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 agentmods add skills/nextstat/yacli/yacli-sharednpx skills add NextStat/yacli --skill yacli-sharedgit clone --depth 1 https://github.com/NextStat/yacliWrote 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/nextstat/yacli/yacli-shared)<a href="https://agentmods.dev/skills/nextstat/yacli/yacli-shared"><img src="https://agentmods.dev/badge/skills/nextstat/yacli/yacli-shared.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 | $0.00056 | $0.00656 |
| Opus 5 | $0.00028 | $0.00328 |
| Sonnet 5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
yacli-shared 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 4d 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.
What it actually says
yacli — общая основа
yacli — CLI для Яндекс Почты, Календаря и Диска. Все команды возвращают JSON.
Формат вывода
Успех: {"ok": true, ...}. Ошибка: {"ok": false, "code": "...", "message": "..."}.
--format table — человекочитаемый вид. По умолчанию --format json.
Коды завершения
| Код | Значение |
|---|---|
| 0 | Успех |
| 1 | Ошибка пользователя (валидация, авторизация, не найдено) |
| 4 | Ошибка конфигурации или ввода/вывода |
| 5 | Ошибка сети или API |
Управление аккаунтами
yacli поддерживает несколько аккаунтов. У каждого есть короткий алиас.
| Команда | Описание |
|---|---|
yacli add <EMAIL> [ALIAS] |
Добавить аккаунт |
yacli accounts |
Список аккаунтов |
yacli use <ALIAS> |
Переключить текущий аккаунт |
yacli whoami |
Показать текущий аккаунт |
yacli status [--account ALIAS] |
Показать подключённые сервисы |
Авторизация
Каждый сервис авторизуется отдельно:
- Почта: OAuth XOAUTH2 (по умолчанию) или пароль приложения
- Календарь: только пароль приложения
- Диск: только OAuth
| Команда | Описание |
|---|---|
yacli login [SERVICE] |
Подключить почту, календарь или диск |
yacli login mail --app-password ПАРОЛЬ |
Почта через пароль приложения |
yacli login calendar --app-password ПАРОЛЬ |
Календарь через пароль приложения |
yacli logout [SERVICE] [--account ALIAS] |
Отключить один или все сервисы |
SERVICE: mail, calendar, disk. Без аргумента — подключить все.
Глобальные флаги
--format json|table— формат вывода (по умолчанию: json)--account ALIAS— целевой аккаунт (по умолчанию: текущий)-h, --help— справка-V, --version— версия
Несколько аккаунтов
Передавай --account ALIAS при работе не с текущим аккаунтом:
yacli mail list --account work
yacli calendar events --account personal
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.
- 4d ago First seen · 70 lines · 56 tokens per session scan A b256c273e2a3
yacli-shared is a skill published in the GitHub repository NextStat/yacli (15 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 656 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
chatgpt-app-builder
Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.
purchasing
Create approved purchase orders with the create-purchase-order tool.
refunds
Check refund eligibility and use the refund-order tool safely.
mcp-patterns
MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, choosing a transport, adding OAuth authentication, wiring MCP Apps UI with @mcp-ui, hardening MCP security, or debugging MCP integrations.
openapi-to-mcp
Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools…
create-tool
ALWAYS use this skill when the user asks to build, modify, or audit a FrontMCP tool. Covers everything inside @Tool({...}): class and function-style tools, Zod input/output schemas with derived execute() types, dependency injection (this.get / this.tryGet), error handling (this.fail, MCP error classes), throttling…