cursor-jr-routing

cursor-jr-routing is a cursor rule for Cursor from Horosheff/cursor-jr. It costs 73 tokens per session (438 once invoked), scanned A, original, MIT.

A routing rule for sending Russian-speaking beginners to a helper agent called CursorJr. It covers first-time Cursor use and basic questions about modes, rules, skills, MCP, and automation.

In plain words
What is it for?
Use it for beginner questions about Cursor, including where to find Agent, Ask, Plan, or Debug modes, what a diff means, and how to configure rules or integrations.
Why use it?
It prevents beginners from having to navigate unfamiliar coding-agent concepts alone and gives them explanations suited to their level.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions subagents.

Good fit Use it for beginner questions about Cursor, including where to find Agent, Ask, Plan, or Debug modes, what a diff means, and how to configure rules or integrations.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/horosheff/cursor-jr/cursor-jr-routing
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Horosheff/cursor-jr

Made for: Cursor.

Wrote 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.

agentmods badge for cursor-jr-routing

README.md
[![agentmods](https://agentmods.dev/badge/rules/horosheff/cursor-jr/cursor-jr-routing.svg)](https://agentmods.dev/rules/horosheff/cursor-jr/cursor-jr-routing)
Your own site
<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>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 2097d1810bfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

rules/cursor-jr-routing.mdc · 48 lines

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.

Changes

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.

  1. 7d ago First seen · 48 lines · 73 tokens per session scan A 2097d1810bfe

Subscribe to this mod's changes

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.