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/neondatabase/ai-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/neondatabase/ai-rules/neon-api-projects)<a href="https://agentmods.dev/rules/neondatabase/ai-rules/neon-api-projects"><img src="https://agentmods.dev/badge/rules/neondatabase/ai-rules/neon-api-projects/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/neondatabase/ai-rules/neon-api-projects"><img src="https://agentmods.dev/badge/rules/neondatabase/ai-rules/neon-api-projects.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 | $0.00021 | $0.06506 |
| Opus 5.5 | $0.00008 | $0.02602 |
| Sonnet 5.5 | $0.00004 | $0.01301 |
| Haiku 4.5 | $0.00002 | $0.00651 |
Grade A, and why
neon-api-projects 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 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.
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?limit=10' \ How it starts
The opening of the file, as written. The whole thing — 581 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This document outlines the rules for managing Neon projects programmatically. It covers creation, retrieval, updates, and deletion.
Manage projects
List projects
- Action: Retrieves a list of all projects accessible to the account associated with the API key. This is the primary method for obtaining
project_idvalues required for other API calls. - Endpoint:
GET /projects - Query Parameters:
limit(optional, integer, default: 10): Specifies the number of projects to return, from 1 to 400.cursor(optional, string): Used for pagination. Provide thecursorvalue from a previous response to fetch the next set of projects.search(optional, string): Filters projects by a partial match on the projectnameorid.org_id(optional, string): Filters projects by a specific organization ID.
- When iterating through all projects, use a combination of the
limitandcursorparameters to handle pagination correctly.
Example request:
# Retrieve the first 10 projects
curl 'https://console.neon.tech/api/v2/projects?limit=10' \
-H 'Accept: application/json' \
-H "Authorization: Bearer $NEON_API_KEY"
Example response:
{
"projects": [
{
"id": "old-fire-32990194",
"platform_id": "aws",
"region_id": "aws-ap-southeast-1",
"name": "old-fire-32990194",
"provisioner": "k8s-neonvm",
"default_endpoint_settings": {
"autoscaling_limit_min_cu": 0.25,
"autoscaling_limit_max_cu": 2,
"suspend_timeout_seconds": 0
},
"settings": {
"allowed_ips": {
"ips": [],
"protected_branches_only": false
},
"enable_logical_replication": false,
"maintenance_window": {
"weekdays": [5],
"start_time": "19:00",
"end_time": "20:00"
},
"block_public_connections": false,
"block_vpc_connections": false,
"hipaa": false
},
"pg_version": 17,
"proxy_host": "ap-southeast-1.aws.neon.tech",
"branch_logical_size_limit": 512,
"branch_logical_size_limit_bytes": 536870912,
"store_passwords": true,
"active_time": 0,
"cpu_used_sec": 0,
"creation_source": "console",
"created_at": "2025-09-10T06:58:33Z",
"updated_at": "2025-09-10T06:58:39Z",
"synthetic_storage_size": 0,
"quota_reset_at": "2025-10-01T00:00:00Z",
"owner_id": "org-royal-sun-91776391",
"compute_last_active_at": "2025-09-10T06:58:38Z",
"org_id": "org-royal-sun-91776391",
"history_retention_seconds": 86400
}
],
"pagination": {
"cursor": "old-fire-32990194"
},
"applications": {},
"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 · 581 lines · 21 tokens per session scan A 5e989ea25dd5
neon-api-projects is a cursor rule published in the GitHub repository neondatabase/ai-rules (86 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 6,506 once invoked, about $0.0001 per session on Opus 5.5. 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
482-snowflake
Snowflake warehouse, security, and query patterns (RBAC, cost/perf, streams/tasks, loading) for production data systems.
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…
cdk-infrastructure-data
CDK DynamoDB, SNS, SQS event source, DynamoDB Streams, RDS Proxy, idempotency table.
rds-proxy
RDS Proxy patterns - PostgreSQL connection pooling, Prisma integration, transaction handling, read replicas.
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.