Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hatefsystems/search-engine-corenpx agentmods add rules/hatefsystems/search-engine-core/code-styleWrote 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/code-style)<a href="https://agentmods.dev/rules/hatefsystems/search-engine-core/code-style"><img src="https://agentmods.dev/badge/rules/hatefsystems/search-engine-core/code-style/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/code-style"><img src="https://agentmods.dev/badge/rules/hatefsystems/search-engine-core/code-style.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 | $0.00357 |
| Opus 5.5 | $0.00000 | $0.00143 |
| Sonnet 5.5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
code-style scanned grade A with 2 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- API: `curl --location 'http://localhost:3000/api/endpoint' --header 'Content-Type: application/json' --data-raw '{ ... }'` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- API: `curl --location 'http://localhost:3000/api/endpoint' --header 'Content-Type: application/json' --data-raw '{ ... }'` What it actually says
Code Style and Practices
Error Handling
try {
mongocxx::instance& instance = MongoDBInstance::getInstance();
// ...
} catch (const mongocxx::exception& e) {
LOG_ERROR("MongoDB error: " + std::string(e.what()));
serverError(res, "Database error occurred");
}
Includes Order
// System headers first
#include <string>
#include <memory>
// Project headers
#include "../../include/Logger.h"
#include "../../include/mongodb.h"
// Third-party headers
#include <mongocxx/client.hpp>
#include <nlohmann/json.hpp>
Security
Validate input; use prepared statements; rate limit APIs; sanitize URLs; validate email/mobile formats.
Performance
Connection pooling (MongoDB); Redis caching; minimize DB round trips; indexes on hot fields.
Memory and Threads
Smart pointers; RAII; mutexes for shared state; lock_guard; minimize lock scope.
Testing
- MongoDB:
docker exec mongodb_test mongosh --username admin --password password123 --eval "db.adminCommand('ping')" - API:
curl --location 'http://localhost:3000/api/endpoint' --header 'Content-Type: application/json' --data-raw '{ ... }' - Verify data:
docker exec mongodb_test mongosh --username admin --password password123 --eval "use('search-engine'); db.collection.find().pretty()" - Logs:
docker logs core --tail 50,docker logs mongodb_test
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 · 53 lines · 0 tokens per session scan A ef26d0d34c3a
code-style 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 357 tokens. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). 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
qb-linq-project
qb-linq — header-only C++17 LINQ; read AGENTS.md and docs/LLMCONTEXT.md before editing.
move-copy-semantics
Avoid std::move(const&) silent copies; use sink-by-value + std::move.
vios-error-security
Error handling and security rules for VIOS C++ code.
cuda
Definitive guidelines for writing high-performance, maintainable, and error-resistant CUDA C++ code, focusing on modern practices, memory management, kernel optimization, and robust error handling.
cpp
Name methods (casing, etc) like "isvalid", "streamtext".
monitor-c-conventions
C coding conventions for HPCPerfStats monitor (C-only).