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 nebelov/yandex-direct-for-all --skill yandex-direct-unifiedgit clone --depth 1 https://github.com/nebelov/yandex-direct-for-allWrote 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/nebelov/yandex-direct-for-all/yandex-direct-unified)<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-direct-unified"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-direct-unified/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.
<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-direct-unified"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-direct-unified.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00516 |
| Opus 5 | $0.00026 | $0.00258 |
| Sonnet 5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
yandex-direct-unified 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 12d 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
Яндекс.Директ: единый рабочий навык
Этот навык задаёт порядок работы. Узкие навыки yandex-wordstat, roistat-reports-api и amocrm-api-control уточняют свои программные интерфейсы, но не заменяют этот порядок.
Перед началом
- Пройти общий поиск навыков по теме задачи.
- Прочитать references/main-workflow.md и references/decision-rules.md.
- Для семантики прочитать references/keyword-collection-runbook.md.
- Для изменения самого навыка прочитать references/source-map.md.
- Для действующего кабинета, авторизации или любой записи пройти references/workflow-supervisor.md.
Все ссылки относительны каталога навыка: установка не зависит от имени пользователя и расположения домашнего каталога.
Неподвижные правила
- Сначала определить клиента, кабинет и разрешённый объём; затем читать данные.
- Доступ подтверждается свежим запросом к нужной службе, а не наличием файла с токеном.
- В поставке есть общие приложения авторизации для Директа и Метрики. Пользователю не требуется создавать собственное приложение.
- Авторизация Директа и Метрики раздельна. Токен, код подтверждения и секрет приложения не передаются в аргументах процесса и не печатаются.
- Чтение и запись разделены. Любая запись, запуск, модерация, бюджет или остановка трафика требуют отдельного явного разрешения.
- Имена кампаний и групп показываются пользователю раньше служебных номеров.
- Сырые данные Wordstat и поисковых фраз не являются готовой семантикой.
- Автоматические сценарии не принимают смысловые решения за человека или проверяющего агента.
- Секреты и клиентские выгрузки хранятся только вне каталога навыка.
Результат
Каждый запуск оставляет проверяемые входы, исходные ответы, решения, план изменения и чтение после изменения. Если обязательного доказательства нет, статус — BLOCKED с конкретной причиной, а не предположение о готовности.
What ships with it
10 files 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 504 B
- references/access-recovery-runbook.md 2.2 KB
- references/build-and-ops.md 1.9 KB
- references/decision-rules.md 1.9 KB
- references/keyword-collection-runbook.md 2.1 KB
- references/main-workflow.md 4.5 KB
- references/script-index.md 1.8 KB
- references/semantic-review-agent-brief.md 1.3 KB
- references/source-map.md 1.5 KB
- references/workflow-supervisor.md 1.5 KB
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.
- 12d ago First seen · 35 lines · 52 tokens per session scan A aa86bb15e83f
yandex-direct-unified is a skill published in the GitHub repository nebelov/yandex-direct-for-all (21 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 516 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.