Sia: Instructions file for Kiro

.kiro/steering/backend-guidelines.md

Sia backend-guidelines.md is an instructions file for Kiro from GetPullRequest/Sia. It costs 951 tokens per session, scanned A, original, MIT.

A project-specific backend guide for Sia's server code and communication systems. It describes Fastify REST endpoints, WebSocket log streaming, gRPC communication with agents, PostgreSQL with Drizzle, Temporal workflows, and authentication.

In plain words
What is it for?
Use it when building or modifying Sia API routes, live job-log streams, agent communication, database access, durable workflows, or authentication-related backend code.
Why use it?
It gives backend work a consistent structure and clarifies which technology handles each kind of communication or data operation. This reduces the risk of using the wrong channel or framework for a feature.

Instructions file for Kiro

Written for Kiro: installed under .kiro/.

This is GetPullRequest/Sia's own configuration. It tells Kiro how to work on Sia itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Sia configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GetPullRequest/Sia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GetPullRequest/Sia/main/.kiro/steering/backend-guidelines.md
Clone the repo
git clone --depth 1 https://github.com/GetPullRequest/Sia

Made for: Kiro.

Wrote 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.

agentmods badge for Sia backend-guidelines.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/getpullrequest/sia/backend-guidelines/github.svg)](https://agentmods.dev/instructions/getpullrequest/sia/backend-guidelines)
Your own site
<a href="https://agentmods.dev/instructions/getpullrequest/sia/backend-guidelines"><img src="https://agentmods.dev/badge/instructions/getpullrequest/sia/backend-guidelines/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.

agentmods 80×15 button for Sia backend-guidelines.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/getpullrequest/sia/backend-guidelines"><img src="https://agentmods.dev/badge/instructions/getpullrequest/sia/backend-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 951 This file is loaded in full into every session.
When invoked 951 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00951 $0.00951
Opus 5.5 $0.00380 $0.00380
Sonnet 5.5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured 1mo ago against content hash 2e3a72ace2c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Sia backend-guidelines.md 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.

.kiro/steering/backend-guidelines.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Development Guidelines (apps/api)

Technology Stack

  • Framework: Fastify for REST APIs
  • Real-time: WebSocket for streaming logs during job execution
  • Agent Communication: gRPC streaming for backend-agent communication
  • Database: PostgreSQL with Drizzle ORM
  • Workflows: Temporal for durable task orchestration
  • Auth: PropelAuth for authentication
  • Language: TypeScript with strict typing

REST API - Fastify

// routes/jobs/index.ts
import { FastifyPluginAsync } from 'fastify';

const jobRoutes: FastifyPluginAsync = async fastify => {
  fastify.get(
    '/',
    {
      schema: {
        response: {
          200: JobListSchema,
        },
      },
    },
    async (request, reply) => {
      const jobs = await jobService.list(request.orgId);
      return jobs;
    }
  );
};

WebSocket - Log Streaming

Use WebSocket for streaming job logs to the frontend in real-time:

// services/websocket-manager.ts
export class WebSocketManager {
  broadcastLog(jobId: string, log: LogEntry) {
    const subscribers = this.jobSubscribers.get(jobId);
    subscribers?.forEach(ws => ws.send(JSON.stringify(log)));
  }
}

gRPC - Agent Communication

Use gRPC bidirectional streaming for backend-agent communication:

// grpc/agent-server.ts
// Agent connects and streams job updates
// Backend streams job assignments

Proto definitions are in libs/models/src/proto/.

TypeScript Guidelines

  • Always use explicit types - avoid any and unknown
  • Exception: External library callbacks where types aren't available
  • Exception: Fastify request/reply generics in some cases
  • Define interfaces for all request/response bodies
// ✅ Good
interface CreateJobRequest {
  prompt: string;
  repoId: string;
  queueType: 'backlog' | 'rework';
}

// ❌ Avoid
const handleRequest = (data: any) => { ... }

Database - Drizzle ORM

// db/schema.ts
export const jobs = pgTable('jobs', {
  id: uuid('id').primaryKey().defaultRandom(),
  status: jobStatusEnum('status').notNull(),
  prompt: text('prompt').notNull(),
  // ...
});

// Usage
const job = await db.query.jobs.findFirst({
  where: eq(jobs.id, jobId),
});

Read the full file on GitHub · 167 lines

Changes

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.

  1. 1mo ago First seen · 167 lines · 951 tokens per session scan A 2e3a72ace2c8

Subscribe to this mod's changes

Sia backend-guidelines.md is an instructions file published in the GitHub repository GetPullRequest/Sia (5 stars, last pushed 1mo ago), licensed MIT. It adds 951 tokens to every session, about $0.0038 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 2026-09-16.

Related

Sia backend-guidelines.md compared with instructions from other repositories

Sia backend-guidelines.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Sia backend-guidelines.mdGetPullRequest/SiaInstructions file51mo agoMITA951Kiro
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode