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/yellow-hammer/ivolgaqlWrote 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/yellow-hammer/ivolgaql/ivolgaql-project)<a href="https://agentmods.dev/rules/yellow-hammer/ivolgaql/ivolgaql-project"><img src="https://agentmods.dev/badge/rules/yellow-hammer/ivolgaql/ivolgaql-project/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/yellow-hammer/ivolgaql/ivolgaql-project"><img src="https://agentmods.dev/badge/rules/yellow-hammer/ivolgaql/ivolgaql-project.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 | $0.00519 | $0.00519 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
ivolgaql-project 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 9d 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
ИволгаQL — общие правила
- Это MVP: меняй только то, что нужно задаче; без масштабных рефакторингов и лишних зависимостей в
Cargo.toml. - Код: только Rust в корне (
Cargo.toml,src/). Не размечай и не подмешивай в основную линию посторонние каталоги с устаревшим кодом без явной задачи на них. - Язык интерфейса: сообщения пользователю, поле
bird, ошибки разбора, README и подсказки CLI — русский, коротко. - Кодировка: UTF-8.
- Импорты в Rust: только в начале файла, без inline/lazy внутри функций.
- В коде и метаданных пакета не плоди отсылки к другим стекам и прочий шум — только по делу.
- Модули:
main.rs(сервер/CLI),client.rs,lib.rs,parser.rs,engine.rs,protocol.rs— не дублируй контракты между ними. - Проверка: перед PR —
cargo build(как в CONTRIBUTING.md); при правках парсера, движка или протокола —cargo test. - Коммиты: Conventional Commits — строка
<тип>[область]: описаниена русском, повелительное наклонение, без точки в конце заголовка. Типы:feat,fix,docs,chore,test,refactor,style,ciи т.д.; область по желанию (parser,protocol,cursor). Примеры:feat(parser): лексер для вставки,fix: корректный JSON при пустом запросе,docs: ссылка на CONTRIBUTING,chore(cursor): правила проекта. - TCP: баннер при connect (строки + пустая строка), затем одна строка запроса → один JSON-ответ; без чата и без нескольких JSON на один запрос.
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.
- 9d ago First seen · 18 lines · 519 tokens per session scan A 8e5e72bfbde2
ivolgaql-project is a cursor rule published in the GitHub repository yellow-hammer/ivolgaql (6 stars, last pushed 1mo ago), licensed MIT. It adds 519 tokens to every session, about $0.0026 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 2026-08-31.
Other cursor rules, from other repositories
testing-patterns
A set of rules and examples for testing 1C code with YaXUnit and Vanessa Automation. YaXUnit is used for unit tests of individual functions, while Vanessa Automation describes user scenarios as “given, when, then” steps.
core
Core STT/TTS abstraction layer documentation.
rust-architect
PoolAI — Rust Architect workflow: runtime stack, MSYS2, target/ disk, pre-push checks, docs sync.
rust-module-refactor
Use when splitting Rust modules, moving tests, tightening visibility, or preserving facades during refactors.
fix-galo
SYNTAX RULES.
arc-deref-pattern
When implementing parallel (Mt) algorithms in Verus, do NOT assume.