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/ghaida/intent/intent-ref-ethical-designgit clone --depth 1 https://github.com/ghaida/intentWhat 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 | $0.00037 | $0.03306 |
| Opus 5 | $0.00018 | $0.01653 |
| Sonnet 5 | $0.00007 | $0.00661 |
| Haiku 4.5 | $0.00004 | $0.00331 |
Grade A, and why
intent-ref-ethical-design 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 2d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ethical Design
Anti-Pattern Remediation Guide
The master skill catalogs anti-patterns. This document explains how to fix them — and how to design the ethical alternative from the start.
Deceptive Patterns → Honest Alternatives
Bait and Switch → Consistent Delivery. What you show is what you deliver. If a button says "Download," it downloads. If a link says "Learn more," it teaches. Test by asking: if a user described what just happened, would their description match the label they clicked?
Trick Questions → Plain Language Choices. Every option should be stateable as an affirmative: "Yes, send me emails" / "No, don't send me emails." Never use double negatives ("Uncheck to not receive..."). Never combine multiple consents into one checkbox. Test by reading the question aloud — if a colleague gets confused, users will too.
Visual Misdirection → Equal Visual Weight. When presenting choices, the "decline" or "opt-out" option should be equally visible — same size, same visual weight, same position prominence. The user's preferred choice, not the business's preferred choice, should determine which option they pick. Test: cover the page with your hand and peek — can you see both options equally?
Hidden Costs → Upfront Pricing. Show the total cost, including taxes, fees, and shipping, before the user enters any personal information. The Baymard Institute found that 48% of cart abandonment is caused by extra costs shown too late. The fix isn't just ethical — it converts better.
Confirmshaming → Neutral Opt-Out. Opt-out text should be factual, not emotional. "No thanks" is fine. "No thanks, I hate saving money" is manipulation. The test is simple: would you say the opt-out text to someone's face without feeling embarrassed?
Sneak into Basket → Explicit Additions Only. Nothing enters a cart, plan, or order without a deliberate user action. Pre-selected add-ons, bundled insurance, and automatic upsells all fail this test. If the user didn't click "add," it shouldn't be there.
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.
- 2d ago First seen · 218 lines · 3,306 tokens per session scan A 1fad99b6a6aa
intent-ref-ethical-design is a cursor rule published in the GitHub repository ghaida/intent (139 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 37 tokens to every session and 3,306 once invoked, about $0.0002 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 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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.