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 theYahia/WWmcp --skill gigachat-embeddingsgit clone --depth 1 https://github.com/theYahia/WWmcpWrote 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/theyahia/wwmcp/gigachat-embeddings)<a href="https://agentmods.dev/skills/theyahia/wwmcp/gigachat-embeddings"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/gigachat-embeddings/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/theyahia/wwmcp/gigachat-embeddings"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/gigachat-embeddings.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 | $0.00030 | $0.00613 |
| Opus 5 | $0.00015 | $0.00307 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
gigachat-embeddings 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.
What it actually says
/gigachat-embeddings — Эмбеддинги GigaChat
Алгоритм
- Собери массив текстов. Если пользователь дал файл — прочитай его и разбей на строки или абзацы; один элемент массива = одна единица, которую будем сравнивать.
- Вызови
get_token_countс model и input (массив текстов) — узнай, сколько токенов уйдёт. Это дешевле, чем упереться в лимит на середине большой партии. - Вызови
embed_textс model = Embeddings и input — массивом текстов. Ответ содержит вектор на каждый текст. - Посчитай косинусную близость между векторами сам — сервер такого инструмента не даёт. Формула: скалярное произведение, делённое на произведение норм.
- Отдай результат под задачу пользователя:
- поиск — топ-N ближайших к запросу;
- дедупликация — пары с близостью выше 0.95;
- кластеризация — группы, где все пары ближе порога.
- Если непонятно, какие модели доступны в этом аккаунте, вызови
list_models.
Формат ответа
## Эмбеддинги GigaChat
**Модель**: Embeddings
**Текстов**: 42
**Токенов**: 3 180
**Размерность вектора**: 1024
### Дубли (близость > 0.95)
| # | Текст A | Текст B | Близость |
|---|---------|---------|----------|
| 1 | «доставка за час» | «доставим за 1 час» | 0.981 |
### Кластеры
1. Доставка (12 текстов)
2. Оплата (8 текстов)
Важно
- Для эмбеддингов модель называется Embeddings, а не GigaChat. Модель для диалога сюда не подходит.
- Векторы от разных моделей несравнимы между собой. Не смешивай выдачи двух прогонов с разными model.
- Большой массив лучше резать на партии — один вызов с сотнями длинных текстов упрётся в лимит запроса.
Примеры
/gigachat-embeddings отзывы.txt найди дубли
/gigachat-embeddings "доставка", "самовывоз", "курьер" — кластеризуй
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 · 60 lines · 30 tokens per session scan A 4706900333a5
gigachat-embeddings is a skill published in the GitHub repository theYahia/WWmcp (29 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 613 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 2026-09-06.
Other skills, from other repositories
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…