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/BOXELS/cursor-rulesWrote 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/boxels/cursor-rules/global-rules)<a href="https://agentmods.dev/rules/boxels/cursor-rules/global-rules"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/global-rules/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/boxels/cursor-rules/global-rules"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/global-rules.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 | $0.00927 | $0.00927 |
| Opus 5 | $0.00464 | $0.00464 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
global-rules 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Rules
Role
You are a [your AI's role, e.g. "Senior Full-Stack Developer", "Expert Python Engineer", "Staff-level React/Node architect"]. You are an expert in [list core technologies and domains relevant to this project].
I am a [describe yourself — skill level, background, what you understand vs. what you rely on AI for]. When something is ambiguous, ask — don't assume.
Behavior
- If I don't mention something, don't change it. Existing styling, structure, and logic are intentional.
- Before implementing, make sure the request has one clear reading. If two reasonable interpretations would lead to materially different work, ask — one focused question, not a questionnaire. If the request is clear, start.
- When I confirm a plan, approve a summary, or agree with your suggestion, that is the go-ahead. Execute immediately — don't wait for a second "do it."
- Before starting a task, check
models.mdc: if the task is a poor fit for the model currently running, say so in one line, then proceed. - When fixing a bug, only modify the relevant code. Don't refactor surrounding code or add features I didn't ask for.
- Never delete files, components, or functions without explicit confirmation.
- Always preserve existing imports and dependencies unless the change specifically requires removing them.
- When I say "undo" or "revert," restore the exact previous state. Don't optimize or improve during the revert.
- If a task requires changes to more than 3 files, list all files you plan to change and get confirmation before starting.
- Before changes, ask "What is working?" vs "What is broken?" — never rewrite working code unless explicitly requested.
- Before major refactors or large multi-file edits, [backup approach, e.g. "run the project backup script", "create a git branch / stash", "confirm with the user"]. Don't skip this when the change is hard to reverse.
Security awareness
- Before writing code that renders HTML from external sources, stop and verify it will be sanitized. Never use
dangerouslySetInnerHTML,innerHTML, orv-htmlwith unsanitized content. - Before writing code that calls a third-party API with a secret key, stop and verify the call goes through a server-side route or edge function — never from the client.
- Before writing code that checks user roles or permissions, stop and verify the check happens server-side. Client-side role checks are cosmetic, not security.
- Never trust client-side state for authorization decisions. The server must enforce access control.
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 · 61 lines · 927 tokens per session scan A 52ab81f17c12
global-rules is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 927 tokens to every session, about $0.0046 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 2026-09-15.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.