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 skills/divinevideo/divine-mobile/cloudsql-idle-connection-timeoutnpx skills add divinevideo/divine-mobile --skill cloudsql-idle-connection-timeoutgit clone --depth 1 https://github.com/divinevideo/divine-mobileWhat 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 | $0.00127 | $0.01063 |
| Opus 5 | $0.00063 | $0.00531 |
| Sonnet 5 | $0.00025 | $0.00213 |
| Haiku 4.5 | $0.00013 | $0.00106 |
Grade A, and why
cloudsql-idle-connection-timeout 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 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.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud SQL Idle Connection Timeout Fix
Problem
Cloud SQL (and other managed PostgreSQL services) kill idle connections after a timeout (typically 10 minutes). Long-running scripts that open a DB connection early, then perform non-DB work (HTTP requests, file I/O, CDX scanning), then try to use the DB connection again will get a misleading error.
Context / Trigger Conditions
psycopg2.OperationalError: could not receive data from server: Operation timed outpsycopg2.InterfaceError: connection already closed- Script has phases: DB setup → long non-DB work → DB writes
- Using Google Cloud SQL, AWS RDS, or Azure Database for PostgreSQL
- Connection was working initially, fails after idle period
- The error appears AFTER a phase that doesn't use the DB (e.g., API crawling, file processing)
Solution
Pattern 1: Defer DB Connection (Preferred)
Structure code so the DB connection opens AFTER the non-DB phase:
# BAD: Connection opens before long CDX scan
with VineDatabase() as db:
ensure_schema(db)
results = long_running_api_scan() # 5-10 minutes, no DB needed
process_results(db, results) # Connection dead here!
# GOOD: CDX scan first, then fresh DB connection
results = long_running_api_scan() # No DB connection open
with VineDatabase() as db: # Fresh connection when actually needed
ensure_schema(db)
process_results(db, results)
Pattern 2: Reconnection Logic (For Long Batch Operations)
For operations that DO use the DB but might exceed the idle timeout between writes:
import psycopg2
def reconnect_db():
"""Create a fresh database connection."""
db = VineDatabase()
cursor = db._cursor()
return db, cursor
def process_batch(db, cursor, items):
for item in items:
data = fetch_from_api(item) # Slow network call
try:
cursor.execute("INSERT INTO ...", data)
db.conn.commit()
except (psycopg2.OperationalError, psycopg2.InterfaceError):
# Connection died, reconnect and retry
try:
db.close()
except Exception:
pass
db, cursor = reconnect_db()
cursor.execute("INSERT INTO ...", data)
db.conn.commit()
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 · 125 lines · 127 tokens per session scan A 30e1b680c4cb
cloudsql-idle-connection-timeout is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed 3d ago), licensed MPL-2.0. It adds 127 tokens to every session and 1,063 once invoked, about $0.0006 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 skills, from other repositories
azure-resource-manager-postgresql-dotnet
Azure PostgreSQL Flexible Server SDK for .NET. Database management for PostgreSQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "PostgreSQL", "PostgreSqlFlexibleServer", "PostgreSQL Flexible Server", "Azure Database for…
stripe-projects
Use when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database", "set up auth", "add caching", "give me a Postgres", "provision Redis", "I need hosting", "add a vector DB", "get me an API key for X", "get credentials for X", "sign up for a service", "set…
neon-postgres-branches
Choose and create the right Neon branch type for testing and development. Use when users ask about Neon branching, migration testing with real data, isolated test environments, schema-only branch workflows for sensitive data, resetting a branch from its parent, branch expiration and CI/CD branch lifecycles, or branch…
aws-essentials
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…
add-backup-db
Add automated Neon database backups to the current project. Registers the project as a snapshot target of the unified shared Cloudflare Worker "hypervibe-jobs" (one Worker per account for ALL background jobs, reused across projects) that creates point-in-time Neon branch snapshots every 2 weeks. Retention - rolling (2…
database-rds-devops
Database-level data-plane diagnostics for Aurora MySQL and Aurora PostgreSQL. Executes predefined read-only health check queries via RDS Data API to analyze buffer pool, connections, locks, replication, storage, performance, and index efficiency. Requires the rds-aidba MCP server for database-internal access beyond…