integrations

A set of rules for connecting an application to outside services, such as AI providers. It defines how to translate their responses, handle repeated requests, isolate failures, and record useful operating information.

In plain words
What is it for?
Use it when adding or changing an external integration, including response types, retry decisions, duplicate-request handling, resource limits, and monitoring.
Why use it?
It keeps vendor-specific details out of the rest of the application and makes failures safer to handle. This reduces the amount of code affected when an outside service changes.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/yerdaulet-damir/vibe-coding-rules/integrations
Clone the repo
git clone --depth 1 https://github.com/yerdaulet-damir/vibe-coding-rules

Made for: Cursor.

Per session 2,188 This file is loaded in full into every session.
When invoked 2,188 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02188 $0.02188
Opus 5 $0.01094 $0.01094
Sonnet 5 $0.00438 $0.00438
Haiku 4.5 $0.00219 $0.00219

Measured 2d ago against content hash 031a833bd748, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integrations 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 2d 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.

.cursor/rules/integrations.mdc · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

External Integration Rules

Every external boundary in this codebase is shaped by 5 rules. Apply them every time you add or modify an integration.

1. Anti-Corruption Layer (ACL): provider returns GenerateResult | ProviderError

Provider adapters MUST translate vendor responses into our domain types. Never return dict, never let the vendor's field names cross the boundary.

# app/providers/_types.py
from dataclasses import dataclass
from decimal import Decimal

@dataclass(frozen=True)
class GenerateResult:
    url: str
    cost_usd: Decimal
    latency_ms: int
    provider_request_id: str

class ProviderError(Exception):
    def __init__(self, message: str, *, retryable: bool, code: str | None = None):
        super().__init__(message); self.retryable = retryable; self.code = code

class ProviderTimeout(ProviderError):
    def __init__(self, message: str): super().__init__(message, retryable=True, code="timeout")

class ProviderQuotaExceeded(ProviderError):
    def __init__(self, message: str): super().__init__(message, retryable=False, code="quota")

class ProviderInvalidRequest(ProviderError):
    def __init__(self, message: str): super().__init__(message, retryable=False, code="invalid_request")
# ✅ GOOD — adapter maps to ACL
class FalImageAdapter:
    def __init__(self, client: FalClient): self._c = client

    async def generate(self, req: ImageRequest) -> GenerateResult | ProviderError:
        try:
            data = await self._c.request("/v1/image", req.model_dump())
        except httpx.TimeoutException as e:
            return ProviderTimeout(str(e))
        except httpx.HTTPStatusError as e:
            if e.response.status_code == 429:
                return ProviderQuotaExceeded(e.response.text)
            return ProviderError(e.response.text, retryable=False, code=str(e.response.status_code))
        return GenerateResult(
            url=data["images"][0]["url"],
            cost_usd=Decimal(str(data["billing"]["cost_usd"])),
            latency_ms=int(data["meta"]["latency_ms"]),
            provider_request_id=data["request_id"],
        )

Read the full file on GitHub · 254 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. 2d ago First seen · 254 lines · 2,188 tokens per session scan A 031a833bd748

Subscribe to this mod's changes

integrations is a cursor rule published in the GitHub repository yerdaulet-damir/vibe-coding-rules (10 stars, last pushed 3mo ago), licensed MIT. It adds 2,188 tokens to every session, about $0.0109 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 2026-08-31.