ticket-deflector

ticket-deflector is a skill for Cursor from ilyautov/small-business-ru. It costs 92 tokens per session (1,789 once invoked), scanned A, original, Apache-2.0.

A customer-support helper that reads a forwarded message, checks the customer's order, payment, and CRM history, and drafts a reply in the owner's voice. It asks for explicit approval before arranging a refund.

In plain words
What is it for?
Use it to investigate customer questions, prepare replies, and handle approved refund requests.
Why use it?
It removes the need to search several systems before answering a customer. It also keeps refunds under the owner's control.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the small-business-ru plugin — 34 skills shipped together

Good fit Use it to investigate customer questions, prepare replies, and handle approved refund requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ilyautov/small-business-ru/ticket-deflector
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.

Any agent
npx skills add ilyautov/small-business-ru --skill ticket-deflector
Clone the repo
git clone --depth 1 https://github.com/ilyautov/small-business-ru

Made for: Cursor.

Or install small-business-ru, the plugin that ships this one along with the rest of its 34 skills.

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 ticket-deflector

README.md
[![agentmods](https://agentmods.dev/badge/skills/ilyautov/small-business-ru/ticket-deflector/github.svg)](https://agentmods.dev/skills/ilyautov/small-business-ru/ticket-deflector)
Your own site
<a href="https://agentmods.dev/skills/ilyautov/small-business-ru/ticket-deflector"><img src="https://agentmods.dev/badge/skills/ilyautov/small-business-ru/ticket-deflector/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.

agentmods 80×15 button for ticket-deflector

Your own site · 80×15
<a href="https://agentmods.dev/skills/ilyautov/small-business-ru/ticket-deflector"><img src="https://agentmods.dev/badge/skills/ilyautov/small-business-ru/ticket-deflector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,789 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 $0.00092 $0.01789
Opus 5 $0.00046 $0.00894
Sonnet 5 $0.00018 $0.00358
Haiku 4.5 $0.00009 $0.00179

Measured yesterday against content hash 2096234e3a58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ticket-deflector 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 yesterday.

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.

small-business-ru/skills/ticket-deflector/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Помощник поддержки (ticket-deflector)

Каждое письмо клиента — это переключение контекста: где заказ, сколько заплатил, что ему отвечать и не сорвётся ли он, если ответить через два дня. Скилл сам поднимает статус оплаты и историю по клиенту и готовит ответ вашими словами, а возврат не оформит без вашего явного «да» — вы только проверяете черновик, а не собираете факты вручную.

Быстрый старт

Перешлите или вставьте письмо клиента — Claude подтянет статус заказа из ~~платежей, найдёт клиента в ~~crm и подготовит ответ в голосе владельца. Если нужен возврат, он соберёт детали и дождётся явного подтверждения, прежде чем что-либо оформлять.

Владелец: «ответь этому клиенту» [пересылает письмо]
→ Извлечь почту клиента + суть обращения из переписки
→ Подтянуть статус оплаты из ~~платежей
→ Подтянуть историю клиента из ~~crm
→ Подготовить ответ в голосе владельца
→ Владелец одобряет черновик → отправить или в черновики
→ Если нужен возврат: запрос подтверждения → владелец подтверждает → оформить

Рабочий процесс

  1. Прочитайте сообщение клиента. Примите пересланное письмо (~~почта), сообщение из мессенджера (~~мессенджер) или вставленный текст. Извлеките: контакт клиента, имя, номер заказа или операции (если есть) и суть — заявка на возврат, вопрос о статусе заказа или общая жалоба. Если вопросов несколько — отвечайте в порядке их появления.

  2. Подтяните статус оплаты из платежей. Найдите операцию в ~~платежах (например ЮKassa, Тинькофф Касса) по контакту клиента или номеру операции. Зафиксируйте: сумму, дату, статус и был ли уже возврат. Если ~~платежи не подключены — отметьте это в черновике и продолжайте. Если совпадений нет — отметьте это, не угадывайте совпадение.

    • Лимит запросов: если клиент дал номер операции — используйте его (точечный поиск не упирается в лимит). Если ищете по контакту — берите окно 7 дней (не 30). Широкие диапазоны дат чаще всего упираются в лимит; запросы подряд в одной сессии исчерпают лимит, если окно слишком широкое.
    • Если подключён ~~мессенджер — проверьте открытые обращения от этого клиента там.
    • Если подключён второй источник оплат — проверьте и его как дополнительный.
    • Если совпало несколько операций — покажите все и спросите владельца, какая относится к делу, прежде чем готовить черновик.

Read the full file on GitHub · 79 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed · +1 lines 2096234e3a58
  2. 12d ago First seen · 78 lines · 92 tokens per session scan A 39264b4df545

Subscribe to this mod's changes

ticket-deflector is a skill published in the GitHub repository ilyautov/small-business-ru (15 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 1,789 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

architecture-reviewer

Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports. Triggers on: "review architecture", "critique design", "audit system", "assess scalability", "enterprise readiness", "technical due diligence". NOT for diagrams, use…

Mathews-Tom/armory · 71 tokens

concept-to-video

Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition. Triggers on: "create a video", "animate this", "make an explainer", "manim animation", "motion graphic". NOT for React video, use remotion-video.

Mathews-Tom/armory · 70 tokens

figure-rhetoric

Evaluate whether figures and plots in a manuscript effectively communicate the claims they support. Audits chart-type fit, axis design, visual hierarchy, data density, caption interpretation, perceptual accuracy, and narrative arc across 8 dimensions. Triggers on: "do my figures work", "check my plots", "are my graphs…

Mathews-Tom/armory · 123 tokens

linkedin-post-style

Writes LinkedIn posts in a direct, analytical, dry-humored technical voice with visual companion guidance. Triggers on: "write this in my style", "draft a post", "rewrite this for LinkedIn", "post about this", "how should I phrase this".

Mathews-Tom/armory · 60 tokens

manuscript-provenance

Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).

Mathews-Tom/armory · 70 tokens

manuscript-review

Pre-publication manuscript audit producing a section-level refactoring report with citation hygiene and submission-readiness checks. Triggers on: "review my paper", "check before submission", "is this ready to submit", "pre-pub checklist", "refactor my paper", "check my references", "does the abstract work".

Mathews-Tom/armory · 70 tokens