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.
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/420-gcp)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/420-gcp"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/420-gcp.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 | $0.00019 | $0.04830 |
| Opus 5 | $0.00010 | $0.02415 |
| Sonnet 5 | $0.00004 | $0.00966 |
| Haiku 4.5 | $0.00002 | $0.00483 |
Grade A, and why
420-gcp 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 7d 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 — 884 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Cloud Platform (GCP) Best Practices
Guiding Principles
- Cloud-Native Services: Leverage GCP-managed services (Cloud Run, Cloud Functions, GKE Autopilot)
- Infrastructure as Code: Terraform for GCP resources, Cloud Build for CI/CD
- Security First: IAM with service accounts, Secret Manager, VPC Service Controls
- Cost Efficiency: Committed use discounts, preemptible VMs, auto-scaling
- Observability: Cloud Logging, Cloud Monitoring, Cloud Trace
GCP Resource Naming Convention
Standard Format
{resource-type}-{project}-{environment}-{region}-{instance}
Examples
# Compute Instance
vm-webapp-prod-us-central1-001
# Cloud Storage Bucket (globally unique)
acme-webapp-prod-storage
# Cloud Run Service
webapp-prod-us-central1
# Cloud Function
function-process-images-prod
# GKE Cluster
gke-webapp-prod-us-central1
# Cloud SQL Instance
sql-webapp-prod-us-central1-001
# VPC Network
vpc-webapp-prod
Terraform for GCP
Provider Configuration
# versions.tf
terraform {
required_version = ">= 1.12"
required_providers {
google = {
source = "hashicorp/google"
version = "~> 5.0"
}
google-beta = {
source = "hashicorp/google-beta"
version = "~> 5.0"
}
}
backend "gcs" {
bucket = "acme-terraform-state"
prefix = "webapp/prod"
}
}
provider "google" {
project = var.project_id
region = var.region
}
provider "google-beta" {
project = var.project_id
region = var.region
}
Cloud Run Service
# cloud-run.tf
resource "google_cloud_run_v2_service" "webapp" {
name = "webapp-${var.environment}"
location = var.region
template {
scaling {
min_instance_count = var.environment == "prod" ? 2 : 0
max_instance_count = var.environment == "prod" ? 100 : 10
}
containers {
image = "gcr.io/${var.project_id}/webapp:${var.image_tag}"
resources {
limits = {
cpu = "1000m"
memory = "512Mi"
}
cpu_idle = true
}
ports {
container_port = 8080
}
env {
name = "ENVIRONMENT"
value = var.environment
}
env {
name = "DATABASE_URL"
value_source {
secret_key_ref {
secret = google_secret_manager_secret.db_url.secret_id
version = "latest"
}
}
}
startup_probe {
http_get {
path = "/health"
port = 8080
}
initial_delay_seconds = 5
period_seconds = 10
failure_threshold = 3
}
liveness_probe {
http_get {
path = "/health"
port = 8080
}
period_seconds = 30
failure_threshold = 3
}
}
service_account = google_service_account.webapp.email
}
traffic {
type = "TRAFFIC_TARGET_ALLOCATION_TYPE_LATEST"
percent = 100
}
depends_on = [google_project_service.cloudrun]
}
# IAM for Cloud Run (public or authenticated)
resource "google_cloud_run_service_iam_member" "public" {
count = var.allow_public_access ? 1 : 0
service = google_cloud_run_v2_service.webapp.name
location = google_cloud_run_v2_service.webapp.location
role = "roles/run.invoker"
member = "allUsers"
}
# Output the service URL
output "cloud_run_url" {
value = google_cloud_run_v2_service.webapp.uri
}
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.
- 7d ago First seen · 884 lines · 19 tokens per session scan A 79a3a54684e0
420-gcp is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 4,830 once invoked, about $0.0001 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
aws-ecs
Definitive guidelines for building, deploying, and operating applications on AWS ECS, emphasizing immutable containers, secure secrets management, and robust operational patterns.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
aws-rds-best-practices
AWS RDS PostgreSQL best practices - database configuration, connection management, authentication, backup, and performance optimization standards.
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.