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-performance-opsgit 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-performance-ops)<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-performance-ops"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-performance-ops/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-performance-ops"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-performance-ops.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 | $0.00028 | $0.00092 |
| Opus 5 | $0.00014 | $0.00046 |
| Sonnet 5 | $0.00006 | $0.00018 |
| Haiku 4.5 | $0.00003 | $0.00009 |
Grade A, and why
yandex-performance-ops 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. Этот каталог сохраняется только ради совместимости путей, сценариев и шаблонов. Он не задаёт отдельные правила работы.
What ships with it
60 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 434 B
- references/ad_format_limits.md 1.8 KB
- references/api_management_guide.md 3.0 KB
- references/competitor_research_workflow.md 652 B
- references/future_session_start_checklist.md 275 B
- references/lessons_registry.md 292 B
- references/local_overlay_contract.md 4.1 KB
- references/metrika/API_REFERENCE.md 2.3 KB
- references/metrika/CONFIG.md 2.4 KB
- references/metrika/CUSTOM_REPORTS.md 2.0 KB
- references/metrika/PERIOD_COMPARISON.md 2.5 KB
- references/metrika/SEARCH_QUERIES.md 2.0 KB
- references/promotion_rules.md 1.0 KB
- references/task_playbooks/00_output_contract.md 5.7 KB
- references/task_playbooks/01_search_negatives_7d.md 1.1 KB
- references/task_playbooks/02_rsy_stop_sites_7d.md 1000 B
- references/task_playbooks/03_creative_outliers_rotation.md 874 B
- references/task_playbooks/04_deep_campaign_review_7d.md 2.6 KB
- references/task_playbooks/05_change_impact_timeline.md 1.7 KB
- references/task_playbooks/06_bids_and_modifiers_review.md 696 B
- references/task_playbooks/07_yougile_hygiene_sync.md 6.7 KB
- references/task_playbooks/08_competitor_search_serp.md 2.7 KB
- references/task_playbooks/09_missing_phrases_growth.md 782 B
- references/task_playbooks/10_extra_control_layers.md 2.0 KB
- references/task_playbooks/11_pre_apply_presentation.md 3.2 KB
- references/task_playbooks/12_wordstat_collection_pipeline.md 325 B
- references/wordstat_collection_framework.md 397 B
- references/yandex_cloud_search_handoffs.md 1.4 KB
- references/yandex_search_api_search_ads_path.md 2.0 KB
- schemas/direct_write_pack.schema.json 3.7 KB
- scripts/apply_ad_failure_point_fix.py 283 B runs code
- scripts/apply_ad_replacement_pack.py 256 B runs code
- scripts/apply_no_moderation_pack.py 267 B runs code
- scripts/apply_search_adgroup_manifest.py 271 B runs code
- scripts/apply_search_marker_review.py 281 B runs code
- scripts/apply_search_negatives_pack.py 255 B runs code
- scripts/apply_shared_negative_set.py 268 B runs code
- scripts/apply_tasks.py 250 B runs code
- scripts/apply_time_targeting_schedule.py 258 B runs code
- scripts/audit_ad_delivery_failures.py 9.8 KB runs code
- scripts/audit_campaign_meta.py 3.2 KB runs code
- scripts/audit_group_ad_copy.py 5.8 KB runs code
- scripts/bootstrap_yougile_workspace.py 17 KB runs code
- scripts/build_creative_rotation_from_outliers.py 295 B runs code
- scripts/build_growth_structure_from_routes.py 280 B runs code
- scripts/build_local_rsya_excluded_sites_pack.py 266 B runs code
- scripts/build_local_search_negatives_pack.py 3.4 KB runs code
- scripts/build_manual_final_pack.py 8.8 KB runs code
- scripts/build_minus_words.py 282 B runs code
- scripts/build_text_rotation_apply_pack_from_tsv.py 14 KB runs code
- scripts/campaign_autotest.py 38 KB runs code
- scripts/change_tracker.py 60 KB runs code
- scripts/check_access_paths.py 19 KB runs code
- scripts/client_context.py 3.3 KB runs code
- scripts/clone_search_groups_to_new_campaign.py 269 B runs code
- scripts/collect_all.py 3.8 KB runs code
- scripts/collect_direct_cabinet_snapshot.py 3.5 KB runs code
- scripts/collect_direct_management_snapshot.py 7.5 KB runs code
- scripts/collect_operational_precheck.py 14 KB runs code
- scripts/deploy_search_campaigns.py 285 B runs code
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 · 28 tokens per session scan A 0683b2e305af
yandex-performance-ops is a skill published in the GitHub repository nebelov/yandex-direct-for-all (21 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 92 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.
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.