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 rules/altaidevorg/rules-for-ai/transformers___t___functions_git clone --depth 1 https://github.com/altaidevorg/rules-for-aiWrote 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.
[](https://agentmods.dev/rules/altaidevorg/rules-for-ai/transformers___t___functions_)<a href="https://agentmods.dev/rules/altaidevorg/rules-for-ai/transformers___t___functions_"><img src="https://agentmods.dev/badge/rules/altaidevorg/rules-for-ai/transformers___t___functions_.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04407 |
| Opus 5 | $0.00000 | $0.02204 |
| Sonnet 5 | $0.00000 | $0.00881 |
| Haiku 4.5 | $0.00000 | $0.00441 |
Grade A, and why
transformers___t___functions_ 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chapter 7: Transformers (t_ functions)
In the previous chapter, Pager / AsyncPager, we saw how the SDK simplifies iterating over paginated API results. Now, we delve into a crucial internal mechanism: the Transformer functions, typically prefixed with t_. These functions form an essential adaptation layer, translating between the user-friendly data types you interact with in the SDK and the specific formats required by the backend Google Generative AI APIs.
Motivation and Use Case
Interacting directly with APIs often involves constructing complex JSON or Protobuf messages with specific field names, nested structures, and precise formatting rules (e.g., resource names like models/gemini-pro or projects/my-proj/locations/us-central1/cachedContents/abc). Manually handling these details for every SDK call would make the code verbose, error-prone, and tightly coupled to the API's specific implementation details.
Transformers (t_ functions) solve this by acting as an Adapter layer. They take high-level, intuitive Python types used in the SDK's public interface—such as strings, PIL.Image objects, simple dictionaries, lists, Pydantic models (types.Content, types.Part), or Python functions (Function Calling Utilities)—and convert them into the exact dictionary/JSON structures the backend API expects. They also perform the reverse transformation for API responses, converting API data back into convenient SDK objects.
Central Use Case: Consider a simple call to generate content:
# Assuming 'client' is configured (Chapter 1)
from google.genai import types
import PIL.Image
# Load an image (replace with your image path)
try:
img = PIL.Image.open('path/to/your/image.jpg')
except FileNotFoundError:
print("Image file not found, using placeholder text.")
img = "Describe this image." # Use text if image fails
# Make the call with user-friendly types
response = client.models.generate_content(
model='gemini-1.5-flash', # Simple model string
contents=["What is in this picture?", img] # List of string and PIL Image
)
print(response.text)
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 · 320 lines · 0 tokens per session scan A 8753942a8457
transformers___t___functions_ 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 4,407 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.