Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/proyecto26/projectxnpx agentmods add rules/proyecto26/projectx/temporal-rulesWrote 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/proyecto26/projectx/temporal-rules)<a href="https://agentmods.dev/rules/proyecto26/projectx/temporal-rules"><img src="https://agentmods.dev/badge/rules/proyecto26/projectx/temporal-rules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/proyecto26/projectx/temporal-rules"><img src="https://agentmods.dev/badge/rules/proyecto26/projectx/temporal-rules.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02467 | $0.02467 |
| Opus 5.5 | $0.00987 | $0.00987 |
| Sonnet 5.5 | $0.00493 | $0.00493 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
temporal-rules 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 1mo 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Temporal Workflow Rules
Project Context
- This project uses Temporal.io for workflow orchestration
- Temporal Server version: 1.29.2
- Temporal Admin Tools: 1.29.1-tctl-1.18.4-cli-1.5.0
- Temporal UI: 2.44.1
- All services connect to Temporal for long-running business processes
Workflow Architecture
Workflow Locations
- Workflow definitions:
apps/*/src/workflows/ - Activity implementations:
apps/*/src/activities/ - Shared workflow utilities:
packages/workflows/src/lib/ - Temporal configuration:
apps/*/src/config/temporal.config.ts
Worker Configuration
- Each NestJS app runs its own Temporal worker
- Workers are initialized in the main application bootstrap
- Task queue is configured per service via environment variables
- Workers bundle workflows using Webpack
Workflow Patterns
Workflow Definition
import { proxyActivities } from '@temporalio/workflow';
import type { ActivitiesService } from '../main';
const activities = proxyActivities<ActivitiesService>({
startToCloseTimeout: '1 minute',
});
export async function myWorkflow(input: WorkflowInput): Promise<WorkflowOutput> {
// Workflow logic here
const result = await activities.myActivity(input);
return result;
}
Activity Definition
@Injectable()
export class ActivitiesService {
constructor(
private readonly prisma: PrismaService,
private readonly emailService: EmailService,
) {}
async myActivity(input: ActivityInput): Promise<ActivityOutput> {
// Activity logic with side effects
return result;
}
}
Critical Rules
Workflow Code Constraints
- ❌ NO direct database calls in workflows
- ❌ NO HTTP requests in workflows
- ❌ NO file I/O in workflows
- ❌ NO random number generation in workflows
- ❌ NO Date.now() or new Date() in workflows
- ✅ YES to deterministic logic only
- ✅ YES to calling activities for side effects
Use Activities For
- Database operations (Prisma queries)
- HTTP/API calls
- Email sending
- File operations
- Any non-deterministic operations
- External service integrations
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.
- 1mo ago First seen · 362 lines · 2,467 tokens per session scan A 5f13fec75f0f
temporal-rules is a cursor rule published in the GitHub repository proyecto26/projectx (83 stars, last pushed 6mo ago), licensed MIT. It adds 2,467 tokens to every session, about $0.0099 per session on Opus 5.5. 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
startup-framework
A standard for configuring and starting CodeSpirit API projects.
controller
A set of development rules for API controllers, the code that receives web requests and returns results. It covers controller attributes, routes, response formats, and operation attributes.
api-design
A set of development rules for REST APIs, which are web interfaces that let software exchange data using standard requests. It covers URL routes and response formats.
backend
Backend development rules for XX Chat AI using Fastify, server-sent events, provider integrations, and SQLite. Server-sent events are a way to stream updates from a server to a browser.
dto
A set of development rules for data transfer objects, or DTOs: structures used to move data between parts of an application. It covers validation, mapping, and multilingual support.
service
A standard for CodeSpirit service classes, including service interfaces, implementations, lifecycles, and dependency injection.