agentmods.dev

build-bot-funnel

build-bot-funnel is a skill for Claude Code from skiddgoddamn/zaytsv-mcp. It costs 137 tokens per session (2,592 once invoked), scanned A, original, MIT.

A workflow that turns a written conversation plan into a validated chatbot flow for Telegram, MAX, or Instagram.

In plain words
What is it for?
It helps build greetings, questions, buttons, branches, delays, subscriptions, broadcasts, and platform-specific entry points, then dry-run and publish the resulting flow.
Why use it?
It removes the need to manually draw and check the bot’s branching logic before testing or publishing it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zaytsv-mcp plugin — 1 skill, 1 MCP server shipped together

not rated 0repo 2mo ago A scan 137 tokens original MIT

Good fit It helps build greetings, questions, buttons, branches, delays, subscriptions, broadcasts, and platform-specific entry points, then dry-run and publish the resulting flow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel
View source ↗ skiddgoddamn/zaytsv-mcp zaytsv.ru
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 skiddgoddamn/zaytsv-mcp --skill build-bot-funnel
Clone the repo
git clone --depth 1 https://github.com/skiddgoddamn/zaytsv-mcp

Made for: Claude Code.

Or install zaytsv-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 build-bot-funnel

README.md
[![agentmods](https://agentmods.dev/badge/skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel/github.svg)](https://agentmods.dev/skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel)
Your own site
<a href="https://agentmods.dev/skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel"><img src="https://agentmods.dev/badge/skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel/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 build-bot-funnel

Your own site · 80×15
<a href="https://agentmods.dev/skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel"><img src="https://agentmods.dev/badge/skills/skiddgoddamn/zaytsv-mcp/build-bot-funnel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,592 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 $0.00137 $0.02592
Opus 5 $0.00068 $0.01296
Sonnet 5 $0.00027 $0.00518
Haiku 4.5 $0.00014 $0.00259

Measured 11d ago against content hash 66c23c1db32a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

build-bot-funnel 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (validate.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/build-bot-funnel/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Сборка воронки бота (zaytsv /bots)

Превращает текстовое описание воронки в валидный граф zaytsv-bot-graph и (опционально) публикует его через MCP-сервер bot-graph. Поддерживаются платформы Telegram, MAX и Instagram — у каждой свои триггеры и ограничения, описанные в schema.md.

Различия платформ (кратко):

  • Telegram — полный функционал: /start и другие команды, все типы узлов, SUBSCRIBED, кнопки-контакты, рассылки.
  • MAX — те же узлы, но без SUBSCRIBED/reply-клавиатур (мягкие предупреждения при публикации, не блокируют).
  • Instagram — ограниченный набор узлов; вход только через комментарий/директ/историю (нет /start); нет рассылок; DELAY не более 24ч; ASK_QUESTION только TEXT/EMAIL/PHONE/NUMBER/CONTACT (CONTACT = ручной ввод номера, кнопки «Поделиться номером» в IG нет); онбординг через OAuth в разделе «Инструменты роста» (/growth), без токена бота.

Когда применять

Пользователь описывает сценарий бота словами: приветствие → подписка → вопрос с кнопками → ветки → задержки → вебинар и т.п. Либо просит залить/опубликовать готовую воронку.

Рабочий процесс (делай по шагам)

  1. Уточни вход. Если описание неполное, спроси кратко: точка(и) входа (команда /start и т.п.), тексты сообщений, кнопки и куда они ведут, развилки/условия, задержки, финал. Не выдумывай маркетинговые тексты — проси у пользователя или помечай [ВСТАВЬ ТЕКСТ] только если он сам разрешил.

  2. Спланируй граф. Нарисуй в голове дерево: триггеры → сообщения → ветки. Каждой кнопке-выбору — свой выходной хэндл (btn_0, btn_1…). Подробности типов узлов и хэндлов: reference/schema.md.

  3. Сгенерируй JSON формата zaytsv-bot-graph (см. схему). Требования к корректности (иначе не опубликуется) — в reference/validation.md. Главное:

    • У каждого SEND_MESSAGE непустой config.text (и продублируй в cards[0].text).
    • id узлов и рёбер — валидные UUID, уникальные.
    • Есть хотя бы один корневой TRIGGER_*; все нелистовые узлы достижимы от триггера; синхронных циклов нет (цикл только через ASK_QUESTION/DELAY/SCHEDULE).
    • Кнопки-выборы разведены по хэндлам btn_N — у такой CALLBACK-кнопки value ОБЯЗАТЕЛЬНО пустой (""): бот сам сгенерит callback_data, непустой value ломает переход (NO_MATCH). Цвет кнопки — только ""/#34C759/#FF3B30. Условия CONDITION — yes/no; вопрос (ASK_QUESTION или SEND_MESSAGE с awaitReply:true) — valid/invalid.
    • Не добавляй узлы END — ветка завершается сама на узле без исходящих рёбер; явный «конец сценария» убран из редактора.
    • SEND_MESSAGE умеет быть и сообщением, и вопросом (awaitReply:true + saveTo/inputKind/validator). У кнопок-ссылок (kind:"URL") есть флаг track:true — на такой шаг ссылается условие LINK_CLICKED.
    • Медиа (фото/видео/аудио/документ/кружок/галерея): загрузи файл инструментом upload_file (локальный path или url для перезаливки) → получишь публичный URL → вставь его в медиа-карточку SEND_MESSAGE (url, у gallery — urls[]) или в SEND_PHOTO.photoUrl. Уже загруженное — list_files. Бинарь в графе не хранится, только ссылки. Подробности — в schema.md.
    • CONDITION умеет: теги, переменные, UTM-метки, имя/email/телефон из профиля, @username, подписку на канал (SUBSCRIBED), клик по ссылке шага (LINK_CLICKED), дату/время/день недели. Полная таблица kind/op — в schema.md.
    • Пакет ACTIONS — до 30 действий (метки, профиль, HTTP, уведомления, интеграции GetCourse/amoCRM/Google Sheets/Я.Метрика, модерация группы). Список — в schema.md.

Read the full file on GitHub · 71 lines

Files

What ships with it

3 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. 11d ago First seen · 71 lines · 137 tokens per session scan A 66c23c1db32a

Subscribe to this mod's changes

build-bot-funnel is a skill published in the GitHub repository skiddgoddamn/zaytsv-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 137 tokens to every session and 2,592 once invoked, about $0.0007 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.

Claude CodeMarketing and SEOanthropicautomationbotchatbotclaude
Related

Other skills, from other repositories

c-telegram

Bidirectional Telegram bridge — talk to Claude from your phone. Built into OpenPaw.

daxaur/openpaw · 22 tokens

telegram-bot

Telegram bot development - chatbots, notifications, AI assistants, and group automation.

claude-office-skills/skills · 19 tokens

profile-screening

Scores a potential date against the user's stated preferences (traits, dealbreakers, age range, distance, intent) and returns a like/pass decision with reasons.

sumitaich1998/OpenDate · 36 tokens

consent-and-safety

The hard guardrail on every action — enforces honesty, consent, and respect; blocks deception, coercion/pressure, harassment, and unwanted explicit content; backs off the moment disinterest appears.

sumitaich1998/OpenDate · 46 tokens

approaching

Breaks the ice and sets the tone in the first couple of exchanges right after a match, establishing warmth and momentum.

sumitaich1998/OpenDate · 27 tokens

banter

Witty, fast back-and-forth with light teasing and callbacks to build chemistry and tension when both people are matching energy.

sumitaich1998/OpenDate · 28 tokens