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/neondatabase/ai-rules/neon-api-endpointsgit clone --depth 1 https://github.com/neondatabase/ai-rulesWhat 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 | $0.00014 | $0.05880 |
| Opus 5 | $0.00007 | $0.02940 |
| Sonnet 5 | $0.00003 | $0.01176 |
| Haiku 4.5 | $0.00001 | $0.00588 |
Grade A, and why
neon-api-endpoints scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl 'https://console.neon.tech/api/v2/projects/hidden-river-50598307/endpoints' \ How it starts
The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This section provides rules for managing compute endpoints associated with branches in a project. Compute endpoints are Neon compute instances that allow you to connect to and interact with your databases.
Manage compute endpoints
Create compute endpoint
- Action: Creates a new compute endpoint (a Neon compute instance) and associates it with a specified branch.
- Endpoint:
POST /projects/{project_id}/endpoints - Path Parameters:
project_id(string, required): The unique identifier of the project.
- Body Parameters:
endpoint(object, required): The container for the new endpoint's properties.branch_id(string, required): The ID of the branch to associate the endpoint with.type(string, required): The endpoint type. A branch can have only oneread_writeendpoint but multipleread_onlyendpoints. Allowed values:read_write,read_only.region_id(string, optional): The region where the endpoint will be created. Must match the project's region.autoscaling_limit_min_cu(number, optional): The minimum number of Compute Units (CU). Minimum0.25.autoscaling_limit_max_cu(number, optional): The maximum number of Compute Units (CU). Minimum0.25.provisioner(string, optional): The compute provisioner. Specifyk8s-neonvmto enable Autoscaling. Allowed values:k8s-pod,k8s-neonvm.suspend_timeout_seconds(integer, optional): Duration of inactivity in seconds before suspending the compute. Ranges from -1 (never suspend) to 604800 (1 week).disabled(boolean, optional): Iftrue, restricts connections to the endpoint.
Example Request:
curl 'https://console.neon.tech/api/v2/projects/hidden-river-50598307/endpoints' \
-H 'Accept: application/json' \
-H "Authorization: Bearer $NEON_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"endpoint": {
"branch_id": "br-your-branch-id",
"type": "read_only"
}
}'
Example Response:
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 · 562 lines · 14 tokens per session scan A 46f36fd10ed7
neon-api-endpoints is a cursor rule published in the GitHub repository neondatabase/ai-rules (86 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 5,880 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-rds
Definitive guidelines for secure, performant, and maintainable database development and operations with AWS RDS, emphasizing modern best practices and common anti-patterns.
aws-dynamodb
Provides definitive best practices and actionable code examples for interacting with AWS DynamoDB using the AWS SDK v3, focusing on data modeling, performance, security, and common pitfalls.
edgeone-makers-storage
KV and Blob storage services on EdgeOne Makers. KV for edge key-value pairs, Blob for file/object storage in Cloud Functions. Covers SDK usage, setup, and troubleshooting.
aws-opensearch-best-practices
AWS OpenSearch best practices - domain configuration, index management, query optimization, access control, and audit logging standards.
aws-rds-best-practices
AWS RDS PostgreSQL best practices - database configuration, connection management, authentication, backup, and performance optimization standards.
netlify-database
Zero-config Postgres for Netlify apps via @netlify/database — querying data from Functions/Edge Functions, writing schema migrations, setting up Drizzle ORM, local dev with netlify dev, database branches for deploy previews, and migrating an existing Postgres project onto Netlify. Use when adding a database, building…