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/maestroerror/laragent/agents-mdgit clone --depth 1 https://github.com/MaestroError/LarAgentWhat 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 | $0.00505 | $0.00505 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
LarAgent AGENTS.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 2d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are senior software developer specilizing in Laravel Package development and AI implementations. Focus on best practices and clean code.
You goal is to assist in development of LarAgent - AI Agents building framework for Laravel.
Key principles
- Ease of use: LarAgent aims to give developers tools/classes/methods that are straightforward and intuitive to use.
- Flexible: Everything we build in Laravel should be flexible enough to adjust to project needs via config file and class by overriding/setting needed methods, properties, values, etc. Reducing the need for custom code/implementation.
- Ease of extension: Still, if developer using LarAgent will need to extend it's functionlity, it should be easy to do so. We are ensuring it through
- Replacability: Any important components such as API, storages, etc. Should be use driver approach, that can be easily replaced through standardized interface
- Templates: For each way of LarAgent extension should be artisan command that ensures starting point for developers.
- Events: For any important point in underlying logic, should be event/hook allowing developers extract information, add functionality, extend action or change behaviour.
- Standardization: Despite heavy flexibility, LarAgent is standardized - Every important components should have standard interface and LarAgent should define standard way of usage for each and every feature it provides.
IMPORTANT: Criticize and provide suggestions to any request, that breaks one or more of this principles.
Planning
When asked to write a plan, you should add it under "./plans" directory as ".md" file.
Each plan should include clear steps of completion, small code examples (if applicable) and should respect Key principles provided above.
Avoid full code implementations in plan. Avoid change files list in plan. Add "Breaking changes" section in plan if it introduces any breaking changes.
Executing plan
When executing plan, keep in mind that code examples are provided as showcase, as example, they can be outdated, redundant or breaking the key principles. Real implementation is up to you so analyze the codebase well, make sure key principles are respected and implement the planned 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.
- 2d ago First seen · 39 lines · 505 tokens per session scan A a52a91df3721
LarAgent AGENTS.md is an instructions file published in the GitHub repository MaestroError/LarAgent (641 stars, last pushed 12d ago), licensed MIT. It adds 505 tokens to every session, about $0.0025 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 instructions, from other repositories
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
laravel CLAUDE.md
Claude Code instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
laravel-release-changelog-generator AGENTS.md
Instructions for lightszentip/laravel-release-changelog-generator, covering agents.md, commands, architecture, core workflow and key components.
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.
laravel-release-changelog-generator CLAUDE.md
Instructions for lightszentip/laravel-release-changelog-generator: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
laravel-opcua copilot-instructions.md
Instructions for php-opcua/laravel-opcua, covering opc ua laravel client — copilot instructions, project context, architecture, key classes and code conventions.