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.
git clone --depth 1 https://github.com/mckaywrigley/o1-pro-template-systemWrote 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/mckaywrigley/o1-pro-template-system/storage)<a href="https://agentmods.dev/rules/mckaywrigley/o1-pro-template-system/storage"><img src="https://agentmods.dev/badge/rules/mckaywrigley/o1-pro-template-system/storage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/mckaywrigley/o1-pro-template-system/storage"><img src="https://agentmods.dev/badge/rules/mckaywrigley/o1-pro-template-system/storage.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00009 | $0.01037 |
| Opus 5.5 | $0.00004 | $0.00415 |
| Sonnet 5.5 | $0.00002 | $0.00207 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
storage 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storage Rules
Follow these rules when working with Supabase Storage.
It uses Supabase Storage for file uploads, downloads, and management.
General Rules
- Always use environment variables for bucket names to maintain consistency across environments
- Never hardcode bucket names in the application code
- Always handle file size limits and allowed file types at the application level
- Use the
upsertmethod instead ofuploadwhen you want to replace existing files - Always implement proper error handling for storage operations
- Use content-type headers when uploading files to ensure proper file handling
Organization
Buckets
- Name buckets in kebab-case:
user-uploads,profile-images - Create separate buckets for different types of files (e.g.,
profile-images,documents,attachments) - Document bucket purposes in a central location
- Set appropriate bucket policies (public/private) based on access requirements
- Implement RLS (Row Level Security) policies for buckets that need user-specific access
- Make sure to let me know instructions for setting up RLS policies on Supabase since you can't do this yourself, including the SQL scripts I need to run in the editor
File Structure
- Organize files in folders based on their purpose and ownership
- Use predictable, collision-resistant naming patterns
- Structure:
{bucket}/{userId}/{purpose}/{filename} - Example:
profile-images/123e4567-e89b/avatar/profile.jpg - Include timestamps in filenames when version history is important
- Example:
documents/123e4567-e89b/contracts/2024-02-13-contract.pdf
Actions
- When importing storage actions, use
@/actions/storage - Name files like
example-storage-actions.ts - Include Storage at the end of function names
Ex: uploadFile -> uploadFileStorage - Follow the same ActionState pattern as DB actions
Example of a storage action:
"use server"
import { createClientComponentClient } from "@supabase/auth-helpers-nextjs"
import { ActionState } from "@/types"
export async function uploadFileStorage(
bucket: string,
path: string,
file: File
): Promise<ActionState<{ path: string }>> {
try {
const supabase = createClientComponentClient()
const { data, error } = await supabase
.storage
.from(bucket)
.upload(path, file, {
upsert: false,
contentType: file.type
})
if (error) throw error
return {
isSuccess: true,
message: "File uploaded successfully",
data: { path: data.path }
}
} catch (error) {
console.error("Error uploading file:", error)
return { isSuccess: false, message: "Failed to upload file" }
}
}
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 · 163 lines · 9 tokens per session scan A cd4cc68bd594
storage is a cursor rule published in the GitHub repository mckaywrigley/o1-pro-template-system (142 stars, last pushed 1y ago), licensed MIT. It adds 9 tokens to every session and 1,037 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-14.
Other cursor rules, from other repositories
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
python
Python best practices and patterns for modern software development with Flask and SQLite.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
selectools-providers
Rules for working with LLM provider adapters in selectools.