codeprotection

A set of Cursor rules for marking code regions with labels such as protected, guarded, testing, debugging, or critical business logic. Cursor is a coding editor with an AI assistant.

In plain words
What is it for?
Use it to label code that should not be modified, needs approval before editing, contains tests or debugging code, or represents important business logic.
Why use it?
It helps communicate which parts of a codebase may be changed freely, which require permission, and which carry special context.

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/omril321/automated-notebooklm/codeprotection
Clone the repo
git clone --depth 1 https://github.com/omril321/automated-notebooklm

Made for: Cursor.

Per session 2,490 This file is loaded in full into every session.
When invoked 2,490 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 $0.02490 $0.02490
Opus 5 $0.01245 $0.01245
Sonnet 5 $0.00498 $0.00498
Haiku 4.5 $0.00249 $0.00249

Measured 2d ago against content hash 032378bbd252, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codeprotection 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.

.cursor/rules/riper/codeprotection.mdc · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CursorRIPER♦Ψ 1.0.1

🛡️ Protection Syntax

Ψ_syntax = { PROTECTED: "PROTECTED - DO NOT MODIFY", GUARDED: "GUARDED - ASK BEFORE MODIFYING", INFO: "INFO - CONTEXT NOTE", DEBUG: "DEBUG - DEBUGGING CODE", TEST: "TEST - TESTING CODE", CRITICAL: "CRITICAL - BUSINESS LOGIC",

// End markers END_PROTECTED: "END-P - PROTECTED REGION END", END_GUARDED: "END-G - GUARDED REGION END", END_INFO: "END-I - INFO REGION END", END_DEBUG: "END-D - DEBUG REGION END", END_TEST: "END-T - TEST REGION END", END_CRITICAL: "END-C - CRITICAL REGION END" }

💬 Language Comment Formats

Ψ_language_syntax = { js: {prefix: "// ", suffix: ""}, ts: {prefix: "// ", suffix: ""}, jsx: {prefix: "// ", suffix: ""}, tsx: {prefix: "// ", suffix: ""}, py: {prefix: "# ", suffix: ""}, html: {prefix: ""}, php: {prefix: "// ", suffix: ""}, css: {prefix: "/* ", suffix: " /"}, scss: {prefix: "/ ", suffix: " */"}, java: {prefix: "// ", suffix: ""}, rb: {prefix: "# ", suffix: ""}, go: {prefix: "// ", suffix: ""}, rs: {prefix: "// ", suffix: ""}, c: {prefix: "// ", suffix: ""}, cpp: {prefix: "// ", suffix: ""}, cs: {prefix: "// ", suffix: ""}, swift: {prefix: "// ", suffix: ""}, kt: {prefix: "// ", suffix: ""}, dart: {prefix: "// ", suffix: ""}, md: {prefix: ""}, xml: {prefix: ""}, sh: {prefix: "# ", suffix: ""}, bash: {prefix: "# ", suffix: ""}, sql: {prefix: "-- ", suffix: ""} }

⌨️ Command Shortcuts

Ψ_shorthand = { "!cp": apply_protection(PROTECTED), "!cg": apply_protection(GUARDED), "!ci": apply_protection(INFO), "!cd": apply_protection(DEBUG), "!ct": apply_protection(TEST), "!cc": apply_protection(CRITICAL) }

apply_protection(type) = { detect_language(current_file) ⟶ lang, get_comment_syntax(lang) ⟶ {prefix, suffix}, selection = get_editor_selection(),

// Insert opening marker insert_at_selection_start(prefix + Ψ_syntax[type] + suffix),

Read the full file on GitHub · 333 lines

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 · 333 lines · 2,490 tokens per session scan A 032378bbd252

Subscribe to this mod's changes

codeprotection is a cursor rule published in the GitHub repository omril321/automated-notebooklm (15 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 2,490 tokens to every session, about $0.0124 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 2026-08-30.