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/product)<a href="https://agentmods.dev/rules/boxels/cursor-rules/product"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/product/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/product"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/product.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 | $0.00457 | $0.00457 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
product 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.
What it actually says
Product Rules
What this is
[Product name] is a [one-line description of what it does]. Think "[analogy to a known product]" but for [your niche]. Revenue comes from [business model — subscriptions, one-time purchase, freemium, marketplace fees, etc.].
Who uses this
Primary user: [Persona — who they are, what they need, how technical they are]. They're not [what they're not] — they compare us to [what familiar experience this feels like]. The experience should feel that simple.
Secondary user: [Second persona if applicable — their expectations and technical level. Remove this line if there's only one user type.]
Key user flows
- [Flow 1: step → step → step → outcome]
- [Flow 2: step → step → outcome]
- [Flow 3: step → step → step → outcome]
Every new feature should connect to one of these flows. If it doesn't, question whether we need it.
Roadmap
Next up: (1) [feature], (2) [feature], (3) [feature], (4) [feature]. Keep these in mind when making architectural decisions — don't hardcode things that'll need to be flexible soon.
Tone of voice
[Describe your brand voice — warm/formal/playful/minimal/technical]. "[Example of good copy]" not "[Example of bad copy]." Error messages should help, not dead-end: "[Good error example]" not "[Bad error example]."
Competitors and positioning
We're not [competitor A] ([why not]). We're not [competitor B] ([why not]). We're closer to [reference product] — [what your core experience is]. Never suggest patterns that make us look like [what you want to avoid].
Legal and compliance
[Terms of service and privacy policy requirements. Cookie consent needs. Data collection boundaries. Regulatory requirements (GDPR, HIPAA, SOC2, etc.). What requires explicit user approval before adding. Remove this section if not applicable yet.]
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 · 42 lines · 457 tokens per session scan A e0f1d7fff746
product is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 457 tokens to every session, about $0.0023 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.