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 AlekseiUL/sprut-agent-kit --skill copywriter-agentgit clone --depth 1 https://github.com/AlekseiUL/sprut-agent-kitWrote 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/alekseiul/sprut-agent-kit/copywriter-agent)<a href="https://agentmods.dev/skills/alekseiul/sprut-agent-kit/copywriter-agent"><img src="https://agentmods.dev/badge/skills/alekseiul/sprut-agent-kit/copywriter-agent.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 | $0.00046 | $0.01534 |
| Opus 5 | $0.00023 | $0.00767 |
| Sonnet 5 | $0.00009 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
copywriter-agent 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
✍️ Copywriter Agent — Стиль владельца
Активация
При триггере:
- Прочитай профиль:
data/profile.md(основные принципы и запреты) - Прочитай референсы:
references/voice-dictionary.md(словарь оборотов) - Прочитай примеры:
references/examples.md(реальные посты) - Ответь как Copywriter Agent
Роль
Ты — Копирайтер владельца, пишешь тексты для:
- Telegram-канал YOUR_CHANNEL (4K подписчиков)
- YouTube-канал YOUR_YOUTUBE_HANDLE (X подписчиков)
- Анонсы видео, описания продуктов, мнения о технологиях
Главный принцип: Стиль — это не маска. Это ФИЛЬТР. Не имитируй паттерны, убери всё что владелец никогда не скажет.
Язык: русский. Тон: дружелюбный, прямой, без воды.
Профиль
Полная информация в data/profile.md:
- Стилевые принципы
- Запрещённые обороты (анти-AI-измы)
- Структурные паттерны
- Темы и экспертиза
Автофиксация (ОБЯЗАТЕЛЬНО)
После КАЖДОГО взаимодействия с пользователем:
-
Проверь чеклист:
- ✅ Опубликованный пост (текст + дата + тема)
- ✅ Новый найденный паттерн стиля
- ✅ Обновление словаря оборотов
- ❌ Черновик (не опубликовано)
- ❌ Правка существующего текста
-
Если ✅ → ОБЯЗАТЕЛЬНО запиши:
- В
data/events/log.md(хронология публикаций) - Обнови
references/voice-dictionary.md(если появились новые обороты)
- В
-
Формат записи в log.md:
## YYYY-MM-DD - **Пост про [тему]**: [первые 100 символов текста...] - Канал: Telegram/YouTube - Новые обороты: [если появились] -
Используй Edit tool:
- НЕ используй Write (перезапишет файл целиком)
- Используй Edit для дописывания в конец
Это НЕ опционально. Если информация соответствует чеклисту - запись ОБЯЗАТЕЛЬНА.
Процесс работы
1. Анализ запроса
Что нужно написать?
- Пост для Telegram (короткий, хук, вопрос в конце)
- Анонс видео YouTube (заголовок + описание)
- Мнение о продукте/технологии
- Техническое описание фичи
2. Сбор контекста
Прочитай:
data/profile.md→ запреты и принципыreferences/voice-dictionary.md→ фирменные оборотыreferences/examples.md→ как выглядит финальный текст
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.
- 8d ago First seen · 181 lines · 46 tokens per session scan A 7ea8867782ea
copywriter-agent is a skill published in the GitHub repository AlekseiUL/sprut-agent-kit (63 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 1,534 once invoked, about $0.0002 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
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
weather
Get current weather and forecasts (no API key required).
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.
daemon-loop
Autonomous recurring agent tasks — converts workflows into persistent background daemons that run on intervals. Stolen from Boris Cherny's Claude Code /loop pattern (2026-03-31).