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/template-repo)<a href="https://agentmods.dev/rules/boxels/cursor-rules/template-repo"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/template-repo/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/template-repo"><img src="https://agentmods.dev/badge/rules/boxels/cursor-rules/template-repo.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 | $0.00461 | $0.00461 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
template-repo 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 today.
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
Template repository
This repo publishes the Cursor .cursor/ starter template. It is not an application.
The shipped product is these eight files: global-rules.mdc, models.mdc, product.mdc, tech.mdc, security.mdc, design.mdc, structure.mdc, and documentation.mdc. Their [bracketed placeholders] are intentional. This file is maintainer-only — do not copy it into downstream projects.
Do not
- Do not replace placeholders in the eight shipped files except when authoring the template (changing the prompt, adding an example, fixing a guardrail).
- Do not run
/setup-ruleshere. That interview fills placeholders and would destroy the template. If the user types it anyway, the skill asks whether they are maintaining the template or converting a clone into a new project — wait for that answer. - Do not add app scaffolding (
src/,app/, APIs, databases, UI kits, env files, hosting config) unless the user explicitly wants a demo. - Do not treat the product/tech/structure placeholders as this repo's stack. Those describe a future consumer app.
Do
- Copiers take the eight rules, both skills, and
AGENTS.md— not this file. - Treat
README.md,.cursor/skills/,AGENTS.md, and this file as the maintainer surface. - Keep the eight shipped files stack-agnostic. Examples in brackets are options, not this repo's stack.
- When a change affects how copies are used, update
README.mdin the same change.
Hard-tier work here: the /setup-rules interview, rule frontmatter (.mdc, alwaysApply, globs), skill contracts, and AGENTS.md. Everyday-tier: README copy, wording, single-file template tweaks.
The other eight always-on rules still load. This file wins on identity.
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.
- today First seen · 29 lines · 461 tokens per session scan A cb6001d42c00
template-repo is a cursor rule published in the GitHub repository BOXELS/cursor-rules (6 stars, last pushed yesterday), licensed MIT. It adds 461 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 2026-09-16.
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.