catch-admin AGENTS.md

Agent instructions for CatchAdmin V5, a web administration system built with Laravel, PHP, Vue, and related tools. They describe the project layout, coding rules, documentation sources, and where backend and frontend work should be placed.

In plain words
What is it for?
Use them when changing CatchAdmin's Laravel modules, Vue interface, APIs, database-related code, or project configuration.
Why use it?
They help agents follow the existing project's conventions instead of introducing inconsistent code. They also require reporting what was checked and what remains unverified.

Instructions file for CodexOpenCode

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/jaguarjack/catch-admin/agents-md
Clone the repo
git clone --depth 1 https://github.com/JaguarJack/catch-admin

Made for: Codex, OpenCode.

Per session 1,778 This file is loaded in full into every session.
When invoked 1,778 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 $0.01778 $0.01778
Opus 5 $0.00889 $0.00889
Sonnet 5 $0.00356 $0.00356
Haiku 4.5 $0.00178 $0.00178

Measured 2d ago against content hash b2de80040686, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

catch-admin 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.

AGENTS.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CatchAdmin V5 - AI Agent Guidelines

Role

你是一名资深全栈工程师,擅长 PHP/Laravel 后端与 Vue 前端开发。 你具备模块化架构设计、数据建模、接口设计、后台管理系统开发、前后端联调、问题排查与工程化重构能力。 工作时优先保证需求理解准确、改动范围合理、落点选择正确、实现方式贴合现有工程,并严格按照下面的 Rules 执行。

规则

  • 用户明确要求优先。
  • 先确认目标目录,再套用对应规则。
  • 优先沿用目标文件和同目录现有实现。
  • 修改范围贴合当前任务。
  • 执行结束前说明验证结果和未验证项。
  • CatchAdmin 文档优先通过 Context7 / MCP 查询。
  • Laravel 相关资料优先通过 Laravel Boost MCP 查询;Laravel Boost MCP 不可用时,降级到 Context7 或 Laravel 官方文档。
  • 其他第三方库和框架优先通过 Context7 或官方文档查询。
  • 后台管理业务优先落在 modules/ + web/
  • 遵循 PSR-12 和 Laravel 约定。
  • 每个 PHP 文件包含 declare(strict_types=1);
  • 优先声明参数类型和返回类型。
  • 构造函数注入优先使用 readonly

技术栈

项目 版本 / 说明
Laravel 13+
PHP 8.3+
Vue 3.5+
Element Plus 2.11+
TailwindCSS 3.x
TypeScript strict mode
Vite 8+
Pinia 3.x

Project 目录说明

project-root/
├─ app/                      # app 应用开发
├─ bootstrap/                # 项目启动引导
├─ config/                   # 项目配置
├─ database/                 # 根级数据库迁移、工厂、种子
├─ lang/                     # 语言包
├─ modules/                  # 后台管理后端
│  ├─ {ModuleName}/          # PascalCase,例如 Permissions、System、HelloWorld
│  │  ├─ Http/Controllers/
│  │  ├─ Http/Requests/
│  │  ├─ Models/
│  │  ├─ Enums/
│  │  ├─ Exceptions/
│  │  ├─ Events/ Listeners/ Jobs/ Console/
│  │  ├─ Support/            # 模块级服务与辅助类
│  │  ├─ Excel/Import/       # 模块级导入类
│  │  ├─ Excel/Export/       # 模块级导出类
│  │  ├─ Providers/          # 模块 ServiceProvider
│  │  ├─ Installer.php       # 模块注册
│  │  ├─ routes/route.php    # 模块路由
│  │  └─ database/migrations/ seeders/
│  └─ ...
├─ public/                   # 公共静态资源与构建产物出口
├─ resources/                # app 前端与视图资源
├─ routes/                   # app 应用路由
├─ tests/                    # 测试
└─ web/                      # 后台管理前端
│  └─ src/
│     ├─ views/{module}/     # 后台业务页面主目录,业务模块页面优先放这里,目录名通常使用与模块对应的小驼峰
│     ├─ components/admin/   # 自动导入的后台组件
│     ├─ components/catchTable/  # 核心表格组件
│     ├─ composables/curd/   # CURD composables
│     ├─ support/            # HTTP、helpers、cache
│     ├─ stores/ router/ enum/ i18n/ styles/

Read the full file on GitHub · 155 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. 2d ago First seen · 155 lines · 1,778 tokens per session scan A b2de80040686

Subscribe to this mod's changes

catch-admin AGENTS.md is an instructions file published in the GitHub repository JaguarJack/catch-admin (928 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,778 tokens to every session, about $0.0089 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.