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-client-lifecyclegit 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-client-lifecycle)<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-direct-client-lifecycle"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-direct-client-lifecycle/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-client-lifecycle"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-direct-client-lifecycle.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 | $0.00031 | $0.00091 |
| Opus 5 | $0.00015 | $0.00046 |
| Sonnet 5 | $0.00006 | $0.00018 |
| Haiku 4.5 | $0.00003 | $0.00009 |
Grade A, and why
yandex-direct-client-lifecycle 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
Переход на единый навык
Сначала открыть соседний ../yandex-direct-unified/SKILL.md и выполнить его порядок. В этом каталоге остаются переносимые сценарии и шаблоны исследования; отдельного канона здесь нет.
What ships with it
46 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 332 B
- references/artifact-contract.md 3.8 KB
- references/coverage-checklist.md 4.5 KB
- references/handoff-map.md 1.0 KB
- references/source_skill_contract.md 386 B
- scripts/build_domain_shortlist_from_serp.py 4.6 KB runs code
- scripts/build_followup_jobs_from_serp.py 6.2 KB runs code
- scripts/build_serp_jobs_from_keyword_matrix.py 7.1 KB runs code
- scripts/firecrawl_scrape.py 11 KB runs code
- scripts/merge_sitemap_batch_outputs.py 3.2 KB runs code
- scripts/render_ad_serp_wave.py 6.0 KB runs code
- scripts/render_page_capture_inventory.py 3.5 KB runs code
- scripts/render_serp_wave.py 3.4 KB runs code
- scripts/render_sitemap_candidates.py 2.7 KB runs code
- scripts/scaffold_client_lifecycle.py 5.9 KB runs code
- scripts/sitemap_probe_batch.py 12 KB runs code
- scripts/split_tsv_batch.py 1.7 KB runs code
- scripts/verify_research_bundle.py 9.0 KB runs code
- scripts/yandex_browser_serp_batch.py 9.1 KB runs code
- scripts/yandex_search_ads_batch.py 20 KB runs code
- scripts/yandex_search_batch.py 15 KB runs code
- templates/access-status-template.md 1.0 KB
- templates/ad-serp-job-template.tsv 280 B
- templates/client-kb-template.md 750 B
- templates/company-footprint-template.md 777 B
- templates/competitor-raw-register-template.tsv 221 B
- templates/direct-copy-pack-template.tsv 591 B
- templates/fact-check-log-template.tsv 222 B
- templates/future-cabinet-structure-template.md 1.4 KB
- templates/human-review-template.tsv 294 B
- templates/landing-inventory-template.md 285 B
- templates/landing-inventory-tsv-template.tsv 439 B
- templates/offers-pack-template.md 1.6 KB
- templates/page-capture-job-template.tsv 468 B
- templates/product-map-template.md 1.2 KB
- templates/proposal-pack-template.md 330 B
- templates/research-backlog-template.md 347 B
- templates/routing-map-template.tsv 302 B
- templates/search-api-env-template.env 226 B
- templates/semantics-product-map-template.md 1.2 KB
- templates/serp-job-template.tsv 524 B
- templates/sitemap-job-template.tsv 287 B
- templates/source-register-template.tsv 299 B
- templates/unified-competitor-map-template.md 2.3 KB
- templates/wordstat-masks-wave1-template.tsv 264 B
- templates/yandex-performance-client-template.json 1.2 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 · 9 lines · 31 tokens per session scan A 421542c4c02f
yandex-direct-client-lifecycle is a skill published in the GitHub repository nebelov/yandex-direct-for-all (21 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 91 once invoked, about $0.0002 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.