alloydb-postgres-admin

A set of tools for managing AlloyDB for PostgreSQL, Google's managed PostgreSQL-compatible database service. It can create clusters and instances, monitor creation, and retrieve basic configuration or health information.

In plain words
What is it for?
Use it to create an AlloyDB cluster in a Google Cloud project, track the operation, and inspect its configuration or health.
Why use it?
It helps avoid handling database provisioning and status checks manually through separate cloud commands.

Skill for Claude CodeCodex

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 skills/gemini-cli-extensions/alloydb/alloydb-postgres-admin
Any agent
npx skills add gemini-cli-extensions/alloydb --skill alloydb-postgres-admin
Clone the repo
git clone --depth 1 https://github.com/gemini-cli-extensions/alloydb

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,439 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00039 $0.01439
Opus 5 $0.00019 $0.00720
Sonnet 5 $0.00008 $0.00288
Haiku 4.5 $0.00004 $0.00144

Measured 2d ago against content hash f4c966b5f63d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alloydb-postgres-admin 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.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/create_cluster.js, scripts/create_instance.js, scripts/database_overview.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/alloydb-postgres-admin/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage

All scripts can be executed using Node.js. Replace <param_name> and <param_value> with actual values.

Bash: node <skill_dir>/scripts/<script_name>.js '{"<param_name>": "<param_value>"}'

PowerShell: node <skill_dir>/scripts/<script_name>.js '{\"<param_name>\": \"<param_value>\"}'

Note: The scripts automatically load the environment variables from various .env files. Do not ask the user to set vars unless skill executions fails due to env var absence.

Scripts

create_cluster

Creates a new AlloyDB cluster. This is a long-running operation, but the API call returns quickly. This will return operation id to be used by get operations tool. Take all parameters from user in one go.

Parameters
Name Type Description Required Default
project string The GCP project ID. This is pre-configured; do not ask for it unless the user explicitly provides a different one. No
location string The location to create the cluster in. The default value is us-central1. If quota is exhausted then use other regions. No us-central1
cluster string A unique ID for the AlloyDB cluster. Yes
password string A secure password for the initial user. Yes
network string The name of the VPC network to connect the cluster to (e.g., 'default'). No default
user string The name for the initial superuser. Defaults to 'postgres' if not provided. No

create_instance

Creates a new AlloyDB instance (PRIMARY or READ_POOL) within a cluster. This is a long-running operation. This will return operation id to be used by get operations tool. Take all parameters from user in one go.

Parameters
Name Type Description Required Default
project string The GCP project ID. This is pre-configured; do not ask for it unless the user explicitly provides a different one. No
location string The location of the cluster (e.g., 'us-central1'). Yes
cluster string The ID of the cluster to create the instance in. Yes
instance string A unique ID for the new AlloyDB instance. Yes
instanceType string The type of instance to create. Valid values are: PRIMARY and READ_POOL. Default is PRIMARY No PRIMARY
displayName string An optional, user-friendly name for the instance. No
nodeCount integer The number of nodes in the read pool. Required only if instanceType is READ_POOL. Default is 1. No 1

Read the full file on GitHub · 142 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 · 142 lines · 39 tokens per session scan A f4c966b5f63d

Subscribe to this mod's changes

alloydb-postgres-admin is a skill published in the GitHub repository gemini-cli-extensions/alloydb (22 stars, last pushed 5d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,439 once invoked, about $0.0002 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.