What is yandex-cloud-search-cost-control?

A procedure for investigating and controlling unexpected costs from the paid Yandex Cloud Search API. The API is a service that lets software send search requests to Yandex Cloud.

Use it to trace billing entries, inspect local callers and logs, pause a proven source of requests, and verify the result without revealing secrets.

It helps identify which product, account, key, time period, and local process caused a charge instead of confusing it with other Yandex or search tools. It also requires evidence before stopping a caller and approval before key removal or replacement.

yandex-cloud-search-cost-control — Skill for Codex by nebelov

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 nebelov/yandex-direct-for-all --skill yandex-cloud-search-cost-control

Clone the repo

git clone --depth 1 https://github.com/nebelov/yandex-direct-for-all

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-cloud-search-cost-control/github.svg)](https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-cloud-search-cost-control)

Your own site

<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-cloud-search-cost-control"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-cloud-search-cost-control/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-cloud-search-cost-control"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-cloud-search-cost-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 657 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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00657
Opus 5	$0.00014	$0.00329
Sonnet 5	$0.00005	$0.00131
Haiku 4.5	$0.00003	$0.00066

Measured 13d ago against content hash b7367445efc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yandex-cloud-search-cost-control 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 13d 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.

plugins/yandex-direct-for-all/skills/yandex-cloud-search-cost-control/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Контроль расходов Yandex Cloud Search API

Разделение продуктов

Не смешивай:

платный Yandex Cloud Search API, в частности POST /v2/web/search;
Яндекс Директ;
Wordstat;
встроенный веб-поиск модели;
браузерный сбор и другие обходчики.

Источник расхода не считается найденным, пока не совпали продукт, время, ключ или служебная учётная запись, настроенный вызывающий контур и факт вызова.

Порядок расследования

Подтверди строку биллинга, платный продукт и окно времени.
Собери безопасные названия облака, папки, служебных учётных записей и ключей. Идентификаторы маскируй, секреты не печатай.
Проверь все местные вызывающие контуры: подключаемые службы, файлы среды, сценарии, расписания, процессы и журналы фактических вызовов.
Если мониторинг или журнал аудита недоступен, зафиксируй разрыв атрибуции. Пустой журнал не доказывает отсутствие расхода.
Сначала отключи или приостанови доказанный местный вызывающий контур, затем перечитай его состояние.
Удаление, отключение или замена облачного ключа требует явного одобрения с названием ключа, служебной учётной записью, областью, влиянием и путём восстановления.
После изменения повторно проверь ключ, вызывающий контур и окно фактического потребления. Нулевой отчёт сначала сверь с заведомо положительным днём или другим надёжным контролем.

Ворота публичного моста

mcp/yandex-search по умолчанию выключен. Он читает ключ и папку только из YANDEX_SEARCH_API_KEY и YANDEX_SEARCH_FOLDER_ID.

YANDEX_SEARCH_ROUTE=manual разрешает один вызов, только если его тело содержит точный paid_search_approval с approved=true, маршрутом, max_calls=1 и ссылкой на одобрение.
YANDEX_SEARCH_ROUTE=approved требует закрытый YANDEX_SEARCH_APPROVAL_FILE, точный отпечаток папки, срок, список маршрутов, предел вызовов и закрытый YANDEX_SEARCH_USAGE_LEDGER.

Вызов резервирует единицу лимита до сети. Повтора и переключения на другой платный маршрут после ошибки нет.

Отчёт

Сначала укажи подтверждённый платный продукт и окно, затем вызывающий контур или разрыв атрибуции, потом безопасные названия ключей и служебных учётных записей, принятое действие и проверку после него. Не утверждай, что расход остановлен, без чтения состояния вызывающего контура и окна фактического потребления.

Read the full file on GitHub · 42 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 444 B

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.

13d ago First seen · 42 lines · 27 tokens per session scan A b7367445efc1

Subscribe to this mod's changes

yandex-cloud-search-cost-control is a skill published in the GitHub repository nebelov/yandex-direct-for-all (21 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 657 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 2026-08-30.

Claude Code Finance and fintech ai-agents codex-plugin marketing-ops mcp wordstat

cost

Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native session data for exact numbers. Complements /dashboard with focused cost views.

SethGammon/Citadel · 46 tokens

negotiation-game-theory

Structures negotiations as formal games with mathematically defined bottom lines, solution sets, and optimal agreement points using the Nash Product Solution. Provides the strategic and quantitative complement to relationship-based negotiation frameworks. Use when calculating walk-away points for fundraising rounds…

fatihguner/foreman · 91 tokens

matlab-optimize-portfolio

Help users formulate and solve portfolio optimization problems using Financial Toolbox's Portfolio object. Covers mean-variance (Markowitz), maximum Sharpe ratio (tangency), and efficient frontier workflows. Use when users ask about portfolio optimization, Markowitz, efficient frontier, Sharpe ratio, or attempt to use…

matlab/matlab-agentic-toolkit · 87 tokens

matlab-price-instrument

Price financial instruments in MATLAB using the Financial Instruments Toolbox. Route to the appropriate numerical method reference based on the user's request: Monte Carlo simulation (AssetMonteCarlo, IRMonteCarlo, RoughVolMonteCarlo), FFT / Numerical Integration (Vanilla European options), or Interest-Rate Trees…

matlab/matlab-agentic-toolkit · 181 tokens

matlab-access-datafeed

Guide for accessing financial and economic data in MATLAB using the Datafeed Toolbox. Covers Bloomberg (market data via bloomberg/blp/bloombergHypermedia), FRED (Federal Reserve economic data via fredrs), Haver Analytics (economic data via haver/haverdirect/haverview), and LSEG Datastream (historical data via…

matlab/matlab-agentic-toolkit · 90 tokens

finance

Runtime subject skill payload for finance subject activation.

jxpeng98/qiongli · 11 tokens