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/meishanlaoyao/elysia-admin/backendgit 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/backend)<a href="https://agentmods.dev/rules/meishanlaoyao/elysia-admin/backend"><img src="https://agentmods.dev/badge/rules/meishanlaoyao/elysia-admin/backend.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 | $0.00000 | $0.02036 |
| Opus 5 | $0.00000 | $0.01018 |
| Sonnet 5 | $0.00000 | $0.00407 |
| Haiku 4.5 | $0.00000 | $0.00204 |
Grade A, and why
backend 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 6d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Module Structure
Every module under server/src/modules/{group}-{name}/ should contain:
modules/{group}-{name}/
dto.ts ← Elysia validation + route DTO fragments; optional afterHandle hooks
handle.ts ← business logic only
route.ts ← HTTP mapping only
task.ts ← BullMQ / sandbox worker exports (optional; omit if no tasks)
No extra files. No renaming. Routes auto-register on startup.
task.ts: add only when registering queue/cron jobs in server/src/worker-sandbox/.
Cross-module handle (Cross-Table Data Access):
- Each module may directly query only its own table schemas.
- To access another module's table, call the owning module's exported PascalCase function from its
handle.ts— do NOT import that module's@database/schema. - Route handlers = lower camelCase (
create,findList); cross-module exports = PascalCase (GetUserBy,GetDeptInfoById). - If the helper is missing, add it in the owning module first, then import it from the consumer.
- New business modules should stay self-contained; avoid mesh dependencies.
Layer Rules (Strict)
| File | Allowed | Forbidden |
|---|---|---|
dto.ts |
Elysia schema, response DTO, optional hooks | complex orchestration, direct DB |
handle.ts |
own-module schema + repository, QueryBuilder, shared, infrastructure; other modules' exported handle functions | raw SQL, direct pg, new Elysia in handle, importing other modules' @database/schema for cross-table queries |
route.ts |
bind dto+handle, return result | business logic, DB access |
task.ts |
export plain functions, call handle | duplicate business logic, direct DB |
Repository Functions (from @/core/database/repository)
InsertOne(schema, ctx) // insert, no return
InsertOneAndRes(schema, ctx) // insert, return record
InsertMany(schema, ctx, dataArray) // bulk insert
FindOneByKey(schema, 'primaryKey', value) // find by key
FindAll(schema, whereSQL, options?) // find all (no pagination)
FindPage(schema, whereSQL, paginationOptions) // paginated query
UpdateByKey(schema, 'primaryKey', ctx) // update by key
UpdateByKeyAndRes(schema, 'primaryKey', ctx) // update, return record
SoftDeleteByKeys(schema, 'primaryKey', ctx) // soft delete (sets delFlag=true)
HardDelete(schema, whereSQL) // permanent delete
HardDeleteByKeys(schema, 'primaryKey', values) // permanent delete by keys
FindAllWithJoin(schema, builder, options?) // find all with join
FindPageWithJoin(schema, builder, options) // paginated with join
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.
- 6d ago First seen · 191 lines · 0 tokens per session scan A 6bf308b96faa
backend is a cursor rule published in the GitHub repository meishanlaoyao/elysia-admin (49 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,036 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 2026-08-30.
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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.