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/qwertic/cursorrules/cursorrulesgit clone --depth 1 https://github.com/Qwertic/cursorrulesWhat 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 | $0.01229 | $0.01229 |
| Opus 5 | $0.00615 | $0.00615 |
| Sonnet 5 | $0.00246 | $0.00246 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
cursorrules 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.
This is a copy
100% identical to cursorrules — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1 lines — stays where its author put it; the contents beside it link to each section on GitHub.
.cursorrules# General rules- Do not apologize- Do not thank me- Talk to me like a human- Verify information before making changes- Preserve existing code structures- Provide concise and relevant responses- Verify all information before making changesYou will be penalized if you:- Skip steps in your thought process- Add placeholders or TODOs for other developers- Deliver code that is not production-readyI'm tipping $9000 for an optimal, elegant, minimal world-class solution that meets all specifications. Your code changesshould be specific and complete. Think through the problem step-by-step.YOU MUST:- Follow the User's intent PRECISELY- NEVER break existing functionality by removing/modifying code or CSS without knowing exactly how to restore the samefunction- Always strive to make your diff as tiny as possible# File-by-file changes- Make changes in small, incremental steps- Test changes thoroughly before committing- Document changes clearly in commit messages# Code style and formatting- Follow the project's coding standards- Use consistent naming conventions- Avoid using deprecated functions or libraries# Debugging and testing- Include debug information in log files- Write unit tests for new code- Ensure all tests pass before merging# Project structure- Maintain a clear and organized project structure- Use meaningful names for files and directories- Avoid clutter by removing unnecessary files# CleanCodeDon't Repeat Yourself (DRY)Duplication of code can make code very difficult to maintain. Any change in logic can make the code prone to bugs or canmake the code change difficult. This can be fixed by doing code reuse (DRY Principle).The DRY principle is stated as "Every piece of knowledge must have a single, unambiguous, authoritative representationwithin a system".The way to achieve DRY is by creating functions and classes to make sure that any logic should be written in only oneplace.Curly's Law - Do One ThingCurly's Law is about choosing a single, clearly defined goal for any particular bit of code: Do One Thing.Curly's Law: A entity (class, function, variable) should mean one thing, and one thing only. It should not mean onething in one circumstance and carry a different value from a different domain some other time. It should not mean twothings at once. It should mean One Thing and should mean it all of the time.Keep It Simple Stupid (KISS)The KISS principle states that most systems work best if they are kept simple rather than made complicated; therefore,simplicity should be a key goal in design, and unnecessary complexity should be avoided.Simple code has the following benefits:less time to writeless chances of bugseasier to understand, debug and modifyDo the simplest thing that could possibly work.Don't make me thinkCode should be easy to read and understand without much thinking. If it isn't then there is a prospect ofsimplification.You Aren't Gonna Need It (YAGNI)You Aren't Gonna Need It (YAGNI) is an Extreme Programming (XP) practice which states: "Always implement things when youactually need them, never when you just foresee that you need them."Even if you're totally, totally, totally sure that you'll need a feature, later on, don't implement it now. Usually,it'll turn out either:you don't need it after all, orwhat you actually need is quite different from what you foresaw needing earlier.This doesn't mean you should avoid building flexibility into your code. It means you shouldn't overengineer somethingbased on what you think you might need later on.There are two main reasons to practice YAGNI:You save time because you avoid writing code that you turn out not to need.Your code is better because you avoid polluting it with 'guesses' that turn out to be more or less wrong but stickaround anyway.Premature Optimization is the Root of All EvilProgrammers waste enormous amounts of time thinking about or worrying about, the speed of noncritical parts of theirprograms, and these attempts at efficiency actually have a strong negative impact when debugging and maintenance areconsidered.We should forget about small efficiencies, say about 97% of the time: premature optimization is the root of all evil.Yet we should not pass up our opportunities in that critical 3%.- Donald KnuthBoy-Scout RuleAny time someone sees some code that isn't as clear as it should be, they should take the opportunity to fix it rightthere and then - or at least within a few minutes.This opportunistic refactoring is referred to by Uncle Bob as following the boy-scout rule - always leave the codebehind in a better state than you found it.The code quality tends to degrade with each change. This results in technical debt. The Boy-Scout Principle saves usfrom that.Code for the MaintainerCode maintenance is an expensive and difficult process. Always code considering someone else as the maintainer andmaking changes accordingly even if you're the maintainer. After a while, you'll remember the code as much as a stranger.Always code as if the person who ends up maintaining your code is a violent psychopath who knows where you live.Principle of Least AstonishmentPrinciple of Least Astonishment states that a component of a system should behave in a way that most users will expectit to behave. The behavior should not astonish or surprise users.Code should do what the name and comments suggest. Conventions should be followed. Surprising side effects should beavoided as much as possible.# Project specific rulesI'm using angular with standalone compnentsI'm integrating novo elements which is the novo-elements moduleDocumentation is here: https://bullhorn.github.io/novo-elements/docs/#/homeGithub is here: https://github.com/bullhorn/novo-elementsI don''t have a module file. I am using standalone components@Docs{ "library_name": "Novo Elements", "documentation": "https://bullhorn.github.io/novo-elements/docs/#/home"}@Docs{ "library_name": "Novo Elements", "documentation": "https://github.com/bullhorn/novo-elements"}
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 · 1 lines · 1,229 tokens per session scan A 6735bb337267
cursorrules is a cursor rule published in the GitHub repository Qwertic/cursorrules (26 stars, last pushed 1y ago), licensed MIT. It adds 1,229 tokens to every session, about $0.0061 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursorrules, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
cursorrules
Cursor rule "cursorrules" from wrm3/cursorrules_siliconvalley, covering assistant personality, character rotation, richard hendricks, gilfoyle and dinesh.
engineering-ticket-template-cursorrules-prompt-file
Cursor rules for engineering development with ticket template integration.
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
cypress-integration-testing-cursorrules-prompt-file
Cursor rules for Cypress development with integration testing.
git-conventional-commit-messages
Cursor rules for Git development with conventional commit messages integration.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.