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 rules/pekral/cursor-rules/architecturegit clone --depth 1 https://github.com/pekral/cursor-rulesWhat 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 | $0.00000 | $0.14929 |
| Opus 5 | $0.00000 | $0.07465 |
| Sonnet 5 | $0.00000 | $0.02986 |
| Haiku 4.5 | $0.00000 | $0.01493 |
Grade A, and why
architecture 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 yesterday.
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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
- Apply these rules only if the project uses
pekral/arch-app-services. - This rule extends core Laravel conventions with package-specific architectural constraints.
- Follow
pekral/arch-app-servicesas the source of truth, including package examples and conventions.
Architecture
- All business logic must follow the Action pattern.
- Mandatory orchestration flow:
Controller / Job / Command / Listener / Livewire Component -> Action -> ModelService -> Repository (read) / ModelManager (write)
- Entry points must stay thin:
- accept input
- validate input or delegate validation
- call an Action
- return a response or update UI state
- Only Laravel-native class types exist in the application; every other concern is a
pekral/arch-app-serviceslayer. The only non-business-logic classes allowed are the framework's own building blocks — controllers, jobs, console commands, listeners, events, Livewire components, middleware, FormRequests, Mailables, Notifications, policies, service providers, customRuleclasses, Enums, DTOs, Eloquent models, and framework boilerplate. All other logic must be split by responsibility into the dedicated classes defined bypekral/arch-app-services— Actions, Model Services (Pekral\Arch\Service\BaseModelService), Repositories (Pekral\Arch\Repository\Mysql\BaseRepository), ModelManagers (Pekral\Arch\ModelManager\Mysql\BaseModelManager), Data Validators (Pekral\Arch\DataValidation\DataValidator), and Data Builders (Pekral\Arch\DataBuilder\DataBuilder). Introducing an ad-hoc class that is neither a Laravel-native type nor one of these arch-app-services layers (a bareHelper,Manager,Handler,Util,Processor,Builder,Mapper,Validator,Servicethat does not extendBaseModelService, etc.) to host business logic is forbidden — move that logic into the correct layer above. An application-owned Facade is never one of those homes — the service layer caps atBaseModelService, see Model Services → No application Facades. - Actions return plain domain data, never HTTP responses. An Action's
__invoke()returns a domain value (a Model, a DTO, a Collection, a scalar,void) — never anIlluminate\Http\Response/JsonResponse/RedirectResponse, and never the result ofresponse(),response()->json(),redirect(),back(),view(), or any other HTTP-response builder. Translating domain data into an HTTP response (status code, headers, JSON envelope, redirect) is always the controller's job — the controller is the single owner of client↔server communication. Jobs, commands, and listeners likewise consume the Action's domain return value directly.
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.
- yesterday First seen · 344 lines · 0 tokens per session scan A 8e1ce40236c9
architecture is a cursor rule published in the GitHub repository pekral/cursor-rules (6 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 14,929 tokens. 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 cursor rules, from other repositories
owl-admin
🎈 Owl Admin : 基于 laravel 和 amis 开发的后台框架, 友好的组件使用体验, 可轻松实现复杂页面, 内置代码生成器, 让开发者快速搭建后台管理系统.
16-wechat-sdk
微信 SDK 接入规范(EasyWeChat / WechatManager).
15-config-center
动态配置中心读取规范(ConfigCenter / configcenter).
lean
Answer densely. Cut filler, keep all technical signal.
00-project
基于 Laravel + Blade + Vue3 + Element Plus 的轻量级后台管理系统.
99-guard
Cursor rule "99-guard" from neoshopcn/neo-admin, covering 🔒 protected directories(禁止修改), ⚠️ conditional(仅在明确要求时允许) and 🚫 dangerous operations(禁止主动执行).