A command for auditing a connected Yandex Direct advertising account. It reviews campaigns, the last 30 days of spending and results, unusual issues, balance, and overdraft.

Use it to inspect campaign status, spending, clicks, conversions, cost per conversion, account balance, and possible anomalies. The Yandex Direct connection must be authenticated first.

It turns several account checks into one structured review, helping identify campaigns that may be underperforming or running low on funds.

audit — Command by askads

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.

agentmods

npx agentmods add commands/askads/claude-plugins/audit

Clone the repo

git clone --depth 1 https://github.com/askads/claude-plugins

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 554 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00027	$0.00554
Opus 5	$0.00014	$0.00277
Sonnet 5	$0.00005	$0.00111
Haiku 4.5	$0.00003	$0.00055

Measured yesterday against content hash 921c1cd36e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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.

plugins/yandex-direct/commands/audit.md · 31 lines

What it actually says

Проведи аудит подключённого кабинета Яндекс Директа. Действуй по шагам:

Если тулы Директа (get_account_info, list_campaigns, …) в этом чате недоступны — не продолжай и не выдумывай данные. Объясни пользователю, как авторизовать коннектор:
- Claude Code: команда /mcp → выбрать yandex-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 пусть откроет новый чат и снова запустит /yandex-direct:audit.
get_account_info — валюта и тип кабинета; get_balance — баланс единого счёта. Остаток овердрафта возьми из get_account_info с fieldNames: ["OverdraftSumAvailable"] (микроединицы → дели на 1 000 000). Показы под угрозой, только если max(баланс, 0) + овердрафт ≤ 0 или близко к нулю.
list_campaigns — какие кампании активны, какие остановлены/приостановлены.
get_statistics за LAST_30_DAYS (CAMPAIGN_PERFORMANCE_REPORT, fieldNames: CampaignId, CampaignName, Impressions, Clicks, Cost, Conversions, CostPerConversion) — по всем кампаниям.
Найди проблемы:
- кампании с заметным расходом и нулём конверсий (возможен слив или поломка трекинга);
- аномально дорогой CPA/CPC относительно остальных кампаний кабинета;
- активные кампании почти без показов (мало трафика или низкие ставки);
- риск остановки показов по балансу.
Сведи результат в короткий отчёт: топ-3 проблемы, у каждой — деньги под риском в валюте кабинета из get_account_info за период и конкретное действие. Коннектор read-only — изменения пользователь вносит в интерфейсе Директа сам.

Дополнительный фокус от пользователя: $ARGUMENTS

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.

yesterday First seen · 31 lines · 27 tokens per session scan A 921c1cd36e47

Subscribe to this mod's changes

audit is a command published in the GitHub repository askads/claude-plugins (2 stars, last pushed 21d ago), licensed MIT. It adds 27 tokens to every session and 554 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 2026-08-31.

audit

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement