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.
git clone --depth 1 https://github.com/cmnemoi/cursor-rulesWrote 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.
[](https://agentmods.dev/rules/cmnemoi/cursor-rules/4-composer)<a href="https://agentmods.dev/rules/cmnemoi/cursor-rules/4-composer"><img src="https://agentmods.dev/badge/rules/cmnemoi/cursor-rules/4-composer/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.
<a href="https://agentmods.dev/rules/cmnemoi/cursor-rules/4-composer"><img src="https://agentmods.dev/badge/rules/cmnemoi/cursor-rules/4-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00287 |
| Opus 5.5 | $0.00000 | $0.00115 |
| Sonnet 5.5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
4-composer 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 1mo 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.
What it actually says
Package Management:
- Use
composer requirefor adding new dependencies - Use
composer removefor removing dependencies - Specify exact version constraints for critical dependencies
- Add extensions with
ext-*prefix in require section - Group packages by purpose in require/require-dev sections
Dependency Configuration:
- Set
optimize-autoloader: truefor production - Configure
preferred-installasdistfor faster installs - Enable
sort-packages: truefor consistent ordering - Explicitly configure plugin permissions in
allow-plugins - Replace polyfills with
replacesection when using newer PHP
Autoloading:
- Follow PSR-4 standard for namespace autoloading
- Use
classmaponly for legacy code without namespaces - Define separate autoloading for tests in
autoload-dev - Keep namespace structure matching directory structure
Scripts:
- Create custom scripts for repetitive tasks
- Group related commands with script arrays
- Use
@notation to reference other scripts - Create namespaced scripts for domain-specific operations
- Define post-install/update hooks for automatic setup
- Add test scripts for specific modules/components
- Create linting scripts that run all code quality tools
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.
- 1mo ago First seen · 35 lines · 0 tokens per session scan A 2798a1c3a36f
4-composer is a cursor rule published in the GitHub repository cmnemoi/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 287 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 2026-08-31.
Other cursor rules, from other repositories
laravel
Definitive guide for writing clean, performant, and secure Laravel applications, emphasizing modern best practices and common pitfalls.
laravel-package-coding-standards
A set of coding rules for Laravel packages, with conventions for names and code across several development areas.
hatch3r-php-laravel-patterns
PHP 8.3+ and Laravel 11.x conventions covering typed properties, attributes, Eloquent ORM, Service Container DI, Pest testing, queue workers, and Laravel Pint formatting.
backend
Essential backend patterns and commands for PHP/Symfony.
php
Rules applied when working in PHP files (incl. Laravel, Symfony, WordPress).
coding-style
Project-specific PHP quality checks.