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 theYahia/WWmcp --skill callbackgit clone --depth 1 https://github.com/theYahia/WWmcpWrote 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/theyahia/wwmcp/callback)<a href="https://agentmods.dev/skills/theyahia/wwmcp/callback"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/callback.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 | $0.00024 | $0.00610 |
| Opus 5 | $0.00012 | $0.00305 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
callback 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.
What it actually says
/callback — Обратный звонок и разбор разговора
Алгоритм
- Уточни, с какого внутреннего номера звоним. Если пользователь не знает — вызови
get_usersс limit и покажи список сотрудников с их внутренними номерами. - Вызови
make_callс from (внутренний номер или SIP-аккаунт инициатора), to (номер назначения в E.164 или внутренний) и опционально line — это CallerID, который увидит клиент. Сначала поднимется трубка сотрудника, потом пойдёт вызов клиенту. - После разговора вызови
get_callsс date_from и date_to за последние минуты, найди запись по номеру клиента и возьми из неё recording_id. - Вызови
get_recordingс recording_id и action = play (ссылка на прослушивание) или download (скачать файл). - Если клиент не ответил — вызови
send_smsс from_extension (внутренний номер отправителя), to_number и text (до 1000 символов). Формулируй коротко: кто звонил, по какому вопросу, как связаться. - Отчитайся: состоялся ли разговор, есть ли запись, ушла ли SMS.
Формат ответа
## Обратный звонок
**От**: 101 (Иванов И.)
**Кому**: +79121234567
**Линия**: +74951234567
**Результат**: разговор состоялся, 3 мин 42 с
**Запись**: https://app.mango-office.ru/... (ссылка временная)
SMS не отправлялась — клиент ответил.
Важно
make_callинициирует звонок физически. Не вызывай его «для проверки» — у сотрудника зазвонит телефон.- Запись появляется не мгновенно: сразу после разговора
get_callsможет ещё не отдать recording_id. Повтори через минуту, прежде чем говорить, что записи нет. - Ссылка из
get_recordingс action = play живёт ограниченное время. Не сохраняй её как постоянную. - Записи разговоров — персональные данные. Не пересказывай содержимое без запроса.
Примеры
/callback 101 +79121234567
/callback 101 +79121234567 "Звонили по вашей заявке, наберите нас"
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 First seen · 56 lines · 24 tokens per session scan A 74bdb7ae6701
callback is a skill published in the GitHub repository theYahia/WWmcp (28 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 610 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
n8n
Manage n8n workflow automation via its public REST API — list/get/create/update workflows, activate/deactivate, inspect execution history, retry/stop executions, manage credentials, tags, variables, users, and projects. Works with self-hosted n8n and n8n Cloud. Use when the user wants programmatic access to their n8n…
notion
Read and write Notion pages, databases, and blocks via the public REST API — query a database with filters, create/update pages, append block content, search the workspace. Use when the user wants an agent to interact with their Notion workspace (e.g., a tasks or docs database) without the MCP server installed.
slack
Send messages, read channels, search Slack via its Web API. Use when the user wants to post to a channel, read recent messages, list users/channels, or search a workspace programmatically — no MCP server required.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
notifications
Send notifications through the unified notification router.