cheapag — плагин для Claude Code: что делает и как установить
Плагин cheapag для Claude Code перепоручает написание кода дешёвым моделям, оставляя планирование и ревью основной модели. Экономит токены на рутинных задачах через внешний MCP-сервер.
MIT ★ 341 обновлён 2026-11-16
/plugin marketplace add muaaz9329/cheap-ag
/plugin install cheapag@cheap-agentЧто делает cheapag
Плагин передаёт генерацию кода рабочим моделям через MCP-сервер с инструментами delegate, research, reply, jobs и land. Основная модель в Claude Code пишет план и проверяет правки, а черновую реализацию берут внешние исполнители. Доступны пресеты cheapest, balanced и strongest, которые настраивают связку исполнителя и эскалации под выбранного провайдера.
Конфигурация хранится в ~/.config/cheapag/config.json, а локальные параметры репозитория можно задать в cheapag.json. Пользовательские команды /cheapag:allow, /cheapag:model, /cheapag:provider, /cheapag:clean и перехватчик правок /cheapag:hook управляют разрешениями и моделями.
Для работы нужен настроенный аккаунт провайдера вроде OpenRouter, DeepSeek, OpenCode Go или OpenCode Zen, который подключается через команду npx cheap-agent login.
Какие задачи решает
- сократить расход токенов на кодогенерацию в Claude Code
- делегировать черновые правки сторонним моделям
- отслеживать размер системного префикса и кэша сессии
- защитить кодовую базу от прямых правок через хук
Примеры запросов агенту
- /cheapag:status
- /cheapag:allow
- /cheapag:hook
Как установить cheapag
Через маркетплейс плагинов
/plugin marketplace add muaaz9329/cheap-ag/plugin install cheapag@cheap-agentПо шагам, с командами для каждой платформы: Плагины Claude Code: маркетплейсы, установка и как собрать свой
Вопросы о cheapag
Как установить cheapag в Claude Code?
В сессии Claude Code выполните по очереди две команды: /plugin marketplace add muaaz9329/cheap-ag, затем /plugin install cheapag@cheap-agent.
Что делает плагин cheapag?
Он разделяет роли: флагманская модель в Claude Code проектирует решение и проверяет результат, а сторонние дешёвые модели выполняют реализацию через MCP-инструменты.
Что нужно для работы cheapag?
Нужно настроить провайдера (OpenRouter, DeepSeek, OpenCode Go или OpenCode Zen) с помощью команды npx cheap-agent login.
Исходный текст
plugin · MIT
# Cheap Agent plugin for Claude Code Gives Claude the Cheap Agent MCP server (`delegate`, `research`, `reply`, `jobs`, `land`), the plan-writing skill, `/cheapag:status`, and the user-only commands `/cheapag:allow`, `/cheapag:model`, `/cheapag:provider`, `/cheapag:clean` and `/cheapag:hook`. ## Worker models `npx cheap-agent login` asks which worker models to use, after the provider. Each preset picks the implement and escalation models for your provider (OpenCode Go, OpenCode Zen, OpenRouter or DeepSeek): - **cheapest**: the lowest worker spend. Claude takes over more often when the worker fails. - **balanced** (the default): the preset the benchmark measured and recommends. - **strongest**: the strongest cheap models, for when you would rather pay the worker than have Claude take over. Measured on SWE-bench Verified (OpenRouter): Flash's worker cost is about $0.005 per easy task and $0.03 per hard one; GLM-5.3 costs about $0.06 on the hard ones, and there Claude used 1.5x fewer tokens than with Flash, because GLM-5.3's failures cost Claude less to recover from. On the hard tier alone GLM-5.3 showed no gain, so `balanced` keeps Flash everywhere and `strongest` (GLM-5.3 for every task) is opt-in. `cheapest` is the same as `balanced` today. The choice goes into `models` in `~/.config/cheapag/config.json`. Run `npx cheap-agent login --preset <cheapest|balanced|strongest>` to switch without the prompts. `ping` and `cheapag status` show it as `preset=<name>`. For a finer choice, set `models` (`implement`, `research`, `escalation`, `fallback`, as full `provider/model` names) in a repo's `cheapag.json`, which overrides the user config, or in the user config itself; answering `custom` (or `--preset custom`) makes login leave it as you wrote it. Changing the models after `/cheapag:allow` makes the next job ask for it again, with the new list. ## What it costs to keep in context Everything Claude Code loads at session start is sent again on every turn: the system prompt, tool definitions, every enabled skill's description, plugin instructions and CLAUDE.md. A bigger prefix means each turn costs more, and a prefix that changes between sessions is rewritten at full price instead of read from cache. Measured on a real machine (Claude Code 2.1.285), a session that only answers "OK" cost $0.10 with ~100 user plugins and skills enabled, against $0.02–0.04 with only what the task needs. - **Disable plugins you are not using** (`/plugin` → disable). Each enabled plugin adds its skills and instructions to every turn of every session. - **Mark skills you only call by name** with `disable-model-invocation: true` in their `SKILL.md` frontmatter. Their descriptions then stay out of the context. Cheap Agent's `allow`, `clean` and `hook` already do this. - **Keep CLAUDE.md under ~200 lines.** It is part of every turn. Move rarely needed detail into files Claude reads on demand. - **Pin the Claude Code version** (`DISABLE_AUTOUPDATER=1`) during long stretches of work. An update changes the system prompt, so the next session rewrites the whole cached prefix. - **For scripted runs** (`claude -p`): `--setting-sources project` skips user plugins and settings, and `--exclude-dynamic-system-prompt-sections` keeps per-machine details (cwd, git status) out of the cached prefix. The `includeGitInstructions: false` setting drops the commit/PR boilerplate when the agent never commits. `cheapag status` prints the prefix size of this repo's most recent Claude Code session, when its transcript is readable (`claude prefix: 18.4k tokens on the first turn …`). Under ~20k is lean; 40k+ usually means plugins or skills the work doesn't use. ## Sessions, `/clear` and the cache TTL Claude Code caches the session prefix. Every turn that starts within the cache's lifetime reads it at a tenth of the input price, instead of writing it again at more than the input price. How you split work into sessions decides how often you pay the full write. - **One session per block of work.** Starting a fresh `claude` for every small task writes the whole prefix each time. Inside a session it is written once and then read. - **`/clear` between unrelated tasks.** It's free: the prefix stays cached, and only the conversation is dropped. It also keeps old, unrelated context from distracting Claude on the next task. - **Pick the TTL for how you work.** The default 1-hour cache suits all-day work with pauses. For short bursts of back-to-back tasks, `CLAUDE_CODE_PROMPT_CACHE_TTL=5m` makes cache writes cheaper ($5 instead of $8 per million tokens on Opus), as long as you never idle more than five minutes. After a longer pause, the next turn rewrites the prefix. - `cheapag status` shows the last session's cache use: `claude cache: 14 requests, 91% of input from cache, 1h TTL`. A low percentage on a long session means the prefix kept changing (plugins toggled, an update, idle gaps past the TTL). On a Pro or Max plan these are dollar estimates at API prices. Anthropic says cached tokens count less toward plan limits, but publishes no ratio.
© muaaz9329 · MIT · muaaz9329/cheap-ag