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/gemini-cli-extensions/cloud-sql-postgresql/cloud-sql-postgres-vectorassistnpx skills add gemini-cli-extensions/cloud-sql-postgresql --skill cloud-sql-postgres-vectorassistgit clone --depth 1 https://github.com/gemini-cli-extensions/cloud-sql-postgresqlWhat 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 | $0.00029 | $0.02148 |
| Opus 5 | $0.00015 | $0.01074 |
| Sonnet 5 | $0.00006 | $0.00430 |
| Haiku 4.5 | $0.00003 | $0.00215 |
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.
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 — 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.
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.
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.
- yesterday First seen · 132 lines · 29 tokens per session scan A 2946c5700723
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.
Other skills, from other repositories
looker
These skills are designed for data discovery and business intelligence.
looker-dev
These skills are built for LookML developers, data engineers, and administrators who manage the backbone of Looker.
firestore-data
Handles NoSQL document operations and collection hierarchy exploration. Use for CRUD tasks and data retrieval. Provides flexible document manipulation and structured querying.
knowledge-catalog-discovery
Use these skills when you need to discover and explore data assets in the Knowledge Catalog. It allows you to search for entries, lookup specific metadata, and explore aspect types to understand your data platform's assets.
cloud-sql-mysql-monitor
Use these skills when you need to troubleshoot slow queries, analyze system-level PromQL metrics, and identify structural performance issues like table fragmentation or missing unique indexes.
cloud-sql-mysql-lifecycle
Use these skills when you need to manage the durability and safety of your data by creating backups, restoring from previous states, or cloning instances for recovery and testing.