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 majdghithan/agent-skills --skill laravel-architecture-reviewgit clone --depth 1 https://github.com/majdghithan/agent-skillsWrote 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/majdghithan/agent-skills/laravel-architecture-review)<a href="https://agentmods.dev/skills/majdghithan/agent-skills/laravel-architecture-review"><img src="https://agentmods.dev/badge/skills/majdghithan/agent-skills/laravel-architecture-review/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/majdghithan/agent-skills/laravel-architecture-review"><img src="https://agentmods.dev/badge/skills/majdghithan/agent-skills/laravel-architecture-review.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 | $0.00188 | $0.02344 |
| Opus 5 | $0.00094 | $0.01172 |
| Sonnet 5 | $0.00038 | $0.00469 |
| Haiku 4.5 | $0.00019 | $0.00234 |
Grade A, and why
laravel-architecture-review 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Laravel: architecture review
Larastan finds type errors. Pint fixes formatting. Rector modernizes syntax. None of them tell you the business logic is in the wrong place. This skill is the layer above the linters: it reads design intent and flags where structure has drifted, then recommends the fix that fits the app's real scale, not a pattern from a blog post.
The single rule that makes this skill worth using: recommend a pattern only when the code earns it. Most "best practices" advice fails because it applies enterprise patterns to a CRUD app. A Repository layer to "abstract the ORM you will never swap" is ceremony Laravel's own team argues against. Match the recommendation to the evidence.
Step 0 - Detect before you judge
Everything downstream depends on these. Never recommend a pattern without them.
php artisan --version # Laravel version -> which idioms apply
composer show | grep -E 'pestphp/pest|phpunit|larastan|rector|pint' # what tooling exists
php artisan route:list --json | jq length # rough app size
ls app/Models | wc -l # model count
find app/Http/Controllers -name '*.php' | wc -l # controller count
Scale sets the bar. A 5-model app with 20 routes is a different conversation than a 60-model app with 400 routes. Small app: keep it flat, controllers + FormRequests + a few Actions. Large app with a genuinely complex domain: that is when Services, bounded contexts, and maybe DDD start paying rent. State the scale bracket at the top of every report so the reader sees the recommendations are sized, not generic.
Step 1 - Run the tools that are already there
Do not hand-audit what a tool already checks. Run what exists, suggest installing what does not, never hard-require.
Larastan (static analysis) - package is larastan/larastan
# if missing: composer require --dev larastan/larastan
vendor/bin/phpstan analyse --memory-limit=2G
phpstan.neon includes vendor/larastan/larastan/extension.neon. Levels run 0-10 (max = 10). New audit target: level 5-6 with a baseline for legacy code, raise over time. Larastan's findings are type-level; fold them in but they are not the architecture story.
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.
- 12d ago First seen · 109 lines · 0 tokens per session scan A aadbe828bc62
laravel-architecture-review is a skill published in the GitHub repository majdghithan/agent-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session and 2,344 once invoked, about $0.0009 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 skills, from other repositories
create-powergrid-plugin
Create a complete PowerGrid plugin from scratch, including PHP class, Column macro, Blade view, Alpine.js component, and registration.
module:assistant
Add an AI assistant chat panel to any Laravel project — with tool calling, streaming, and MCP support.
tactical-ddd
Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model…
review-workflow-management
This skill reviews the HTTP management endpoints (start, status, terminate, pause, resume, raise-event, purge) that an app exposes for Dapr Workflows. Use this skill when the user asks to "review workflow management", "audit workflow management API", "check workflow HTTP endpoints", or similar.
review-workflow-activity
This skill reviews Dapr Workflow activity implementations for idempotency, retries, error boundaries, and convention violations. Use this skill when the user asks to "review workflow activities", "check activity idempotency", "audit Dapr activities", or similar.
api-design-review
Review an API contract (REST or GraphQL) before or while it is implemented, checking resource naming, HTTP semantics, status codes, error shape, pagination, versioning, idempotency, and backward compatibility, and producing concrete revisions rather than abstract advice. Use when designing new endpoints, changing an…