cpp-lectures-dev

A project-specific coding workflow for building a system that searches Konstantin Vladimirov's C++ lectures through an MCP server. It tells the agent to implement the approved plan, including the lecture-processing pipeline and its code and tests.

In plain words
What is it for?
Writing and testing the lecture-search project, following its plan, creating task branches, and tracking progress through the project's defined stages.
Why use it?
It keeps implementation tied to a written plan and requires each step to be checked before moving on. It also limits decisions about architecture or paid services that should be confirmed by the user.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/alexvozhak/cpp-lectures-mcp/cpp-lectures-dev
Any agent
npx skills add Alexvozhak/cpp-lectures-mcp --skill cpp-lectures-dev
Clone the repo
git clone --depth 1 https://github.com/Alexvozhak/cpp-lectures-mcp

Made for: Claude Code, Codex.

Per session 238 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00238 $0.01857
Opus 5 $0.00119 $0.00928
Sonnet 5 $0.00048 $0.00371
Haiku 4.5 $0.00024 $0.00186

Measured yesterday against content hash 57693d0dd404, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cpp-lectures-dev 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 yesterday.

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/skills/cpp-lectures-dev/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Исполнитель проекта по лекциям C++

Роль

Проблема: пользователь хочет, чтобы решение реализовывалось самостоятельно, а он только проверял и отвечал на вопросы. Средство: этот скилл выступает исполнителем — пишет код, тесты и фиксирует прогресс сам. Следствие: пользователь вовлекается только на проверках и развилках.

Ты — исполнитель. Ты пишешь код по плану, гоняешь проверки, коммитишь и показываешь результат. Пользователь ревьюит и решает спорное. Не перекладывай на него рутину, но и не принимай в одиночку решения, которые меняют архитектуру или тратят его деньги (платные API) — по ним спрашивай.

План этапов и архитектура лежат в references/plan.md. Стандарт тестов — в references/testing.md. Читай их перед работой, не пересказывай по памяти.

Рабочий цикл на каждом шаге

Проблема: без дисциплины код копится непроверенным и нечистым. Средство: жёсткий цикл на каждую единицу работы. Следствие: каждое изменение проверено и обратимо.

  1. Сверься с планом. Открой references/plan.md, определи текущий этап и его критерий выхода. Бери задачу только текущего этапа.
  2. Ветка git. Создай ветку под задачу (git checkout -b <этап>-<кратко>). Не работай в основной ветке.
  3. Реализуй малыми шагами. Пиши минимальный рабочий кусок, не «весь этап разом».
  4. Тесты вместе с кодом. На каждый кусок логики — тест по стандарту из references/testing.md. Тест пишется не «для галочки», а проверяет поведение, имеющее ценность.
  5. Прогони проверки локально:
    • uv run pytest — тесты зелёные.
    • uv run mypy . — типы без ошибок.
    • линт/формат, если настроен.
  6. Коммит с осмысленным сообщением, описывающим поведение, а не файлы.
  7. Покажи пользователю короткий итог: что сделано, что проверено, какой следующий шаг. Спрашивай только по реальным развилкам.
  8. Сверь критерий выхода этапа перед переходом к следующему. Не выполнен — оставайся.

Инструменты (зафиксировано)

  • uv — окружение и зависимости. Используй uv run <cmd>, uv add <pkg>. Не смешивай с системным pip.
  • pytest — тесты. Структура и фикстуры — по references/testing.md.
  • mypy — статическая проверка типов. Код пишется с аннотациями типов; mypy должен проходить чисто. Типы — часть контракта, не украшение.
  • git — ветка на задачу, частые осмысленные коммиты, основная ветка остаётся зелёной.
  • Python — язык проекта (зафиксировано планом).

Read the full file on GitHub · 80 lines

Files

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.

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.

  1. yesterday First seen · 80 lines · 238 tokens per session scan A 57693d0dd404

Subscribe to this mod's changes

cpp-lectures-dev is a skill published in the GitHub repository Alexvozhak/cpp-lectures-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 238 tokens to every session and 1,857 once invoked, about $0.0012 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens