What is cpp-lectures-mcp CLAUDE.md?

Repository instructions for cpp-lectures-mcp, a Python project that provides semantic search over C++ lecture transcripts through an MCP server. They describe startup reading, documentation responsibilities, development workflow, and project status.

Use them when developing or maintaining the lecture-search pipeline and its online MCP service.

They tell the agent which project documents to consult and how to work consistently, including coding, testing, type checking, and reporting.

How Alexvozhak/cpp-lectures-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Alexvozhak/cpp-lectures-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.

Copy the file

curl -O https://raw.githubusercontent.com/Alexvozhak/cpp-lectures-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Alexvozhak/cpp-lectures-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alexvozhak/cpp-lectures-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/alexvozhak/cpp-lectures-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/alexvozhak/cpp-lectures-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alexvozhak/cpp-lectures-mcp/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/alexvozhak/cpp-lectures-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alexvozhak/cpp-lectures-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,342 This file is loaded in full into every session.

When invoked 3,342 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03342	$0.03342
Opus 5.5	$0.01337	$0.01337
Sonnet 5.5	$0.00668	$0.00668
Haiku 4.5	$0.00334	$0.00334

Measured 2mo ago against content hash 59ad774779e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cpp-lectures-mcp CLAUDE.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.

CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cpp-lectures-mcp

Семантический поиск по лекциям Константина Владимирова по C++ через MCP-сервер. Соло-проект, Python 3.11+, uv. Два контура: подготовка (офлайн: yt-dlp → Deepgram → Jina → Postgres/pgvector) и обслуживание (онлайн: MCP-сервер отдаёт фрагменты с тайм-кодами, инференс — на стороне клиента).

Роль агента: исполнитель, не навигатор. Пишешь код по плану, гоняешь проверки, коммитишь, показываешь итог. Пользователь ревьюит и решает спорное. Подробно — в скилле cpp-lectures-dev (.claude/skills/cpp-lectures-dev/SKILL.md).

Старт сессии

Прочитать перед работой:

Эту секцию + «Состояние» ниже.
.claude/skills/cpp-lectures-dev/SKILL.md — рабочий цикл и роль (источник истины по тому, КАК работать).
.claude/skills/cpp-lectures-dev/references/plan.md — этапы и архитектура (источник истины по тому, ЧТО строить). Определи текущий этап и его критерий выхода.
.claude/skills/cpp-lectures-dev/references/testing.md — стандарт тестов (читать перед написанием тестов этапа).
Последний docs/sessions/session-NNN-*.md, если есть.

Распределение ответственности по докам

SKILL.md — рабочий цикл (git → код → тесты → pytest/mypy → коммит → итог), роль исполнителя, когда спрашивать пользователя. Источник истины по процессу.
references/plan.md — этапы 0–4, архитектура, модель данных, MCP-ручки, что НЕ делать, открытые вопросы. Источник истины по стратегии. Не пересказывать по памяти — открывать.
references/testing.md — стандарт тестов (невыдуманные, бизнес-ценные, консистентные, чистые фикстуры, мок на границе адаптеров). Источник истины по тестам.
docs/sessions/session-NNN-*.md — полные логи сессий.

Рабочий цикл (кратко; полно — в SKILL.md)

Сверься с plan.md: текущий этап и критерий выхода. 2. Ветка под задачу (git checkout -b <этап>-<кратко>), не в main. 3. Малые шаги. 4. Тест вместе с кодом по testing.md. 5. Локально: uv run pytest + uv run mypy . (+ uv run ruff check). 6. Осмысленный коммит. 7. Короткий итог пользователю. 8. Сверь критерий выхода перед переходом этапа.

Read the full file on GitHub · 92 lines

Changes

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 First seen · 92 lines · 3,342 tokens per session scan A 59ad774779e2

Subscribe to this mod's changes

cpp-lectures-mcp CLAUDE.md is an instructions file published in the GitHub repository Alexvozhak/cpp-lectures-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 3,342 tokens to every session, about $0.0134 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.

C and C++Languages Learning and teaching

cpp-lectures-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cpp-lectures-mcp CLAUDE.mdAlexvozhak/cpp-lectures-mcp	Instructions file	0	3mo ago	MIT	A	3,342	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cpp-lectures-mcp: Instructions file for Claude Code