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/savedpixel/ai-agent-rules-generatorWrote 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/savedpixel/ai-agent-rules-generator/project)<a href="https://agentmods.dev/rules/savedpixel/ai-agent-rules-generator/project"><img src="https://agentmods.dev/badge/rules/savedpixel/ai-agent-rules-generator/project/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/savedpixel/ai-agent-rules-generator/project"><img src="https://agentmods.dev/badge/rules/savedpixel/ai-agent-rules-generator/project.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 | $0.03426 | $0.03426 |
| Opus 5.5 | $0.01370 | $0.01370 |
| Sonnet 5.5 | $0.00685 | $0.00685 |
| Haiku 4.5 | $0.00343 | $0.00343 |
Grade A, and why
project scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **b. Visual Verification Gate** — If the work affects front-end/UI: open a browser, navigate to affected pages, resize to proper dimensions, take screenshots, and visually confirm. **HTML inspection, DOM analysis, `cur How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glitch Payment Gateway — Project Rules
Project Overview
A bespoke WooCommerce payment gateway plugin for Glitch, a major South African payment provider. Enables merchants to accept payments through Glitch's infrastructure with support for multiple payment methods, webhooks, refunds, and full order status synchronization.
- Plugin root:
src/— Main plugin PHP files, gateway class, includes - Includes:
src/includes/— Helper classes, API client, webhook handler - Admin:
src/admin/— WooCommerce settings page, admin views - Templates:
src/templates/— Checkout and payment form templates - Assets:
src/assets/— CSS and JS for checkout/admin - Docs:
docs/— Architecture, deployment, and task documentation - Tests:
tests/— PHPUnit test cases
Stack
- CMS: WordPress 6.x
- E-commerce: WooCommerce 8.x+ (HPOS compatible)
- Language: PHP 8.1+
- Database: MySQL / MariaDB (via WordPress $wpdb and WC CRUD)
- Payment Provider: Glitch API (South Africa)
- Currency: ZAR (South African Rand)
- Testing: PHPUnit + WooCommerce test framework
- Styling: WordPress admin CSS + minimal custom checkout CSS
- Dev Environment: Docker (WordPress + MySQL containers)
CRITICAL: Never Push to Live
You must never push, deploy, or sync code to the live/production environment. All live deployments are the user's responsibility. This includes:
- Running any deploy command that targets production
- Triggering any CI/CD pipeline that pushes to live
- Using
git pushto production branches - Invoking any deploy action aimed at the live server
You may deploy to local or staging environments only.
CRITICAL: Always Follow task.mdc
Before starting any task, you MUST read and follow the rules in .cursor/rules/task.mdc. This includes:
- Planning before implementation (Plan Node)
- Writing checklists to
docs/task/todo.mdfor planned, multi-step work (features, refactors, multi-step tasks) — not for every ad-hoc single-message request or quick fix - Updating
docs/task/lessons.mdafter any user correction - Verification before marking work complete (3-tier verification gate pipeline)
- The full Task Management Protocol
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.
- 1mo ago First seen · 304 lines · 3,426 tokens per session scan A 616c3c803f35
project is a cursor rule published in the GitHub repository savedpixel/ai-agent-rules-generator (8 stars, last pushed 6mo ago), licensed MIT. It adds 3,426 tokens to every session, about $0.0137 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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
general
Cursor rule "general" from maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.
checklist
Before making ANY changes or implementing ANY new features.
main
Cursor rule "main" from Bita71/Agent-Workflow-Kit, covering cursor adapter, commands and roles.
stripe
Stripe payment integration, webhooks, checkout, and subscriptions.
browser-ops-agent
Agent rules for browser-ops-agent.
browser-ops-demo
Agent rules for browser-ops-demo.