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/tech)<a href="https://agentmods.dev/rules/boxels/cursor-rules/tech"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/tech/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/tech"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/tech.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 | $0.02580 | $0.02580 |
| Opus 5 | $0.01290 | $0.01290 |
| Sonnet 5 | $0.00516 | $0.00516 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
tech 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Rules
Language and framework
- [Primary language, e.g. "TypeScript strict mode", "Python 3.12+", "Go 1.22", "Rust stable"]. [Key constraint, e.g. "No 'any' types unless explicitly approved", "Type hints on all function signatures", etc.]
- [Primary framework, e.g. "Next.js App Router", "Django 5", "Rails 7", "SvelteKit", "FastAPI"]. [Default pattern, e.g. "Server Components by default, 'use client' only when interactivity is needed", "class-based views unless logic is trivial", etc.]
- [Styling approach, e.g. "Tailwind CSS utility classes", "CSS Modules", "styled-components", "SCSS with BEM"]. [Constraint, e.g. "Never write custom CSS unless the framework can't do it."]
- [Primary backend service, e.g. "Supabase", "Firebase", "AWS Amplify", "self-hosted Postgres"]. Don't introduce alternative services without asking.
Code organization
- File naming: [convention, e.g. "kebab-case for files, PascalCase for components", "snake_case for all files", "PascalCase for classes, camelCase for utilities"].
- Group by [organization strategy, e.g. "feature, not by type", "module", "domain layer"].
- Imports: [import convention, e.g. "absolute paths with @/ alias", "relative imports within modules, absolute across modules"]. Group by: external libs → internal modules → components → types. Separate groups with blank lines.
- Functions should do one thing. If a function exceeds [threshold, e.g. "30 lines", "50 lines"], it should be split.
Data and state management
- Validation: [validation library, e.g. "Zod", "Pydantic", "Joi", "class-validator"]. Never trust external data without validating. Validate at every trust boundary — client input, API params, webhook payloads, URL params. Prefer allowlists over denylists.
- Data fetching: [approach, e.g. "TanStack Query for client-side, server components for initial loads", "SWR", "RTK Query", "built-in framework loaders"]. [Anti-pattern to avoid, e.g. "Never use useEffect for data fetching", "No raw fetch calls without error handling."]
- State management: [approach, e.g. "React state + context for UI, server state libraries for async data", "Pinia for global state", "Zustand", "Redux Toolkit"]. [Constraint, e.g. "Never mix UI state and server state."]
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 · 109 lines · 2,580 tokens per session scan A 72e53ed1cc81
tech is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 2,580 tokens to every session, about $0.0129 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.