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/caioribeiroclw-pixel/pluribus/cursorrulesgit clone --depth 1 https://github.com/caioribeiroclw-pixel/pluribusWrote 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/caioribeiroclw-pixel/pluribus/cursorrules)<a href="https://agentmods.dev/rules/caioribeiroclw-pixel/pluribus/cursorrules"><img src="https://agentmods.dev/badge/rules/caioribeiroclw-pixel/pluribus/cursorrules.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 | $0.00829 | $0.00829 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
cursorrules 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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by Pluribus 0.1.0 on 2026-03-08 — do not edit manually
Source: pluribus.md | Skill: cursor
Project: Orbital — Multi-tenant logistics SaaS
Project Overview
You are assisting the Orbital engineering team — 5 backend engineers building a multi-tenant SaaS for logistics operations. TypeScript monorepo using NestJS, PostgreSQL (drizzle-orm), and BullMQ. All engineers use shared conventions.
Tech Stack
- TypeScript 5.4 (strict mode) + Node.js 22 LTS
- NestJS 10 with Fastify adapter
- PostgreSQL 16 via drizzle-orm (NO raw SQL in application code)
- BullMQ + Redis 7 for job queues
- Jest 29 + Supertest for testing
- pnpm workspaces monorepo
- ESLint flat config + Prettier (2-space, single quotes, trailing commas)
Code Conventions
async/awaitonly — never.then()/.catch()- No
any— useunknownwith explicit narrowing - Named exports only — no default exports, no barrel files
- File naming:
kebab-case.ts - NestJS pattern:
<feature>.module.ts,<feature>.service.ts,<feature>.controller.ts - Error handling: always use
AppErrorfrompackages/core/errors— never throw plain strings or genericError - No circular dependencies (enforced by ESLint)
- No
@ts-ignoreor@ts-expect-error
Testing
- Unit tests for all service methods with side effects
- Integration tests for all controller endpoints via Supertest
- Use test factories from
test/factories/— never construct objects manually in tests - Inject mocks via DI — no module-level
jest.mock() - Test naming:
describe('<Unit>', () => { it('should <behavior> when <condition>', ...) })
Pull Requests
- PRs must be < 400 lines (excluding generated files and migrations)
- Every PR needs at least one test covering the new behavior
- Migrations must be reviewed by Ana (
@ana/tech-lead) before merge - No self-merging — minimum 1 approval required
- Fill the PR description template: What, Why, How, Risk, Test plan
AI Review Rules
When reviewing code:
- Check for correctness, type safety, and convention violations (not style — Prettier handles that)
- Flag missing error handling in async paths
- Flag raw SQL outside drizzle-orm
- Flag new endpoints without integration tests
- Flag new endpoints without declared RBAC role
- Never suggest approving a PR with failing CI
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.
- 3d ago First seen · 82 lines · 829 tokens per session scan A 89f031f6d78b
cursorrules is a cursor rule published in the GitHub repository caioribeiroclw-pixel/pluribus (11 stars, last pushed 1mo ago), licensed MIT. It adds 829 tokens to every session, about $0.0041 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
postgresql
Cursor rule "postgresql" from ItamarZand88/awesome-agent-conventions, covering postgresql rules, schema, queries, indexes and migrations.
postgres
Postgres/Supabase roof — RLS, queries, migrations. Index only.
30-database-postgres
PostgreSQL and persistence rules.
supabase-migrations
You are a Postgres Expert who loves creating secure database schemas.
supabase
Supabase best practices for Auth, Database, RLS, Edge Functions, and Realtime.
cursorrules
DO NOT run command to run or restart the server, always assume that server is running at port 3000.