agentmods.dev

laravel-loop CLAUDE.md

A project guide for Laravel Loop, a Laravel package that lets AI assistants interact with Laravel applications through a standard connection system. It documents the package structure, commands, tests, formatting, and analysis checks.

In plain words
What is it for?
It helps develop the package, create and run its AI server, build custom tools, run tests, format code, and perform static analysis.
Why use it?
It puts the package's development rules and quality checks in one place, so changes can be built and verified consistently.

Instructions file

132 5mo ago A scan 665 tokens original MIT
View the source file kirschbaum-development/laravel-loop
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.

agentmods
npx agentmods add instructions/kirschbaum-development/laravel-loop/claude-md
Clone the repo
git clone --depth 1 https://github.com/kirschbaum-development/laravel-loop
Per session 665 This file is loaded in full into every session.
When invoked 665 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00665 $0.00665
Opus 5 $0.00332 $0.00332
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00067 $0.00067

Measured 3d ago against content hash 133c351b19c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

laravel-loop CLAUDE.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 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Laravel Loop Package

Laravel Loop is a Model Context Protocol (MCP) server package for Laravel applications that enables AI assistants to interact with Laravel apps through multiple transport protocols (STDIO, Streamable HTTP, SSE). Uses Prism PHP for tool building.

Build/Test Commands

  • Run tests: composer test
  • Code formatting: composer lint (Laravel Pint)
  • Static analysis: composer analyse (Larastan)
  • All quality checks: composer check (lint + analyse + test)
  • Run artisan commands: vendor/bin/testbench
  • MCP server (STDIO): php artisan loop:mcp:start [--user-id=1] [--debug]
  • Generate MCP config: php artisan loop:mcp:config
  • Development server: composer serve (testbench workbench)

Architecture

Core Components:

  • Loop - Main service class for managing tools/toolkits
  • McpHandler - Handles MCP JSON-RPC protocol messages
  • Tool interface - Contract for individual tools (implements Prism\Tool)
  • Toolkit interface - Contract for tool collections
  • CustomTool - Flexible tool builder for custom functionality

Transport Layer:

  • STDIO transport via Artisan command using ReactPHP event loop
  • Streamable HTTP transport (/mcp endpoint)
  • SSE transport (/mcp/sse endpoint, deprecated)

Design Patterns:

  • All classes use Makeable trait for static factory methods
  • Contract-based architecture with clear interfaces
  • ToolCollection for managing groups of tools
  • Facade pattern (Loop::tool(), Loop::toolkit())

Development Guidelines

Tool Development:

  • Tools implement Tool contract with build() and getName() methods
  • Use Prism's fluent API for parameter definition and tool configuration
  • Group related tools in Toolkits that return ToolCollection
  • Register tools in service providers using Loop::tool() or Loop::toolkit()

Code Style:

  • Uses Pest testing framework with Orchestra Testbench
  • Strict typing with declare(strict_types=1)
  • PSR-12 compliant via Laravel Pint
  • Type hints required for parameters and return types

Read the full file on GitHub · 71 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 · 71 lines · 665 tokens per session scan A 133c351b19c9

Subscribe to this mod's changes

laravel-loop CLAUDE.md is an instructions file published in the GitHub repository kirschbaum-development/laravel-loop (132 stars, last pushed 5mo ago), licensed MIT. It adds 665 tokens to every session, about $0.0033 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.

LanguagesPHPlaravelmcpmcp-server
Related

Other instructions, from other repositories

LarAgent AGENTS.md

Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.

MaestroError/LarAgent · 505 tokens

real-estate-laravel copilot-instructions.md

Instructions for liberusoftware/real-estate-laravel, covering lerd, a local php development environment, architecture, dns modes, mcp tools and key conventions.

liberusoftware/real-estate-laravel · 7,960 tokens

events-tracker CLAUDE.md

Claude Code instructions for geoff-maddock/events-tracker, covering claude.md, project, common commands, static analysis (larastan, level 3) and phpunit directly.

geoff-maddock/events-tracker · 1,137 tokens

laravel-release-changelog-generator AGENTS.md

Instructions for lightszentip/laravel-release-changelog-generator, covering agents.md, commands, architecture, core workflow and key components.

lightszentip/laravel-release-changelog-generator · 750 tokens

mcp-client-laravel CLAUDE.md

Instructions for RedberryProducts/mcp-client-laravel, covering project overview, commands, file map, architecture and request flow.

RedberryProducts/mcp-client-laravel · 2,011 tokens

laravel-mcp-server AGENTS.md

Instructions for opgginc/laravel-mcp-server, covering common commands, testing and quality assurance, mcp tool development, mcp notification development and configuration publishing.

opgginc/laravel-mcp-server · 1,465 tokens