baseapiclient

baseapiclient is a cursor rule for coding agents from altaidevorg/rules-for-ai. It costs 0 tokens per session (4,420 once invoked), scanned A, original, MIT.

The internal part of the Google GenAI SDK that communicates with the web API. It handles HTTP requests, authentication, endpoint addresses, request and response conversion, and network errors.

In plain words
What is it for?
Use it when implementing or debugging the SDK's shared request handling for Gemini or Vertex AI, including API keys and cloud credentials.
Why use it?
It keeps low-level web communication out of each higher-level SDK operation and supports different Google AI backends.

Cursor rule

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 rules/altaidevorg/rules-for-ai/baseapiclient
Clone the repo
git clone --depth 1 https://github.com/altaidevorg/rules-for-ai

Wrote 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.

agentmods badge for baseapiclient

README.md
[![agentmods](https://agentmods.dev/badge/rules/altaidevorg/rules-for-ai/baseapiclient.svg)](https://agentmods.dev/rules/altaidevorg/rules-for-ai/baseapiclient)
Your own site
<a href="https://agentmods.dev/rules/altaidevorg/rules-for-ai/baseapiclient"><img src="https://agentmods.dev/badge/rules/altaidevorg/rules-for-ai/baseapiclient.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 4,420 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 $0.00000 $0.04420
Opus 5 $0.00000 $0.02210
Sonnet 5 $0.00000 $0.00884
Haiku 4.5 $0.00000 $0.00442

Measured 3d ago against content hash 03c51517fe52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baseapiclient 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.

examples/google-genai/baseapiclient.mdc · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chapter 8: BaseApiClient

In Chapter 7: Transformers (t_ functions), we saw how the google-genai SDK uses internal helper functions to convert user-friendly data types into the structured formats required by the API. Once the data is correctly formatted, something needs to actually send it over the network, handle authentication, and process the response. This chapter dives into that core component: the BaseApiClient.

Motivation and Use Case

Directly interacting with HTTP APIs involves numerous low-level details: correctly formatting URLs, setting headers (like Content-Type, User-Agent, and authorization tokens), serializing request bodies (usually to JSON), sending the request using an HTTP library, handling potential network errors, deserializing the response body, and checking the response status code. Furthermore, authentication requires managing API keys or obtaining and refreshing access tokens from credentials (like Google Cloud ADC). Different backends (Gemini vs. Vertex AI) might use different base URLs or API versions.

Managing all this complexity within each high-level SDK function (like Models.generate_content) would lead to massive code duplication and make the SDK difficult to maintain.

The BaseApiClient solves this by encapsulating all the core logic for API communication. It acts as the central engine that higher-level components, like the API Modules (Models, Chats, Files, Tunings, Caches, Batches, Operations, Live), rely on to execute their tasks. It abstracts away the complexities of HTTP, authentication, endpoint differences, and basic error checking.

Central Use Case: Although you, as an SDK user, will interact with the Client and its API modules, understanding BaseApiClient is crucial for grasping the SDK's internal architecture. When you call a method like client.models.generate_content(...):

Read the full file on GitHub · 312 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. 3d ago First seen · 312 lines · 0 tokens per session scan A 03c51517fe52

Subscribe to this mod's changes

baseapiclient is a cursor rule published in the GitHub repository altaidevorg/rules-for-ai (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,420 tokens. 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 2026-08-31.