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 axisrow/yandex-direct-mcp-plugin --skill direct-edagit clone --depth 1 https://github.com/axisrow/yandex-direct-mcp-pluginWrote 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/axisrow/yandex-direct-mcp-plugin/direct-eda)<a href="https://agentmods.dev/skills/axisrow/yandex-direct-mcp-plugin/direct-eda"><img src="https://agentmods.dev/badge/skills/axisrow/yandex-direct-mcp-plugin/direct-eda.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 | $0.00106 | $0.02163 |
| Opus 5 | $0.00053 | $0.01081 |
| Sonnet 5 | $0.00021 | $0.00433 |
| Haiku 4.5 | $0.00011 | $0.00216 |
Grade A, and why
direct-eda 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- direct-eda — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Разведочный анализ статистики Яндекс.Директ (EDA)
Скилл для исследования статистики кампаний через отчётные MCP-инструменты плагина.
Не вводит новых API-методов — это композиция reports_get / reports_custom /
reports_list_types (+ v4goals_get_stat_goals для целей) с правильным выбором
разреза, метрик и подачи выводов.
С чего начинать
- Авторизация. Сначала
auth_status(). Еслиvalid: false—auth_login(). Без авторизации отчёты вернут ошибку. - Выбор инструмента:
reports_get(date_from, date_to)— быстрый снимок по кампаниям за короткое окно (по умолчанию ~8 дней, дефолтные поля). Для ответа «как там кампании».reports_custom(field_names=…)— всё остальное: произвольные поля, разрезы по времени/срезам, фильтры, сортировка, цели, пагинация, выгрузка в файл.reports_list_types()— если не уверен, какойreport_typeподходит.
- Сомневаешься в полях/фильтрах —
dry_run=True. Reports API отвергает неверные enum'ы опаковымerror_code=8000; локальный dry-run экономит раунд-трип и показывает итоговыйrequest_body.
Типовые рецепты EDA
report_type по умолчанию = CUSTOM_REPORT (самый широкий набор измерений).
Деньги по умолчанию в рублях (не микро). field_names — регистрозависимый enum.
| Вопрос | Как получить |
|---|---|
| Общий снимок по кампаниям | reports_get() (или reports_custom с CampaignName,Impressions,Clicks,Cost,Conversions,Ctr,AvgCpc) |
| Динамика по месяцам/неделям/дням | field_names="Month,Cost,Clicks,Conversions,…", order_by=["Month:ASC"] (или Week/Date) |
| Топ-N кампаний по расходу/конверсиям | field_names="CampaignName,Cost,Clicks,Conversions,CostPerConversion", order_by=["Cost:DESC"], page_limit=N |
| Топ-N ключевых фраз | report_type="CRITERIA_PERFORMANCE_REPORT", field_names="CampaignName,Criterion,Clicks,Cost,Ctr,Conversions", order_by=["Cost:DESC"], page_limit=N |
| Разрез по устройствам | field_names="Device,Cost,Clicks,Ctr,Conversions,CostPerConversion" |
| Разрез по площадкам (Поиск/Сети) | field_names="AdNetworkType,Cost,Clicks,Ctr,Conversions" |
| Пол / возраст | field_names="Gender,Age,Impressions,Clicks,Ctr,Conversions" |
| География | field_names="LocationOfPresenceName,Cost,Clicks,Conversions" (или TargetingLocationName) |
| Поисковые запросы (для минус-слов / новых ключей) | report_type="SEARCH_QUERY_PERFORMANCE_REPORT", field_names="Query,Impressions,Clicks,Ctr,Cost,Conversions", order_by=["Cost:DESC"] |
| Конверсии по целям Метрики | задай goal_ids="123,456" → в выводе появятся Conversions_<goal>_<attr> и CostPerConversion_<goal>_<attr>. ID целей: v4goals_get_stat_goals(campaign_ids=…) |
| Итоги по всему аккаунту | report_type="ACCOUNT_PERFORMANCE_REPORT" |
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.
- 7d ago First seen · 117 lines · 106 tokens per session scan A 090f0697254e
direct-eda is a skill published in the GitHub repository axisrow/yandex-direct-mcp-plugin (12 stars, last pushed 6d ago), licensed MIT. It adds 106 tokens to every session and 2,163 once invoked, about $0.0005 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
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…