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.
npx agentmods add instructions/elmochilyas/laraskills/copilot-instructionsgit clone --depth 1 https://github.com/elmochilyas/laraskillsWrote 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/instructions/elmochilyas/laraskills/copilot-instructions)<a href="https://agentmods.dev/instructions/elmochilyas/laraskills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/elmochilyas/laraskills/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
laraskills copilot-instructions.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for Laravel 13
For full agent operating instructions and knowledge layer navigation, see:
Architecture
- Use modular domain structure:
app/Modules/{Feature}/ - Use Actions (
execute()method) for single-purpose operations - Use readonly DTOs for data transfer
- Use FormRequest for validation and authorization
- Follow Controller → Action → Domain Service → Contract → Infrastructure flow
- Always use constructor injection, never
app()orresolve()in business code - Depend on contracts, not concrete implementations
- Use facades only for infrastructure concerns (Cache, Log, DB)
Models (Laravel 13)
- Use PHP 8 attributes instead of properties:
#[Table('users', key: 'user_id')]instead ofprotected $table#[Fillable(['name', 'email'])]instead ofprotected $fillable#[Hidden(['password'])]instead ofprotected $hidden#[Casts(['is_admin' => 'boolean'])]instead ofprotected $casts
Testing (Pest 4)
- Write tests before implementation (TDD)
- 80% feature tests, 20% unit tests
- Use Laravel fakes (Http, Mail, Queue, Storage, Event, Bus)
- Use
RefreshDatabasetrait for database tests - Write architecture tests with Pest
test('example', function () {
$response = $this->get('/');
$response->assertOk();
});
Security
- Every model needs
#[Fillable]or#[Guarded] - All user input validated via FormRequest
- Blade
{{ }}for output (auto-escaped) - Rate limiting on all API endpoints
- CSRF on all web forms
- Authorization checks on all state-changing actions
Code Quality
./vendor/bin/pint # Format code
./vendor/bin/phpstan analyse --level=6 # Static analysis
php artisan test --parallel # Run tests
Queue Jobs
#[Connection('redis')]
#[Tries(3)]
#[Timeout(60)]
class ProcessJob implements ShouldQueue
{
use Dispatchable, InteractsWithQueue, Queueable, SerializesModels;
}
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.
- 5d ago First seen · 79 lines · 563 tokens per session scan A ddae7320fbf4
laraskills copilot-instructions.md is an instructions file published in the GitHub repository elmochilyas/laraskills (8 stars, last pushed 2mo ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 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.
Other instructions, from other repositories
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
instructor-php AGENTS.md
AGENTS.md instructions for cognesy/instructor-php, covering key reference files, monorepo root, individual subpackages, code style and agents package style.
FreshRSS php.instructions.md
Instructions for FreshRSS/FreshRSS, covering php files and autoloader.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
real-estate-laravel copilot-instructions.md
Copilot instructions for liberusoftware/real-estate-laravel, covering lerd, a local php development environment, architecture, dns modes, mcp tools and key conventions.
phpClickHouse CLAUDE.md
Instructions for smi2/phpClickHouse, covering claude.md — phpclickhouse, project overview, principles, architecture and key notes.