cursorrules

Repository instructions that tell a coding agent how a project is structured, built, tested, and maintained.

In plain words
What is it for?
Use it when working in a TypeScript project that has an AGENTS.md file with architecture, build, test, and coding guidelines.
Why use it?
They give the agent the project context it needs and reduce mistakes caused by guessing conventions or ignoring important rules.

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/kksudo/agentfs/cursorrules
Clone the repo
git clone --depth 1 https://github.com/kksudo/AgentFS

Made for: Cursor.

Per session 142 This file is loaded in full into every session.
When invoked 142 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 $0.00142 $0.00142
Opus 5 $0.00071 $0.00071
Sonnet 5 $0.00028 $0.00028
Haiku 4.5 $0.00014 $0.00014

Measured yesterday against content hash c1a15cd9a2e9, 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 · 14 lines

What it actually says

AgentFS — Cursor Agent Instructions

Read AGENTS.md in this repository root for full project context, architecture rules, and development guidelines.

Quick Reference

  • TypeScript strict mode, ESM ("type": "module", .js extensions in imports)
  • Node.js >= 18.0.0
  • npm run build to compile, npm test to run 261+ Jest tests
  • Architecture source of truth: docs/architecture.md
  • Everything is a file. No databases, no APIs, no cloud dependencies.
  • Compile, don't symlink. Idempotent operations only.
  • Follow existing formats from architecture doc exactly. Don't invent new conventions.
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 · 14 lines · 142 tokens per session scan A c1a15cd9a2e9

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository kksudo/AgentFS (2 stars, last pushed 4mo ago), licensed MIT. It adds 142 tokens to every session, about $0.0007 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.