cloud-sql-postgres-vectorassist

A toolkit for setting up and tuning vector search workloads in PostgreSQL databases, including applying recommended database changes.

In plain words
What is it for?
Use it to define or change vector-search specifications, review recommendations, and apply those recommendations to a PostgreSQL database.
Why use it?
It removes the need to manually translate vector-search requirements into database commands and run them in the right order.

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

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,148 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 $0.00029 $0.02148
Opus 5 $0.00015 $0.01074
Sonnet 5 $0.00006 $0.00430
Haiku 4.5 $0.00003 $0.00215

Measured yesterday against content hash 2946c5700723, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloud-sql-postgres-vectorassist 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 yesterday.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/apply_spec.js, scripts/define_spec.js, scripts/execute_sql.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.

skills/cloud-sql-postgres-vectorassist/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 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

apply_spec

This tool automatically executes all the SQL recommendations associated with a specific vector specification (spec_id) or table. It runs the necessary commands in the correct sequence to provision the workload, marking each step as applied once successful. Use this tool when the user has reviewed the generated recommendations from a defined (or modified) spec and is ready to apply the changes directly to their database instance to finalize the vector search setup. This tool can be used as a follow-up action after invoking the 'define_spec' or 'modify_spec' tool.

Parameters
Name Type Description Required Default
spec_id string The unique ID of the vector specification to apply. No
table_name string The name of the table to apply the vector specification to (in case of a single spec defined on the table). No
column_name string The text_column_name or vector_column_name of the spec to identify the exact spec in case there are multiple specs defined on a table. No
schema_name string The schema name for the table. No

define_spec

This tool defines a new vector specification by capturing the user's intent and requirements for a vector search workload. This generates a complete, ordered set of SQL recommendations required to set up the database, embeddings, and vector indexes. While highly customizable, any optional parameters left unspecified will use internally determined defaults optimized for the specific workload. Use this tool at the very beginning of the vector setup process when a user first wants to configure a table for vector search, generate embeddings, or create a new vector index.

Read the full file on GitHub · 132 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 132 lines · 29 tokens per session scan A 2946c5700723

Subscribe to this mod's changes

cloud-sql-postgres-vectorassist is a skill published in the GitHub repository gemini-cli-extensions/cloud-sql-postgresql (42 stars, last pushed 4d ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,148 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.