agentmods.dev

laravel-ai-lord

laravel-ai-lord is a skill for Claude Code, Codex from m3taz-ahmed/ai-globals. It costs 32 tokens per session (1,057 once invoked), scanned A, original, MIT.

A Laravel development guide for connecting applications to language models, AI agents, and MCP servers using Laravel's own packages. It also covers streaming responses, vector search, secret keys, and human approval for risky actions.

In plain words
What is it for?
Use it when adding chat, agent workflows, MCP tools, embeddings, or vector search to a Laravel 12 or 13 application. It also helps configure key rotation and approval checks.
Why use it?
It avoids scattered provider-specific code, exposed API keys, uncontrolled tool calls, and missing safeguards around destructive actions. It gives AI features a consistent Laravel-based setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 5repo yesterday A scan 32 tokens original MIT

Good fit Use it when adding chat, agent workflows, MCP tools, embeddings, or vector search to a Laravel 12 or 13 application. It also helps configure key rotation and approval checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/m3taz-ahmed/ai-globals/laravel-ai-lord
View source ↗ m3taz-ahmed/ai-globals
Install

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.

Any agent
npx skills add m3taz-ahmed/ai-globals --skill laravel-ai-lord
Clone the repo
git clone --depth 1 https://github.com/m3taz-ahmed/ai-globals

Made for: Claude Code, Codex.

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 laravel-ai-lord

README.md
[![agentmods](https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/laravel-ai-lord/github.svg)](https://agentmods.dev/skills/m3taz-ahmed/ai-globals/laravel-ai-lord)
Your own site
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/laravel-ai-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/laravel-ai-lord/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 laravel-ai-lord

Your own site · 80×15
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/laravel-ai-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/laravel-ai-lord.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,057 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 $0.00032 $0.01057
Opus 5 $0.00016 $0.00528
Sonnet 5 $0.00006 $0.00211
Haiku 4.5 $0.00003 $0.00106

Measured 3d ago against content hash 7ace4ca4e8dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

laravel-ai-lord 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 3d 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.

skills/laravel-ai-lord/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Laravel AI Lord

[OBJ] Integrate LLMs, agents, MCP servers, and AI tooling into Laravel 12/13 applications using first-party packages.

Problem

Laravel 13 (Mar 2026) introduced a first-party AI SDK, MCP server package, and Boost (AI agent context). Ad-hoc integrations leak keys, bypass rate limits, skip human approval for destructive tool calls, and fail to leverage vector search. This skill enforces secure, idiomatic, production-grade AI integration.

Rules

  1. [REQ] Use laravel/ai (v0.11+) for all LLM calls. Never call OpenAI/Anthropic/Gemini SDKs directly — use Ai::provider('openai')->text(...) for abstraction, key rotation, and unified logging.
  2. [REQ] Keys in config/ai.php + .env only. Never hardcode API keys. Use AI_OPENAI_API_KEY, AI_ANTHROPIC_API_KEY, etc. Rotate via php artisan ai:keys:rotate.
  3. [REQ] Streaming by default. Use Ai::stream(...) for chat/completion — SSE-compatible, reduces TTFB. Avoid blocking text() for user-facing responses.
  4. [REQ] Embeddings + vector search. Use AsVector Eloquent cast + whereVectorSimilarTo('embedding', $query, $k). Requires pgvector (PostgreSQL) or mysql-vector extension.
  5. [REQ] Human-in-the-Loop (HITL) for destructive tools. Ai::agent(tools: [...], hitl: true) — approve/deny/modify tool calls before execution. Mandatory for tools that write to DB, send emails, or call external APIs.
  6. [REQ] Tool definitions as PHP closures. Tools are typed closures with JSON Schema: Ai::tool(name: 'get_order', schema: [...], handler: fn($args) => ...).
  7. [REQ] Use laravel/mcp (v1.0-beta) to expose your app as an MCP server for AI clients (Cursor, Claude, etc.). Tools/resources/prompts auto-discovered via attributes.
  8. [REQ] Use laravel/boost (v2.7+) for AI agent context — versioned docs, guidelines, skills, MCP tools. php artisan boost:publish generates context bundle.
  9. [REQ] Rate-limit AI endpoints. Use RateLimiter::for('ai', ...) — per-user, per-IP. LLM calls are expensive; prevent abuse.
  10. [REQ] Log token usage. Ai::logUsage() records input/output tokens, cost, latency per call. Monitor with ai:usage:report.
  11. [REQ] Retry with exponential backoff. Ai::retry(times: 3, backoff: 100) — handles 429, 500, timeout. Never retry 400/401/403.
  12. [REQ] Validate AI outputs. Use Ai::validate($output, schema: [...]) — JSON Schema validation. Reject malformed AI responses.
  13. [PROHIBIT] Never expose raw API keys to frontend. All AI calls server-side only.
  14. [PROHIBIT] Never skip HITL for tools with side effects (DB writes, emails, payments).
  15. [PROHIBIT] Never use file_get_contents for AI API calls — use the SDK for streaming, retries, error handling.

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 32 tokens per session scan A 7ace4ca4e8dd

Subscribe to this mod's changes

laravel-ai-lord is a skill published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,057 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 2026-09-09.

Backend and APIsData and AIRAG and vectors
Related

Other skills, from other repositories

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

azure-search-documents-ts

Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.

microsoft/skills · 48 tokens

convex-agent

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

openclaw/clawhub · 25 tokens

wegent-knowledge

Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.

wecode-ai/Wegent · 51 tokens

langchain4j-spring-boot-integration

Provides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection, and Spring ecosystem integration. Use when embedding LangChain4j into Spring Boot…

giuseppe-trisciuoglio/developer-kit · 88 tokens

azure-search-documents-py

Full-text, vector, and hybrid search with AI enrichment capabilities.

benjaminasterA/antigravity-awesome-skills · 0 tokens