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.
npx skills add ilyautov/small-business-ru --skill handle-complaintgit clone --depth 1 https://github.com/ilyautov/small-business-ruWrote 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/skills/ilyautov/small-business-ru/handle-complaint)<a href="https://agentmods.dev/skills/ilyautov/small-business-ru/handle-complaint"><img src="https://agentmods.dev/badge/skills/ilyautov/small-business-ru/handle-complaint/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/skills/ilyautov/small-business-ru/handle-complaint"><img src="https://agentmods.dev/badge/skills/ilyautov/small-business-ru/handle-complaint.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 | $0.00062 | $0.01102 |
| Opus 5 | $0.00031 | $0.00551 |
| Sonnet 5 | $0.00012 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
handle-complaint 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Злой клиент — это ещё спасаемый клиент, если ответить быстро и по делу. Скилл поднимает историю и заказ, готовит ответ под остроту ситуации и заодно подсказывает, что починить, чтобы та же жалоба не пришла снова.
Запустите разбор жалобы, связав два скилла. Прочитайте жалобу, соберите контекст, подготовьте ответ и предложите исправление, чтобы это не повторилось.
Разбор аргументов:
EMAIL_OR_TICKET_ID(необязательно) — ID письма (~~почта), ID обращения (~~crm) или «последняя», чтобы взять самую свежую нерешённую жалобу. Если не указан — попросите владельца вставить текст жалобы.
Шаг 1 — Загрузить жалобу (ticket-deflector)
По рабочему процессу скилла ticket-deflector:
- Если дан ID: подтяните полную переписку из
~~почтыили~~crm. - Если «последняя»: подтяните самое свежее нерешённое обращение из
~~crmили письмо из~~почтыс пометкой жалоба/поддержка. - Если ничего нет: попросите владельца вставить текст жалобы напрямую.
- Определите: имя клиента, данные заказа/счёта, чем недоволен, что просит.
Шаг 2 — Собрать контекст
- Найдите историю клиента в
~~crm: прошлые покупки, прежние жалобы, стадия сделки, сумма покупок за всё время. - Найдите связанную операцию в
~~платежах: статус заказа, история возвратов, статус спора. - Сведите итог: «Это {новый/постоянный} клиент, покупок на {сумма} ₽, {0/N} прежних жалоб. Текущая проблема — {одно предложение}.»
Шаг 3 — Подготовить ответ (ticket-deflector)
По рабочему процессу скилла ticket-deflector (ответ в подобранном тоне):
- Подготовьте ответ под остроту ситуации и историю клиента:
- Впервые жалуется, много покупок → с пониманием, щедро
- Жалуется повторно → корректно, твёрдо, по делу
- Хамит → корректно, кратко, с обозначением границ
- Включите: признание, объяснение (если известно), предложение решения, следующий шаг.
- ⚠️ Если жалоба про возврат/качество товара — действуйте в общей рамке закона «О защите прав потребителей», не выдумывайте конкретные статьи и сроки. При сомнении — «уточните условия возврата».
- Покажите черновик владельцу. НЕ отправляйте.
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.
- yesterday Changed · -20 tokens per session e7999026fb9d
- 12d ago First seen · 63 lines · 82 tokens per session scan A 454fd43f392a
handle-complaint is a skill published in the GitHub repository ilyautov/small-business-ru (15 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,102 once invoked, about $0.0003 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.
Other skills, from other repositories
manuscript-typography
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic…
architecture-diagram
Generate architecture diagrams as fully editable SVG with native AWS, Azure, and GCP icons for cloud diagrams, or hand-drawn generic icons for everything else. Optionally deliver a self-contained editable draw.io mxGraph companion. Deterministic layout computes zone nesting and orthogonal routing instead of…
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…
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.
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…
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".