rule

A project rule requiring all code, comments, documentation, configuration text, and user-facing strings to be written in English. Localization should use internationalization support.

In plain words
What is it for?
Checking variable and function names, comments, error messages, README files, documentation, and text in configuration files.
Why use it?
It prevents mixed-language project content and makes the codebase and documentation consistent for English-speaking contributors.

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/hassansaadfr/log-reader-mcp/rule
Clone the repo
git clone --depth 1 https://github.com/hassansaadfr/log-reader-mcp

Made for: Cursor.

Per session 1,022 This file is loaded in full into every session.
When invoked 1,022 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 $0.01022 $0.01022
Opus 5 $0.00511 $0.00511
Sonnet 5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 2d ago against content hash 6a799eee9c4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rule 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/rule.mdc · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

English-Only Development Rule

This rule enforces that all code, comments, and documentation must be written in English throughout the project.

Scope

This rule applies to:

  • All source code files (.ts, .js, .tsx, .jsx, etc.)
  • All comments within code files
  • All documentation files (.md, .mdx, etc.)
  • All configuration files with text content
  • All README files and project documentation

Requirements

Code Files

  • Variable names: Must be in English
  • Function names: Must be in English
  • Class names: Must be in English
  • Comments: Must be in English
  • String literals: User-facing strings should be in English (use i18n for localization)
  • Error messages: Must be in English

Documentation Files

  • README files: Must be in English
  • API documentation: Must be in English
  • Code comments: Must be in English
  • Inline documentation: Must be in English

Configuration Files

  • Comments in config files: Must be in English
  • Descriptive text: Must be in English

Examples

✅ Correct (English)

// Initialize the user authentication service
const authService = new AuthenticationService();

/**
 * Validates user credentials and returns authentication token
 * @param username - The user's username
 * @param password - The user's password
 * @returns Promise<AuthToken>
 */
async function validateCredentials(username: string, password: string): Promise<AuthToken> {
  // Check if user exists in database
  const user = await findUserByUsername(username);

  if (!user) {
    throw new Error('User not found');
  }

  // Verify password hash
  const isValidPassword = await verifyPassword(password, user.passwordHash);

  if (!isValidPassword) {
    throw new Error('Invalid credentials');
  }

  return generateAuthToken(user);
}

❌ Incorrect (French)

// Initialiser le service d'authentification utilisateur
const serviceAuth = new ServiceAuthentification();

/**
 * Valide les identifiants utilisateur et retourne le token d'authentification
 * @param nomUtilisateur - Le nom d'utilisateur
 * @param motDePasse - Le mot de passe
 * @returns Promise<AuthToken>
 */
async function validerIdentifiants(nomUtilisateur: string, motDePasse: string): Promise<AuthToken> {
  // Vérifier si l'utilisateur existe dans la base de données
  const utilisateur = await trouverUtilisateurParNom(nomUtilisateur);

  if (!utilisateur) {
    throw new Error('Utilisateur non trouvé');
  }

  // Vérifier le hash du mot de passe
  const motDePasseValide = await verifierMotDePasse(motDePasse, utilisateur.hashMotDePasse);

  if (!motDePasseValide) {
    throw new Error('Identifiants invalides');
  }

  return genererTokenAuth(utilisateur);
}

Read the full file on GitHub · 150 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 · 150 lines · 1,022 tokens per session scan A 6a799eee9c4b

Subscribe to this mod's changes

rule is a cursor rule published in the GitHub repository hassansaadfr/log-reader-mcp (6 stars, last pushed 1y ago), licensed MIT. It adds 1,022 tokens to every session, about $0.0051 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.