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/hatefsystems/search-engine-coreWrote 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/hatefsystems/search-engine-core/frontend)<a href="https://agentmods.dev/rules/hatefsystems/search-engine-core/frontend"><img src="https://agentmods.dev/badge/rules/hatefsystems/search-engine-core/frontend/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/hatefsystems/search-engine-core/frontend"><img src="https://agentmods.dev/badge/rules/hatefsystems/search-engine-core/frontend.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 | $0.00000 | $0.00366 |
| Opus 5.5 | $0.00000 | $0.00146 |
| Sonnet 5.5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
frontend 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 1mo ago.
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
Frontend Integration
Paths
- Static:
/public/(StaticFileController, 1-year cache for JS/CSS) - Templates:
/templates/(Inja) - Locales:
/locales/— use language subfolders (en/,fa/), not files in root. Keeplanguages.jsonin root.
Localization Loading
// Load from language-specific folder
std::string localesPath = "locales/" + lang + "/crawling-notification.json";
std::string localeContent = loadFile(localesPath);
if (localeContent.empty()) {
localesPath = "locales/en/crawling-notification.json";
localeContent = loadFile(localesPath);
}
Locales checklist: locales/en/, locales/fa/; descriptive filenames (common.json, sponsor.json); fallback to English.
Links
Use {{ base_url }} for all internal links. Never hardcode localhost or port.
<a href="{{ base_url }}/crawl-request">Crawl Request</a>
CSS
Reuse existing classes; define shared values in :root; use BEM and utility classes.
JavaScript (CSP)
No inline handlers (onclick, etc.). Use data-* attributes and addEventListener().
<button data-copy-text="text" class="copy-btn">Copy</button>
Use addEventListener() and event delegation for dynamic elements. No onclick, onload, onsubmit, etc. in HTML.
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.
- 1mo ago First seen · 50 lines · 0 tokens per session scan A 55fcee57b513
frontend is a cursor rule published in the GitHub repository hatefsystems/search-engine-core (5 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 366 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
internationalization
A set of rules for internationalization, the practice of adapting an application for multiple languages and regions. It covers file structure, translation namespaces, and using translations in components.
chinese-language
A language rule that requires replies, comments, and commit messages to use Simplified Chinese unless another language is requested.
cmd-moodle-mustache-lint
Lint Mustache templates for accessibility, security, hard-coded strings, and Moodle template conventions. (invoke by typing: @moodle-mustache-lint).
rtl-right-to-left-i18n-cursorrules-prompt-file
Cursor rule "rtl-right-to-left-i18n-cursorrules-prompt-file" from XD3an/awesome-ai-coding-all-in-one, covering rtl (right-to-left) development rules, core rules, 1. logical css properties, 2. tailwind css logical classes and 3. react native logical properties.
uninettuno-monografia
Regole UNINETTUNO per tesi TRIENNALE in italiano, con termini tecnici inglesi ammessi.
controlflow-docs-evals
Rules for documentation parity, localized tutorials, and eval verification.