UI components.
  • Use Postgres Functions (rpc) for complex atomic database operations.

SDK Usage Standards

  • Always use the @helm decorators (Python) when defining tools.
  • Never hardcode the baseUrl; use DEFAULT_BASE_URL or environment variables.
  • Ensure track_tokens is called after every LLM completion to secure revenue and monitor burn-rates.

Telemetry Patterns

  • Use dock.progress(percent, message) to ensure Telegram users see live status updates.
  • Use dock.checkpoint(name, state) before any tool that might fail.
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. yesterday First seen · 29 lines · 320 tokens per session scan A 2463824a3ab5

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository jayasukuv11-beep/agenthelm (4 stars, last pushed 6d ago), licensed MIT. It adds 320 tokens to every session, about $0.0016 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.