Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/VKirill/claude-lane-stacknpx agentmods add skills/vkirill/claude-lane-stack/xmlstockWrote 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/vkirill/claude-lane-stack/xmlstock)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/xmlstock"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/xmlstock/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/vkirill/claude-lane-stack/xmlstock"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/xmlstock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00383 | $0.05803 |
| Opus 5 | $0.00192 | $0.02901 |
| Sonnet 5 | $0.00077 | $0.01161 |
| Haiku 4.5 | $0.00038 | $0.00580 |
Grade A, and why
xmlstock 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 Version Requirements (August 2026)
Primary pins:
- xmlstock API:
docs-only (stable JSON/XML REST, no version path; https://xmlstock.com/{yandex|yandexlive|google}/{xml|json|html}/) - Python:
3.14.x - Node.js:
24.x (Active LTS)
Source of truth: STACK_VERSIONS.md — verified 2026-08-24
Usage
Loaded automatically when its description matches the active task. Read only the section you need, then follow the link to the relevant reference file for full detail.
Use this skill when
- Парсинг позиций сайта в Яндексе или Google по списку ключей с региональностью (
lr=,domain=,device=) - Проверка индексации страниц / количества проиндексированных страниц через
query=site:domain.com - Сбор SERP-снапшотов (ТОП-10/50/100) для аналитики, мониторинга конкурентов, кластеризации
- Парсинг живой выдачи Яндекса с дополнительными блоками: реклама Яндекс.Директ (
ads=1), товарная карусель (scroller=1), Related Searches (related=1) - Парсинг Яндекс/Google картинок (
tbm=images), Google новостей (tbm=news), видео (tbm=video) - Обратный поиск по картинкам в Яндексе через
query=image:URL+tbm=images - Замена прямого скрапинга через прокси/решение капч на стабильный API за ~18 руб/1000 запросов (≈100× дешевле официального Yandex Search API)
- Интеграция Key Collector / Topvisor / Site-Control / Topsite через готовый URL
https://xmlstock.com/{engine}/xml/?user=...&key=... - Building a Python / Node.js client с async-polling req_id, dedup, balance pre-check, retry на 210/202 с exponential backoff
- Asynchronous (
delayed=1) batch SERP parsing для больших объёмов с гибким контролем (нет квот, только пропускная способность их сервера)
Do not use this skill when
- Сбор частотностей / уровня конкуренции / Wordstat — это не делает xmlstock. Использовать
mutagen(cascade marker) для wordstat_qso иstrong - Собственный скрапер SERP через прокси / разгадывание капч — на масштабах >5к запросов это дороже и менее стабильно. Если запросов очень мало (<100/мес) — пользователь не обязан подключать сторонний сервис; для прокси —
proxy6(cascade marker) - Других поисковиков: Bing, DuckDuckGo, Baidu — xmlstock поддерживает только Яндекс и Google
- Прямой Yandex Search API (api.search.yandex.ru) — другой endpoint, другие цены, другая аутентификация. Этот скилл — про reseller xmlstock, а не про официальный API
- Google Custom Search JSON API (CSE) — другой surface, JSON-only, 100 бесплатных/день; разные параметры
- Использование собранных данных downstream (HTTP-плeerинг, БД, аналитика) — это работа runtime-скиллов (
httpx,nodejs,postgresql) - Парсинг SERP-фич сложнее базовых блоков (People Also Ask с раскрытием, Knowledge Graph, Featured Snippets с разметкой) — xmlstock возвращает только то, что описано; для подобного — SerpApi/DataForSEO (другие сервисы, дороже)
What ships with it
8 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.
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.
- 5d ago First seen · 212 lines · 383 tokens per session scan A 9bd03e180a15
xmlstock is a skill published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed yesterday), licensed MIT. It adds 383 tokens to every session and 5,803 once invoked, about $0.0019 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 2026-09-05.
Other skills, from other repositories
afc:release-notes
Generate release notes from git history.
afc:clean
Pipeline artifact cleanup and codebase hygiene.
afc:consult
Expert consultation — backend, infra, PM, design, marketing, legal, or tech guidance.
afc:issue
Analyze GitHub issue — investigate bug reports, understand requirements, inspect issues.
afc:launch
Generate release artifacts — version bump, changelog, release tags.
afc:learner
Review and promote learned patterns to project rules.