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/Horosheff/cursor-jrWrote 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/horosheff/cursor-jr/cursor-jr-routing)<a href="https://agentmods.dev/rules/horosheff/cursor-jr/cursor-jr-routing"><img src="https://agentmods.dev/badge/rules/horosheff/cursor-jr/cursor-jr-routing.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.00438 |
| Opus 5 | $0.00036 | $0.00219 |
| Sonnet 5 | $0.00015 | $0.00088 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
cursor-jr-routing 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 7d 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
CursorJr — маршрутизация для новичков
Когда вызывать Task(cursor-jr)
- Пользователь впервые в Cursor или спрашивает «с чего начать»
- Непонимание интерфейса: «где агент», «что такое diff», «что нажать»
- Вопросы про режимы Agent / Ask / Plan / Debug
- Настройка rules, skills, subagents, MCP, Run Mode, автоматизация
- Задачи не-разработчика: лендинг, отчёт, публикации
- Страх или ошибка: «ничего не понимаю», «откатить», «боится терминала»
- Явный вызов:
/cursor-jr, «позови CursorJr», «объясни как для новичка»
Когда НЕ вызывать
- Пользователь просит «без объяснений, просто сделай»
- Глубокий production-дебаг → режим Debug / debugger
- Enterprise API без запроса объяснения
- Пользователь уверенно на шаге 5+ workflow без вопросов
Как делегировать
Task(cursor-jr)
Передай: цель пользователя, уровень (новичок), профессию если известна, что уже пробовали.
Не дублируй длинное объяснение в main chat — дождись ответа субагента и кратко резюмируй.
Fallback
Если Task(cursor-jr) недоступен:
Task(generalPurpose)
Промпт: полный текст из agents/cursor-jr.md + путь к knowledge-base/INDEX.md в плагине cursor-jr.
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.
- 7d ago First seen · 48 lines · 73 tokens per session scan A 2097d1810bfe
cursor-jr-routing is a cursor rule published in the GitHub repository Horosheff/cursor-jr (10 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 438 once invoked, about $0.0004 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
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
docs-plain-language
Write clear, jargon-free documentation (README, docs, SECURITY, memory bank).
general
You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.
pr-cleaner-ai
Automatically fetch and resolve GitHub Pull Request comments. Activates when you mention PR (with or without number): 'fix PR', 'PR 2146', 'fix PR 2146', '#2146', 'PR#2146', 'pr2146', or any variation.