Borrowing it
Nothing to install: this file belongs to sergeyfedyakov/v8help-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sergeyfedyakov/v8help-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/sergeyfedyakov/v8help-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/instructions/sergeyfedyakov/v8help-mcp/agents-md)<a href="https://agentmods.dev/instructions/sergeyfedyakov/v8help-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sergeyfedyakov/v8help-mcp/agents-md/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/instructions/sergeyfedyakov/v8help-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sergeyfedyakov/v8help-mcp/agents-md.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 | $0.00524 | $0.00524 |
| Opus 5.5 | $0.00210 | $0.00210 |
| Sonnet 5.5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
v8help-mcp AGENTS.md 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 2mo 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
Проектные инструкции
Индексация Kilo (семантический поиск)
В этом проекте включено индексирование Kilo (см. kilo.jsonc → indexing.enabled: true).
Перед операциями, которые зависят от семантического поиска (semantic_search) или индексации:
- Прочитай
kilo.jsoncи проверьindexing.enabledиindexing.provider. - Провайдер эмбеддинга — LM Studio (OpenAI-совместимый endpoint
http://localhost:1234/v1), модельtext-embedding-qwen3-embedding-0.6b(мультиязычная, 1024 измерения, поддерживает русский). Перед операциями индексации убедись, чтоhttp://localhost:1234/v1/modelsотвечает (GET запрос). - Если не отвечает — запусти
lms server startкак фоновый процесс (инструмент background_process). Процесс автоматически остановится при завершении сессии Kilo. После старта повторно проверь/v1/models; если нужной embedding-модели нет в списке — загрузи её черезlms load <идентификатор>и укажи в запросе. - Проверь, что сервер отдаёт эмбеддинги размерности 1024 (соответствует
indexing.dimension).
Статус "IDX Disabled" (consent в VS Code) — исправлено
Баг был: в VS Code индексация дополнительно управлялась consent (разрешением на проект), а не только indexing.enabled; UI-тумблеры в некоторых версиях расширения (например 7.4.20) consent не выставляли, статус оставался Disabled, а обходной путь через внутренний HTTP-API (PUT /indexing/consent) не персистился между перезапусками.
В текущей версии исправлено: consent ставится автоматически, семантический поиск поднимается при подключении — обходные пути через HTTP-API больше не нужны.
Логи индексации и работы Kilo: ~/.local/share/kilo/log/opencode.log и dev.log.
Кириллица в консоли Windows
PowerShell 5.1 выводит UTF-8 как кракозябры (OEM-кодировка). Это косметика терминала, не дефект кода.
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.
- 2mo ago Changed · -9 lines · -212 tokens per session 1519b5b2c81f
- 2mo ago First seen · 33 lines · 736 tokens per session scan A b9bda95e02af
v8help-mcp AGENTS.md is an instructions file published in the GitHub repository sergeyfedyakov/v8help-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 524 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-08-31.
v8help-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| v8help-mcp AGENTS.mdsergeyfedyakov/v8help-mcp | Instructions file | 0 | 1mo ago | MIT | A | 524 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |