experiments: Cursor rule for Cursor

.cursor/deprecated/use-reliverse-rempts-instead-of-commander.mdc

use-reliverse-rempts-instead-of-commander is a cursor rule for Cursor from reliverse/experiments. It costs 0 tokens per session (774 once invoked), scanned A, original, MIT.

A set of rules for building Dler command-line tools with the Rempts framework instead of Commander. It covers command definitions, validated options, handlers, and access to command context.

In plain words
What is it for?
Use it when adding or changing Dler CLI commands, options, handlers, prompts, spinners, shell commands, or plugin-context access.
Why use it?
It keeps CLI commands consistent and makes their options and inputs easier to validate and use correctly.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

This is reliverse/experiments's own configuration. It tells Cursor how to work on experiments itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything experiments configures →

Reuse

Borrowing it

Nothing to install: this file belongs to reliverse/experiments. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/reliverse/experiments/main/.cursor/deprecated/use-reliverse-rempts-instead-of-commander.mdc
Clone the repo
git clone --depth 1 https://github.com/reliverse/experiments

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for use-reliverse-rempts-instead-of-commander

README.md
[![agentmods](https://agentmods.dev/badge/rules/reliverse/experiments/use-reliverse-rempts-instead-of-commander/github.svg)](https://agentmods.dev/rules/reliverse/experiments/use-reliverse-rempts-instead-of-commander)
Your own site
<a href="https://agentmods.dev/rules/reliverse/experiments/use-reliverse-rempts-instead-of-commander"><img src="https://agentmods.dev/badge/rules/reliverse/experiments/use-reliverse-rempts-instead-of-commander/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for use-reliverse-rempts-instead-of-commander

Your own site · 80×15
<a href="https://agentmods.dev/rules/reliverse/experiments/use-reliverse-rempts-instead-of-commander"><img src="https://agentmods.dev/badge/rules/reliverse/experiments/use-reliverse-rempts-instead-of-commander.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00774
Opus 5 $0.00000 $0.00387
Sonnet 5 $0.00000 $0.00155
Haiku 4.5 $0.00000 $0.00077

Measured 9d ago against content hash 99c8335634ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

use-reliverse-rempts-instead-of-commander 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 9d 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/deprecated/use-reliverse-rempts-instead-of-commander.mdc · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rempts CLI Development Patterns

Dler framework uses Rempts to build CLI tools.

Follow these patterns when developing CLI functionality in the Rempts framework.

Command Structure

Commands follow a consistent pattern using the core framework:

// In any command file (e.g., packages/cli/src/commands/build.ts)
import { defineCommand, option } from '@reliverse/rempts'
import { z } from 'zod'

export const buildCommand = defineCommand({
  name: 'build',
  description: 'Build the project',
  options: {
    // Define options with Zod validation
    output: option(
      z.string().default('dist'),
      { description: 'Output directory', short: 'o' }
    ),
    compress: option(
      z.boolean().default(false),
      { description: 'Compress output' }
    )
  },
  handler: async ({ flags, positional, shell, env, cwd, prompt, spinner, colors, context }) => {
    // Access type-safe flags
    const spin = spinner(`Building to ${flags.output}...`)
    spin.start()
    
    // Access plugin context if available
    if (context?.env.isAIAgent) {
      console.log(`AI Agent detected: ${context.store.aiAgents.join(', ')}`)
    }
    
    // Implementation
    await shell`bun build src/index.ts --outdir ${flags.output}`
    spin.succeed('Build complete!')
  }
})

Configuration

File Naming

  • Use kebab-case for all files: my-command.ts not MyCommand.ts
  • Commands go in commands/ directory
  • Use .js extensions for all local imports (ESM requirement)
  • Keep files focused on single responsibilities

Error Handling

  • Use utilities from the handler context: relico.error(), relico.warn(), relico.info()
  • Throw meaningful errors with helpful messages
  • Zod schemas provide automatic validation for command options
  • Use validation from packages/utils/src/validation.ts

Read the full file on GitHub · 117 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. 9d ago First seen · 117 lines · 0 tokens per session scan A 99c8335634ff

Subscribe to this mod's changes

use-reliverse-rempts-instead-of-commander is a cursor rule published in the GitHub repository reliverse/experiments (118 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 774 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 2026-09-01.