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.
git clone --depth 1 https://github.com/meishanlaoyao/elysia-adminWrote 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.
[](https://agentmods.dev/rules/meishanlaoyao/elysia-admin/general)<a href="https://agentmods.dev/rules/meishanlaoyao/elysia-admin/general"><img src="https://agentmods.dev/badge/rules/meishanlaoyao/elysia-admin/general.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01503 | $0.01503 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
general 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 7d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
Full-stack admin: Vue 3 + TypeScript (admin/) + Elysia + Bun (server/). Layer layout: .ai/AI_STRUCTURE.md.
Dependency Direction (Strict)
admin → server (HTTP only)
modules → core
modules → shared
modules → infrastructure
modules → other modules' exported handle functions (PascalCase cross-module API only)
core ✗→ modules
shared ✗→ modules
infrastructure ✗→ modules (sandbox via worker-sandbox/, not infrastructure → modules)
modules ✗→ other modules' @database/schema (cross-table data via owner exported handle function)
shared ✗→ core/database (cron + Redis lock: server/src/infrastructure/cron/cron-scheduler.ts)
Server types: server/src/types/*.ts = importable types; server/src/types/ambient/*.d.ts = ambient only.
Generation Principles
- Explain plan in max 5 lines before writing code
- List files to create or modify
- Generate minimal code — no extra abstraction
- Follow existing patterns (backend →
.ai/AI_CODE_EXAMPLES_BACKEND.md; frontend →.ai/AI_CODE_EXAMPLES_FRONTEND.md) - Do NOT introduce new dependencies
- Do NOT refactor unrelated files
- Ask before modifying database schema
- No over-engineering
dto.tsvalidation: every validated field must includeerrorwith a readable Chinese user-facing message (error, noterrorMessage) — seeserver/AGENTS.md/ backend examples- Soft delete & uniqueness: uniqueness checks MUST account for soft-deleted rows; new unique constraints → partial unique index
WHERE del_flag = false - Form validation both sides: frontend
rules+ backenddto.tswith Chineseerror handle.tsJSDoc: every exported function needs purpose +@param/@returns; non-trivial flows list numbered steps- Rule-file language: when editing English AI rule docs (
.ai/, IDE rules), write new/changed prose in English (this edit only — no bulk translate). Chinese OK for product copy and listed trigger phrases; identifiers (dict_type,permission,path, …) stay English dict_typenaming: short semantic Englishsnake_case(prefer 2–3 segments /goods_status); reuse via MCP; skip dict for pure boolean —.ai/AI_HANDOFF_SQL.md
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.
- 7d ago First seen · 121 lines · 1,503 tokens per session scan A 0ac95bba9fa2
general is a cursor rule published in the GitHub repository meishanlaoyao/elysia-admin (49 stars, last pushed 2d ago), licensed MIT. It adds 1,503 tokens to every session, about $0.0075 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.