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 Belolipetsky/YooKassa-MCP --skill integration-reviewgit clone --depth 1 https://github.com/Belolipetsky/YooKassa-MCPWrote 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/belolipetsky/yookassa-mcp/integration-review)<a href="https://agentmods.dev/skills/belolipetsky/yookassa-mcp/integration-review"><img src="https://agentmods.dev/badge/skills/belolipetsky/yookassa-mcp/integration-review/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/belolipetsky/yookassa-mcp/integration-review"><img src="https://agentmods.dev/badge/skills/belolipetsky/yookassa-mcp/integration-review.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 | $0.00080 | $0.00590 |
| Opus 5 | $0.00040 | $0.00295 |
| Sonnet 5 | $0.00016 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
integration-review 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 10d 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
Ревью интеграции ЮKassa
Порядок проверки
- Прочитай правила репозитория и найди весь платежный контур: клиент, routes/controllers, service, модели, jobs, webhook, конфигурацию, миграции и тесты.
- Получи актуальные документы и операции через MCP. Не считай старые SDK-типы или README источником истины, если они расходятся с OpenAPI/changelog.
- Построй фактический flow от заказа до платежа, webhook, подтверждения, возврата и чека.
- Сравни реализацию с
references/checklist.md. - Если нужны данные магазина, применяй skill
diagnostics; не выполняй живые проверки до подтвержденияtest=true. - Не исправляй код, если пользователь просил только ревью.
Приоритеты
- P0: утечка secret key/PII, вызов write API из клиента, возможность реального денежного действия из тестовой логики, отсутствие проверки суммы/валюты, выдача товара по redirect.
- P1: новый Idempotence-Key при retry, неидемпотентный webhook, неверный переход статуса, неправильный чек/возврат, float для денег, отсутствие server-side API verification.
- P2: неограниченные retries, слабые timeout/логи/метрики, пропущенный негативный тест, смешение test/production конфигурации.
- P3: поддерживаемость, дублирование, неясные имена и устаревшая документация без немедленного риска корректности.
Формат ответа
Сначала перечисли findings по убыванию серьезности. Для каждого укажи:
- приоритет;
- точный файл и короткий диапазон строк;
- конкретный сценарий отказа;
- почему это нарушает контракт ЮKassa или инвариант системы;
- минимальное исправление;
- тест, который доказывает исправление;
- официальный документ/операцию, если вывод зависит от API.
После findings дай:
- вопросы и непроверенные допущения;
- краткую карту фактического flow;
- отсутствующие тесты;
- итоговый release gate:
block,conditional passилиpass.
Если значимых проблем нет, скажи это явно, но перечисли остаточные риски и границы проверки.
What ships with it
2 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.
- 10d ago First seen · 44 lines · 80 tokens per session scan A fa389559bbc9
integration-review is a skill published in the GitHub repository Belolipetsky/YooKassa-MCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 590 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
reviewing-personhog-protocol
The full review process for personhog coordination-protocol changes — leases, fencing, handoffs, supervisors, failure budgets, warming, and changelog semantics. Use before pushing or requesting review on any personhog protocol changeset, when asked for an exhaustive or careful review of personhog code, and after any…
sprr
Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".
ln-41-test-strategy-planner
Plans a risk-based test portfolio and prioritized scenarios without editing tests. Not for test execution or implementation.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
bprr
Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.
vertical-fintech-mobile
Domain-knowledge pack for money on a phone — wallets, payments, custody and signing, transaction lifecycle, KYC/AML gates, and offline reconciliation. The rules that separate a payments app from a CRUD app with a currency symbol: a balance is a claim about a server, an idempotency key must outlive the process that…