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 skills add SumonMSelim/agentguard --skill laravelgit clone --depth 1 https://github.com/SumonMSelim/agentguardWrote 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/skills/sumonmselim/agentguard/laravel)<a href="https://agentmods.dev/skills/sumonmselim/agentguard/laravel"><img src="https://agentmods.dev/badge/skills/sumonmselim/agentguard/laravel/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/skills/sumonmselim/agentguard/laravel"><img src="https://agentmods.dev/badge/skills/sumonmselim/agentguard/laravel.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 | $0.00036 | $0.01378 |
| Opus 5 | $0.00018 | $0.00689 |
| Sonnet 5 | $0.00007 | $0.00276 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
laravel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Laravel
Architecture
- Thin controllers: validate input, call service or action, return response. No business logic in controllers
- Form Requests for validation and authorisation. Never validate in controller body
- Service classes or Actions for domain logic. One responsibility each
- Repositories only when swapping data sources is a real requirement
- No logic in routes or middleware beyond stated purpose
- Strict mode in
AppServiceProvider:Model::shouldBeStrict()in non-production,Model::preventLazyLoading()in all envs
PHP Attributes (Laravel 13+)
- PHP Attributes are optional but preferred for co-locating config with classes
- Models:
#[Fillable],#[Guarded],#[Hidden]replace$fillable,$guarded,$hiddenproperties - Controllers:
#[Middleware],#[Authorize]replace$this->middleware()in constructor - Jobs:
#[Tries],#[Backoff],#[Timeout],#[FailOnTimeout]replace class properties - Adopt Attributes on new code. No need to migrate existing property-based code — not deprecated
Eloquent
- Eager-load all relationships with
with(). EnableModel::preventLazyLoading()to catch N+1 in dev - Scope complex query logic into named scopes on the model
firstOrFail()/findOrFail()— never manually null-check query results- Mass assignment:
#[Fillable]or explicit$fillable. Never$guarded = []in production - Observers and model events for cross-cutting concerns only. No core logic inside them
DB::transaction(fn() => ...)for all multi-step writes- UUID or ULID primary keys for distributed systems:
HasUuids/HasUlidstraits - Always add indexes for foreign keys, frequently filtered columns, and unique constraints in migrations
Security
- Sanctum for SPA/mobile API auth. Passport for OAuth server. Never hand-rolled token auth
- Passkey auth available via Laravel 13 first-party support — prefer for new user-facing apps
- Authorise with Policies or Gates. Never inline ownership checks
- CSRF on by default — never disable
- Validate all input with Form Requests. Use
sometimesandnullableintentionally - Secrets in secret manager (AWS Secrets Manager, Vault). Never in
.envcommitted to repo - Encrypt sensitive data at rest via
Cryptfacade - Rate-limit sensitive routes (
login,register, password reset) withthrottlemiddleware - Never
DB::statement()with user input. Use query builder or Eloquent - Sanctum tokens: set expiry. Revoke on logout. Store hashed in DB (default behaviour — don't bypass)
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.
- 9d ago First seen · 94 lines · 0 tokens per session scan A 01ec6a8a884d
laravel is a skill published in the GitHub repository SumonMSelim/agentguard (56 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,378 once invoked, about $0.0002 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.
Other skills, from other repositories
php-pro
A set of practices for building PHP applications with modern PHP, Laravel, or Symfony. PHP is a programming language commonly used for server-side web applications.
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…
create-powergrid-plugin
Create a complete PowerGrid plugin from scratch, including PHP class, Column macro, Blade view, Alpine.js component, and registration.
owl-admin-devtools-generator
A development guide for Owl Admin, a Laravel-based administration system, covering its code generator, API templates, relationships, and visual pages.
llamaindex-development
Expert guidance for LlamaIndex development including RAG applications, vector stores, document processing, query engines, and building production AI applications.
craftcms
Craft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, services, models, records, controllers, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, widgets, filesystems, permissions, project config, GraphQL, testing…