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/askads/claude-plugins/yandex-directnpx skills add askads/claude-plugins --skill yandex-directgit clone --depth 1 https://github.com/askads/claude-pluginsWrote 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/askads/claude-plugins/yandex-direct)<a href="https://agentmods.dev/skills/askads/claude-plugins/yandex-direct"><img src="https://agentmods.dev/badge/skills/askads/claude-plugins/yandex-direct.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 | $0.00065 | $0.01108 |
| Opus 5 | $0.00032 | $0.00554 |
| Sonnet 5 | $0.00013 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
yandex-direct 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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Яндекс Директ через Ask Ads MCP
Коннектор строго read-only: ни один инструмент ничего не меняет в кабинете. Если пользователь просит что-то изменить (ставки, бюджеты, статусы) — объясни, что коннектор только читает, и предложи конкретные шаги для ручного изменения в интерфейсе Директа.
Если тулы Директа недоступны
Не гадай и не выдумывай данные — коннектор не авторизован. Дай пользователю шаги:
- Claude Code:
/mcp→ выбратьyandex-direct→ Authenticate (вход через Яндекс); - Claude Desktop / claude.ai: Settings → Connectors → коннектор Ask Ads → Connect;
если коннектора нет в списке — Add custom connector →
https://mcp.askads.cloud/mcp.
После авторизации — открыть новый чат и повторить запрос.
С чего начинать
get_account_info— логин, валюта кабинета, тип (агентство/рекламодатель).list_campaigns— карта кампаний: Id, Name, Type, State (ON/OFF/SUSPENDED…), Status.
Дальше отвечай на вопрос пользователя, фильтруя по campaignIds, — не выгружай
весь аккаунт без необходимости.
Статистика
get_statistics — отчёты Reports API:
reportType: чаще всегоCAMPAIGN_PERFORMANCE_REPORT; по объявлениям —AD_PERFORMANCE_REPORT, по фразам —CRITERIA_PERFORMANCE_REPORT.dateRangeType:LAST_7_DAYS,LAST_30_DAYS,THIS_MONTHилиCUSTOM_DATE+dateFrom/dateTo(YYYY-MM-DD).fieldNames: запрашивай только нужное, например["CampaignId", "CampaignName", "Impressions", "Clicks", "Cost", "Conversions", "CostPerConversion"].- Сузь выборку через
campaignIds, когда речь об конкретных кампаниях.
Деньги в отчётах и списках сервер уже отдаёт в валюте кабинета (микроединицы
сконвертированы). Валюту бери из get_account_info — не предполагай, что это ₽.
Баланс и «показы остановлены»
get_balance— баланс единого счёта (Live v4):Amountстрокой в валюте кабинета, отрицательное значение = задолженность.- Остаток овердрафта:
get_account_infoсfieldNames: ["OverdraftSumAvailable"]— значение в микроединицах, дели на 1 000 000. - «Тратить нечем» (показы встают) только когда
max(баланс, 0) + остаток овердрафта ≤ 0. Минус на балансе при живом овердрафте — показы идут (кабинет тратит в кредит); не пугай пользователя преждевременно.
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.
- 5d ago First seen · 75 lines · 65 tokens per session scan A 04071b1c0300
yandex-direct is a skill published in the GitHub repository askads/claude-plugins (2 stars, last pushed 25d ago), licensed MIT. It adds 65 tokens to every session and 1,108 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…